MediaMetz/gemini-cli
1
0
Fork 0
mirror of https://github.com/google-gemini/gemini-cli.git synced 2026-04-17 08:41:19 -07:00
Code Issues Packages Projects Releases Wiki Activity

docs(teleporter): append productionization roadmap to TELEPORTATION.md

Browse Source
This commit is contained in:
Sehoon Shon
2026-02-24 17:07:52 -05:00
parent f79a34a81a
commit b0b6ebf574
8 changed files with 66036 additions and 32815 deletions
Download Patch File Download Diff File Expand all files Collapse all files

302
packages/core/src/skills/builtin/skill-creator/SKILL.md
View File

@@ -1,6 +1,9 @@
---
name: skill-creator
description: Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Gemini CLI's capabilities with specialized knowledge, workflows, or tool integrations.
description:
Guide for creating effective skills. This skill should be used when users want
to create a new skill (or update an existing skill) that extends Gemini CLI's
capabilities with specialized knowledge, workflows, or tool integrations.
---
# Skill Creator
@@ -9,22 +12,33 @@ This skill provides guidance for creating effective skills.
## About Skills
Skills are modular, self-contained packages that extend Gemini CLI's capabilities by providing specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific domains or tasks—they transform Gemini CLI from a general-purpose agent into a specialized agent equipped with procedural knowledge that no model can fully possess.
Skills are modular, self-contained packages that extend Gemini CLI's
capabilities by providing specialized knowledge, workflows, and tools. Think of
them as "onboarding guides" for specific domains or tasks—they transform Gemini
CLI from a general-purpose agent into a specialized agent equipped with
procedural knowledge that no model can fully possess.
### What Skills Provide
1. Specialized workflows - Multi-step procedures for specific domains
2. Tool integrations - Instructions for working with specific file formats or APIs
2. Tool integrations - Instructions for working with specific file formats or
APIs
3. Domain expertise - Company-specific knowledge, schemas, business logic
4. Bundled resources - Scripts, references, and assets for complex and repetitive tasks
4. Bundled resources - Scripts, references, and assets for complex and
repetitive tasks
## Core Principles
### Concise is Key
The context window is a public good. Skills share the context window with everything else Gemini CLI needs: system prompt, conversation history, other Skills' metadata, and the actual user request.
The context window is a public good. Skills share the context window with
everything else Gemini CLI needs: system prompt, conversation history, other
Skills' metadata, and the actual user request.
**Default assumption: Gemini CLI is already very smart.** Only add context Gemini CLI doesn't already have. Challenge each piece of information: "Does Gemini CLI really need this explanation?" and "Does this paragraph justify its token cost?"
**Default assumption: Gemini CLI is already very smart.** Only add context
Gemini CLI doesn't already have. Challenge each piece of information: "Does
Gemini CLI really need this explanation?" and "Does this paragraph justify its
token cost?"
Prefer concise examples over verbose explanations.
@@ -32,13 +46,19 @@ Prefer concise examples over verbose explanations.
Match the level of specificity to the task's fragility and variability:
**High freedom (text-based instructions)**: Use when multiple approaches are valid, decisions depend on context, or heuristics guide the approach.
**High freedom (text-based instructions)**: Use when multiple approaches are
valid, decisions depend on context, or heuristics guide the approach.
**Medium freedom (pseudocode or scripts with parameters)**: Use when a preferred pattern exists, some variation is acceptable, or configuration affects behavior.
**Medium freedom (pseudocode or scripts with parameters)**: Use when a preferred
pattern exists, some variation is acceptable, or configuration affects behavior.
**Low freedom (specific scripts, few parameters)**: Use when operations are fragile and error-prone, consistency is critical, or a specific sequence must be followed.
**Low freedom (specific scripts, few parameters)**: Use when operations are
fragile and error-prone, consistency is critical, or a specific sequence must be
followed.
Think of Gemini CLI as exploring a path: a narrow bridge with cliffs needs specific guardrails (low freedom), while an open field allows many routes (high freedom).
Think of Gemini CLI as exploring a path: a narrow bridge with cliffs needs
specific guardrails (low freedom), while an open field allows many routes (high
freedom).
### Anatomy of a Skill
@@ -61,45 +81,75 @@ skill-name/
Every SKILL.md consists of:
- **Frontmatter** (YAML): Contains `name` and `description` fields. These are the only fields that Gemini CLI reads to determine when the skill gets used, thus it is very important to be clear and comprehensive in describing what the skill is, and when it should be used.
- **Body** (Markdown): Instructions and guidance for using the skill. Only loaded AFTER the skill triggers (if at all).
- **Frontmatter** (YAML): Contains `name` and `description` fields. These are
the only fields that Gemini CLI reads to determine when the skill gets used,
thus it is very important to be clear and comprehensive in describing what the
skill is, and when it should be used.
- **Body** (Markdown): Instructions and guidance for using the skill. Only
loaded AFTER the skill triggers (if at all).
#### Bundled Resources (optional)
##### Scripts (`scripts/`)
Executable code (Node.js/Python/Bash/etc.) for tasks that require deterministic reliability or are repeatedly rewritten.
Executable code (Node.js/Python/Bash/etc.) for tasks that require deterministic
reliability or are repeatedly rewritten.
- **When to include**: When the same code is being rewritten repeatedly or deterministic reliability is needed
- **When to include**: When the same code is being rewritten repeatedly or
deterministic reliability is needed
- **Example**: `scripts/rotate_pdf.cjs` for PDF rotation tasks
- **Benefits**: Token efficient, deterministic, may be executed without loading into context
- **Agentic Ergonomics**: Scripts must output LLM-friendly stdout. Suppress standard tracebacks. Output clear, concise success/failure messages, and paginate or truncate outputs (e.g., "Success: First 50 lines of processed file...") to prevent context window overflow.
- **Note**: Scripts may still need to be read by Gemini CLI for patching or environment-specific adjustments
- **Benefits**: Token efficient, deterministic, may be executed without loading
into context
- **Agentic Ergonomics**: Scripts must output LLM-friendly stdout. Suppress
standard tracebacks. Output clear, concise success/failure messages, and
paginate or truncate outputs (e.g., "Success: First 50 lines of processed
file...") to prevent context window overflow.
- **Note**: Scripts may still need to be read by Gemini CLI for patching or
environment-specific adjustments
##### References (`references/`)
Documentation and reference material intended to be loaded as needed into context to inform Gemini CLI's process and thinking.
Documentation and reference material intended to be loaded as needed into
context to inform Gemini CLI's process and thinking.
- **When to include**: For documentation that Gemini CLI should reference while working
- **Examples**: `references/finance.md` for financial schemas, `references/mnda.md` for company NDA template, `references/policies.md` for company policies, `references/api_docs.md` for API specifications
- **Use cases**: Database schemas, API documentation, domain knowledge, company policies, detailed workflow guides
- **Benefits**: Keeps SKILL.md lean, loaded only when Gemini CLI determines it's needed
- **Best practice**: If files are large (>10k words), include grep search patterns in SKILL.md
- **When to include**: For documentation that Gemini CLI should reference while
working
- **Examples**: `references/finance.md` for financial schemas,
`references/mnda.md` for company NDA template, `references/policies.md` for
company policies, `references/api_docs.md` for API specifications
- **Use cases**: Database schemas, API documentation, domain knowledge, company
policies, detailed workflow guides
- **Benefits**: Keeps SKILL.md lean, loaded only when Gemini CLI determines it's
needed
- **Best practice**: If files are large (>10k words), include grep search
patterns in SKILL.md
- **Avoid duplication**: Information should live in either SKILL.md or
references files, not both. Prefer references files for detailed information unless it's truly core to the skill—this keeps SKILL.md lean while making information discoverable without hogging the context window. Keep only essential procedural instructions and workflow guidance in SKILL.md; move detailed reference material, schemas, and examples to references files.
references files, not both. Prefer references files for detailed information
unless it's truly core to the skill—this keeps SKILL.md lean while making
information discoverable without hogging the context window. Keep only
essential procedural instructions and workflow guidance in SKILL.md; move
detailed reference material, schemas, and examples to references files.
##### Assets (`assets/`)
Files not intended to be loaded into context, but rather used within the output Gemini CLI produces.
Files not intended to be loaded into context, but rather used within the output
Gemini CLI produces.
- **When to include**: When the skill needs files that will be used in the final output
- **Examples**: `assets/logo.png` for brand assets, `assets/slides.pptx` for PowerPoint templates, `assets/frontend-template/` for HTML/React boilerplate, `assets/font.ttf` for typography
- **Use cases**: Templates, images, icons, boilerplate code, fonts, sample documents that get copied or modified
- **Benefits**: Separates output resources from documentation, enables Gemini CLI to use files without loading them into context
- **When to include**: When the skill needs files that will be used in the final
output
- **Examples**: `assets/logo.png` for brand assets, `assets/slides.pptx` for
PowerPoint templates, `assets/frontend-template/` for HTML/React boilerplate,
`assets/font.ttf` for typography
- **Use cases**: Templates, images, icons, boilerplate code, fonts, sample
documents that get copied or modified
- **Benefits**: Separates output resources from documentation, enables Gemini
CLI to use files without loading them into context
#### What to Not Include in a Skill
A skill should only contain essential files that directly support its functionality. Do NOT create extraneous documentation or auxiliary files, including:
A skill should only contain essential files that directly support its
functionality. Do NOT create extraneous documentation or auxiliary files,
including:
- README.md
- INSTALLATION_GUIDE.md
@@ -107,7 +157,10 @@ A skill should only contain essential files that directly support its functional
- CHANGELOG.md
- etc.
The skill should only contain the information needed for an AI agent to do the job at hand. It should not contain auxiliary context about the process that went into creating it, setup and testing procedures, user-facing documentation, etc. Creating additional documentation files just adds clutter and confusion.
The skill should only contain the information needed for an AI agent to do the
job at hand. It should not contain auxiliary context about the process that went
into creating it, setup and testing procedures, user-facing documentation, etc.
Creating additional documentation files just adds clutter and confusion.
### Progressive Disclosure Design Principle
@@ -115,13 +168,21 @@ Skills use a three-level loading system to manage context efficiently:
1. **Metadata (name + description)** - Always in context (~100 words)
2. **SKILL.md body** - When skill triggers (<5k words)
3. **Bundled resources** - As needed by Gemini CLI (Unlimited because scripts can be executed without reading into context window)
3. **Bundled resources** - As needed by Gemini CLI (Unlimited because scripts
can be executed without reading into context window)
#### Progressive Disclosure Patterns
Keep SKILL.md body to the essentials and under 500 lines to minimize context bloat. Split content into separate files when approaching this limit. When splitting out content into other files, it is very important to reference them from SKILL.md and describe clearly when to read them, to ensure the reader of the skill knows they exist and when to use them.
Keep SKILL.md body to the essentials and under 500 lines to minimize context
bloat. Split content into separate files when approaching this limit. When
splitting out content into other files, it is very important to reference them
from SKILL.md and describe clearly when to read them, to ensure the reader of
the skill knows they exist and when to use them.
**Key principle:** When a skill supports multiple variations, frameworks, or options, keep only the core workflow and selection guidance in SKILL.md. Move variant-specific details (patterns, examples, configuration) into separate reference files.
**Key principle:** When a skill supports multiple variations, frameworks, or
options, keep only the core workflow and selection guidance in SKILL.md. Move
variant-specific details (patterns, examples, configuration) into separate
reference files.
**Pattern 1: High-level guide with references**
@@ -143,7 +204,8 @@ Gemini CLI loads FORMS.md, REFERENCE.md, or EXAMPLES.md only when needed.
**Pattern 2: Domain-specific organization**
For Skills with multiple domains, organize content by domain to avoid loading irrelevant context:
For Skills with multiple domains, organize content by domain to avoid loading
irrelevant context:
```
bigquery-skill/
@@ -157,7 +219,8 @@ bigquery-skill/
When a user asks about sales metrics, Gemini CLI only reads sales.md.
Similarly, for skills supporting multiple frameworks or variants, organize by variant:
Similarly, for skills supporting multiple frameworks or variants, organize by
variant:
```
cloud-deploy/
@@ -183,15 +246,20 @@ Use pandas for loading and basic queries. See [PANDAS.md](PANDAS.md).
## Advanced Operations
For massive files that exceed memory, see [STREAMING.md](STREAMING.md). For timestamp normalization, see [TIMESTAMPS.md](TIMESTAMPS.md).
For massive files that exceed memory, see [STREAMING.md](STREAMING.md). For
timestamp normalization, see [TIMESTAMPS.md](TIMESTAMPS.md).
Gemini CLI reads REDLINING.md or OOXML.md only when the user needs those features.
Gemini CLI reads REDLINING.md or OOXML.md only when the user needs those
features.
```
**Important guidelines:**
- **Avoid deeply nested references** - Keep references one level deep from SKILL.md. All reference files should link directly from SKILL.md.
- **Structure longer reference files** - For files longer than 100 lines, include a table of contents at the top so Gemini CLI can see the full scope when previewing.
- **Avoid deeply nested references** - Keep references one level deep from
SKILL.md. All reference files should link directly from SKILL.md.
- **Structure longer reference files** - For files longer than 100 lines,
include a table of contents at the top so Gemini CLI can see the full scope
when previewing.
## Skill Creation Process
@@ -205,66 +273,93 @@ Skill creation involves these steps:
6. Install and reload the skill
7. Iterate based on real usage
Follow these steps in order, skipping only if there is a clear reason why they are not applicable.
Follow these steps in order, skipping only if there is a clear reason why they
are not applicable.
### Skill Naming
- Use lowercase letters, digits, and hyphens only; normalize user-provided titles to hyphen-case (e.g., "Plan Mode" -> `plan-mode`).
- When generating names, generate a name under 64 characters (letters, digits, hyphens).
- Use lowercase letters, digits, and hyphens only; normalize user-provided
titles to hyphen-case (e.g., "Plan Mode" -> `plan-mode`).
- When generating names, generate a name under 64 characters (letters, digits,
hyphens).
- Prefer short, verb-led phrases that describe the action.
- Namespace by tool when it improves clarity or triggering (e.g., `gh-address-comments`, `linear-address-issue`).
- Namespace by tool when it improves clarity or triggering (e.g.,
`gh-address-comments`, `linear-address-issue`).
- Name the skill folder exactly after the skill name.
### Step 1: Understanding the Skill with Concrete Examples
Skip this step only when the skill's usage patterns are already clearly understood. It remains valuable even when working with an existing skill.
Skip this step only when the skill's usage patterns are already clearly
understood. It remains valuable even when working with an existing skill.
To create an effective skill, clearly understand concrete examples of how the skill will be used. This understanding can come from either direct user examples or generated examples that are validated with user feedback.
To create an effective skill, clearly understand concrete examples of how the
skill will be used. This understanding can come from either direct user examples
or generated examples that are validated with user feedback.
For example, when building an image-editor skill, relevant questions include:
- "What functionality should the image-editor skill support? Editing, rotating, anything else?"
- "What functionality should the image-editor skill support? Editing, rotating,
anything else?"
- "Can you give some examples of how this skill would be used?"
- "I can imagine users asking for things like 'Remove the red-eye from this image' or 'Rotate this image'. Are there other ways you imagine this skill being used?"
- "I can imagine users asking for things like 'Remove the red-eye from this
image' or 'Rotate this image'. Are there other ways you imagine this skill
being used?"
- "What would a user say that should trigger this skill?"
**Avoid interrogation loops:** Do not ask more than one or two clarifying questions at a time. Bias toward action: propose a concrete list of features or examples based on your initial understanding, and ask the user to refine them.
**Avoid interrogation loops:** Do not ask more than one or two clarifying
questions at a time. Bias toward action: propose a concrete list of features or
examples based on your initial understanding, and ask the user to refine them.
Conclude this step when there is a clear sense of the functionality the skill should support.
Conclude this step when there is a clear sense of the functionality the skill
should support.
### Step 2: Planning the Reusable Skill Contents
To turn concrete examples into an effective skill, analyze each example by:
1. Considering how to execute on the example from scratch
2. Identifying what scripts, references, and assets would be helpful when executing these workflows repeatedly
2. Identifying what scripts, references, and assets would be helpful when
executing these workflows repeatedly
Example: When building a `pdf-editor` skill to handle queries like "Help me rotate this PDF," the analysis shows:
Example: When building a `pdf-editor` skill to handle queries like "Help me
rotate this PDF," the analysis shows:
1. Rotating a PDF requires re-writing the same code each time
2. A `scripts/rotate_pdf.cjs` script would be helpful to store in the skill
Example: When designing a `frontend-webapp-builder` skill for queries like "Build me a todo app" or "Build me a dashboard to track my steps," the analysis shows:
Example: When designing a `frontend-webapp-builder` skill for queries like
"Build me a todo app" or "Build me a dashboard to track my steps," the analysis
shows:
1. Writing a frontend webapp requires the same boilerplate HTML/React each time
2. An `assets/hello-world/` template containing the boilerplate HTML/React project files would be helpful to store in the skill
2. An `assets/hello-world/` template containing the boilerplate HTML/React
project files would be helpful to store in the skill
Example: When building a `big-query` skill to handle queries like "How many users have logged in today?" the analysis shows:
Example: When building a `big-query` skill to handle queries like "How many
users have logged in today?" the analysis shows:
1. Querying BigQuery requires re-discovering the table schemas and relationships each time
2. A `references/schema.md` file documenting the table schemas would be helpful to store in the skill
1. Querying BigQuery requires re-discovering the table schemas and relationships
each time
2. A `references/schema.md` file documenting the table schemas would be helpful
to store in the skill
To establish the skill's contents, analyze each concrete example to create a list of the reusable resources to include: scripts, references, and assets.
To establish the skill's contents, analyze each concrete example to create a
list of the reusable resources to include: scripts, references, and assets.
### Step 3: Initializing the Skill
At this point, it is time to actually create the skill.
Skip this step only if the skill being developed already exists, and iteration or packaging is needed. In this case, continue to the next step.
Skip this step only if the skill being developed already exists, and iteration
or packaging is needed. In this case, continue to the next step.
When creating a new skill from scratch, always run the `init_skill.cjs` script. The script conveniently generates a new template skill directory that automatically includes everything a skill requires, making the skill creation process much more efficient and reliable.
When creating a new skill from scratch, always run the `init_skill.cjs` script.
The script conveniently generates a new template skill directory that
automatically includes everything a skill requires, making the skill creation
process much more efficient and reliable.
**Note:** Use the absolute path to the script as provided in the `available_resources` section.
**Note:** Use the absolute path to the script as provided in the
`available_resources` section.
Usage:
@@ -277,30 +372,48 @@ The script:
- Creates the skill directory at the specified path
- Generates a SKILL.md template with proper frontmatter and TODO placeholders
- Creates example resource directories: `scripts/`, `references/`, and `assets/`
- Adds example files (`scripts/example_script.cjs`, `references/example_reference.md`, `assets/example_asset.txt`) that can be customized or deleted
- Adds example files (`scripts/example_script.cjs`,
`references/example_reference.md`, `assets/example_asset.txt`) that can be
customized or deleted
After initialization, customize or remove the generated SKILL.md and example files as needed.
After initialization, customize or remove the generated SKILL.md and example
files as needed.
### Step 4: Edit the Skill
When editing the (newly-generated or existing) skill, remember that the skill is being created for another instance of Gemini CLI to use. Include information that would be beneficial and non-obvious to Gemini CLI. Consider what procedural knowledge, domain-specific details, or reusable assets would help another Gemini CLI instance execute these tasks more effectively.
When editing the (newly-generated or existing) skill, remember that the skill is
being created for another instance of Gemini CLI to use. Include information
that would be beneficial and non-obvious to Gemini CLI. Consider what procedural
knowledge, domain-specific details, or reusable assets would help another Gemini
CLI instance execute these tasks more effectively.
#### Learn Proven Design Patterns
Consult these helpful guides based on your skill's needs:
- **Multi-step processes**: See references/workflows.md for sequential workflows and conditional logic
- **Specific output formats or quality standards**: See references/output-patterns.md for template and example patterns
- **Multi-step processes**: See references/workflows.md for sequential workflows
and conditional logic
- **Specific output formats or quality standards**: See
references/output-patterns.md for template and example patterns
These files contain established best practices for effective skill design.
#### Start with Reusable Skill Contents
To begin implementation, start with the reusable resources identified above: `scripts/`, `references/`, and `assets/` files. Note that this step may require user input. For example, when implementing a `brand-guidelines` skill, the user may need to provide brand assets or templates to store in `assets/`, or documentation to store in `references/`.
To begin implementation, start with the reusable resources identified above:
`scripts/`, `references/`, and `assets/` files. Note that this step may require
user input. For example, when implementing a `brand-guidelines` skill, the user
may need to provide brand assets or templates to store in `assets/`, or
documentation to store in `references/`.
Added scripts must be tested by actually running them to ensure there are no bugs and that the output matches what is expected. If there are many similar scripts, only a representative sample needs to be tested to ensure confidence that they all work while balancing time to completion.
Added scripts must be tested by actually running them to ensure there are no
bugs and that the output matches what is expected. If there are many similar
scripts, only a representative sample needs to be tested to ensure confidence
that they all work while balancing time to completion.
Any example files and directories not needed for the skill should be deleted. The initialization script creates example files in `scripts/`, `references/`, and `assets/` to demonstrate structure, but most skills won't need all of them.
Any example files and directories not needed for the skill should be deleted.
The initialization script creates example files in `scripts/`, `references/`,
and `assets/` to demonstrate structure, but most skills won't need all of them.
#### Update SKILL.md
@@ -311,11 +424,17 @@ Any example files and directories not needed for the skill should be deleted. Th
Write the YAML frontmatter with `name` and `description`:
- `name`: The skill name
- `description`: This is the primary triggering mechanism for your skill, and helps Gemini CLI understand when to use the skill.
- Include both what the Skill does and specific triggers/contexts for when to use it.
- **Must be a single-line string** (e.g., `description: Data ingestion...`). Quotes are optional.
- Include all "when to use" information here - Not in the body. The body is only loaded after triggering, so "When to Use This Skill" sections in the body are not helpful to Gemini CLI.
- Example: `description: Data ingestion, cleaning, and transformation for tabular data. Use when Gemini CLI needs to work with CSV/TSV files to analyze large datasets, normalize schemas, or merge sources.`
- `description`: This is the primary triggering mechanism for your skill, and
helps Gemini CLI understand when to use the skill.
- Include both what the Skill does and specific triggers/contexts for when to
use it.
- **Must be a single-line string** (e.g., `description: Data ingestion...`).
Quotes are optional.
- Include all "when to use" information here - Not in the body. The body is
only loaded after triggering, so "When to Use This Skill" sections in the
body are not helpful to Gemini CLI.
- Example:
`description: Data ingestion, cleaning, and transformation for tabular data. Use when Gemini CLI needs to work with CSV/TSV files to analyze large datasets, normalize schemas, or merge sources.`
Do not include any other fields in YAML frontmatter.
@@ -325,9 +444,13 @@ Write instructions for using the skill and its bundled resources.
### Step 5: Packaging a Skill
Once development of the skill is complete, it must be packaged into a distributable .skill file that gets shared with the user. The packaging process automatically validates the skill first (checking YAML and ensuring no TODOs remain) to ensure it meets all requirements:
Once development of the skill is complete, it must be packaged into a
distributable .skill file that gets shared with the user. The packaging process
automatically validates the skill first (checking YAML and ensuring no TODOs
remain) to ensure it meets all requirements:
**Note:** Use the absolute path to the script as provided in the `available_resources` section.
**Note:** Use the absolute path to the script as provided in the
`available_resources` section.
```bash
node <path-to-skill-creator>/scripts/package_skill.cjs <path/to/skill-folder>
@@ -347,15 +470,22 @@ The packaging script will:
- Description completeness and quality
- File organization and resource references
2. **Package** the skill if validation passes, creating a .skill file named after the skill (e.g., `my-skill.skill`) that includes all files and maintains the proper directory structure for distribution. The .skill file is a zip file with a .skill extension.
2. **Package** the skill if validation passes, creating a .skill file named
after the skill (e.g., `my-skill.skill`) that includes all files and
maintains the proper directory structure for distribution. The .skill file is
a zip file with a .skill extension.
If validation fails, the script will report the errors and exit without creating a package. Fix any validation errors and run the packaging command again.
If validation fails, the script will report the errors and exit without creating
a package. Fix any validation errors and run the packaging command again.
### Step 6: Installing and Reloading a Skill
Once the skill is packaged into a `.skill` file, offer to install it for the user. Ask whether they would like to install it locally in the current folder (workspace scope) or at the user level (user scope).
Once the skill is packaged into a `.skill` file, offer to install it for the
user. Ask whether they would like to install it locally in the current folder
(workspace scope) or at the user level (user scope).
If the user agrees to an installation, perform it immediately using the `run_shell_command` tool:
If the user agrees to an installation, perform it immediately using the
`run_shell_command` tool:
- **Locally (workspace scope)**:
```bash
@@ -366,13 +496,19 @@ If the user agrees to an installation, perform it immediately using the `run_she
gemini skills install <path/to/skill-name.skill> --scope user
```
**Important:** After the installation is complete, notify the user that they MUST manually execute the `/skills reload` command in their interactive Gemini CLI session to enable the new skill. They can then verify the installation by running `/skills list`.
**Important:** After the installation is complete, notify the user that they
MUST manually execute the `/skills reload` command in their interactive Gemini
CLI session to enable the new skill. They can then verify the installation by
running `/skills list`.
Note: You (the agent) cannot execute the `/skills reload` command yourself; it must be done by the user in an interactive instance of Gemini CLI. Do not attempt to run it on their behalf.
Note: You (the agent) cannot execute the `/skills reload` command yourself; it
must be done by the user in an interactive instance of Gemini CLI. Do not
attempt to run it on their behalf.
### Step 7: Iterate
After testing the skill, users may request improvements. Often this happens right after using the skill, with fresh context of how the skill performed.
After testing the skill, users may request improvements. Often this happens
right after using the skill, with fresh context of how the skill performed.
**Iteration workflow:**

194
packages/core/src/teleportation/TELEPORTATION.md
View File

@@ -28,7 +28,19 @@ dedicated teleporter bundle:
teleporter's `trajectoryToJson` function, which outputs a standard JavaScript
object.
## 3. Conversion Logic
## 3. Workspace Identification
To filter sessions by the user's active workspace, the CLI attempts to read the
target workspace from the trajectory.
1. **Primary**: It reads `metadata.workspaces[0].workspaceFolderAbsoluteUri`
from the top-level trajectory metadata. This is the authoritative data
populated by the Jetski Go backend.
2. **Fallback**: For older trajectories without top-level metadata, it attempts
to extract `workspaceUri` from the first user input's
`activeUserState.activeDocument` context.
## 4. Conversion Logic
The conversion layer
([converter.ts](file:///Users/sshon/developments/gemini-cli/packages/core/src/teleportation/converter.ts))
@@ -43,9 +55,82 @@ translates the technical "Steps" of an Antigravity trajectory into the CLI's
and populates the `thoughts` array in the CLI record, preserving the model's
logic.
- **Tool Calls**: Maps Antigravity tool execution steps to CLI `ToolCallRecord`
objects, including status mapping (Success/Error) and argument parsing.
objects. The integration handles these in three main categories:
## 4. Session Resumption
| Tool Capability | Gemini CLI Tool | Jetski Protobuf Step | Teleportation Status |
| :------------------- | :------------------------------------- | :---------------------------------------------- | :----------------------- |
| **Read File** | `read_file` | `CORTEX_STEP_TYPE_VIEW_FILE` | ✅ Native Mapping |
| **List Directory** | `ls` | `CORTEX_STEP_TYPE_LIST_DIRECTORY` | ✅ Native Mapping |
| **Search Code** | `grep_search` | `CORTEX_STEP_TYPE_GREP_SEARCH` | ✅ Native Mapping |
| **Edit File** | `replace` | `CORTEX_STEP_TYPE_FILE_CHANGE` | ✅ Native Mapping |
| **Search Web** | `google_web_search` | `CORTEX_STEP_TYPE_SEARCH_WEB` | ✅ Native Mapping |
| **Execute Shell** | `run_shell_command` | `CORTEX_STEP_TYPE_RUN_COMMAND` | ✅ Native Mapping |
| **Browser Agent** | _N/A_ \* | `CORTEX_STEP_TYPE_BROWSER_SUBAGENT` | ❌ Dropped |
| **User Input** | `ask_user` | `CORTEX_STEP_TYPE_GENERIC` | ⚠️ Generic / MCP |
| **Read URL Content** | `web_fetch` | `CORTEX_STEP_TYPE_READ_URL_CONTENT` | ❌ Dropped |
| **Find Files** | `glob` | `CORTEX_STEP_TYPE_FIND` | ❌ Dropped |
| **Write File** | `write_file` | `CORTEX_STEP_TYPE_WRITE_TO_FILE` | ❌ Dropped |
| **Read Many Files** | `read_many_files` | `CORTEX_STEP_TYPE_GENERIC` | ⚠️ Generic / MCP |
| **Write Todos** | `write_todos` | `CORTEX_STEP_TYPE_GENERIC` | ⚠️ Generic / MCP |
| **Save Memory** | `save_memory` | `CORTEX_STEP_TYPE_GENERIC` | ⚠️ Generic / MCP |
| **Docs/Skills** | `get_internal_docs` & `activate_skill` | `CORTEX_STEP_TYPE_GENERIC` | ⚠️ Generic / MCP |
| **Plan Mode** | `enter_plan_mode` & `exit_plan_mode` | `CORTEX_STEP_TYPE_GENERIC` | ⚠️ Generic / MCP |
| **IDE Actions** | _N/A_ | `VIEW_CODE_ITEM`, `LINT_DIFF`, `ADD_ANNOTATION` | 🚫 Jetski Only (Dropped) |
**1. Native Mappings** Antigravity has specific protobuf message types for
common tool calls, which map directly to the CLI's native tools:
- `CORTEX_STEP_TYPE_VIEW_FILE` -> `read_file`
- `CORTEX_STEP_TYPE_LIST_DIRECTORY` -> `ls`
- `CORTEX_STEP_TYPE_GREP_SEARCH` -> `grep_search`
- `CORTEX_STEP_TYPE_RUN_COMMAND` -> `run_shell_command`
- `CORTEX_STEP_TYPE_FILE_CHANGE` -> `replace`
- `CORTEX_STEP_TYPE_BROWSER_SUBAGENT` -> (Dropped)
**2. Generic & MCP Integrations** Jetski uses `CORTEX_STEP_TYPE_GENERIC` to
handle dynamic or MCP (Model Context Protocol) tool calls that are not hardcoded
into the native protobuf schema.
- The CLI reads the `toolName` and `argsJson` directly from the generic step
payload and executes them as-is (e.g. `ask_user`, `mcp_*` tools).
**3. Unsupported Tools** Many isolated actions, sub-agent tools, and
IDE-specific UI interactions are dropped by the teleporter to maintain strict
CLI compatibility and preserve valid context-window state.
<details>
<summary><b>Click to view exhaustive list of all 75+ dropped Jetski steps</b></summary>
Any step mapped in `cortex.proto` that isn't functionally replicated by the CLI
is skipped. This includes:
- **Browser UI & Automation**: `CORTEX_STEP_TYPE_BROWSER_CLICK_ELEMENT`,
`CORTEX_STEP_TYPE_BROWSER_MOVE_MOUSE`, `CORTEX_STEP_TYPE_BROWSER_SUBAGENT`,
`CORTEX_STEP_TYPE_EXECUTE_BROWSER_JAVASCRIPT`,
`CORTEX_STEP_TYPE_CAPTURE_BROWSER_SCREENSHOT`,
`CORTEX_STEP_TYPE_READ_BROWSER_PAGE`, `CORTEX_STEP_TYPE_BROWSER_GET_DOM`,
`CORTEX_STEP_TYPE_BROWSER_LIST_NETWORK_REQUESTS`,
`CORTEX_STEP_TYPE_BROWSER_SCROLL_UP`, `CORTEX_STEP_TYPE_OPEN_BROWSER_URL`, and
15+ other browser controls.
- **IDE & UI Actions**: `CORTEX_STEP_TYPE_VIEW_CODE_ITEM`,
`CORTEX_STEP_TYPE_LINT_DIFF`, `CORTEX_STEP_TYPE_ADD_ANNOTATION`,
`CORTEX_STEP_TYPE_VIEW_FILE_OUTLINE`, `CORTEX_STEP_TYPE_CODE_SEARCH`,
`CORTEX_STEP_TYPE_FIND_ALL_REFERENCES`, `CORTEX_STEP_TYPE_CODE_ACTION`.
- **Agent Framework**: `CORTEX_STEP_TYPE_TASK_BOUNDARY`,
`CORTEX_STEP_TYPE_NOTIFY_USER`, `CORTEX_STEP_TYPE_INVOKE_SUBAGENT`,
`CORTEX_STEP_TYPE_CHECKPOINT`, `CORTEX_STEP_TYPE_EPHEMERAL_MESSAGE`,
`CORTEX_STEP_TYPE_COMMAND_STATUS`, `CORTEX_STEP_TYPE_SEND_COMMAND_INPUT`.
- **Knowledge & Workspace**: `CORTEX_STEP_TYPE_KNOWLEDGE_GENERATION`,
`CORTEX_STEP_TYPE_KI_INSERTION`, `CORTEX_STEP_TYPE_TRAJECTORY_SEARCH`,
`CORTEX_STEP_TYPE_MQUERY`, `CORTEX_STEP_TYPE_INTERNAL_SEARCH`,
`CORTEX_STEP_TYPE_LIST_RESOURCES`, `CORTEX_STEP_TYPE_WORKSPACE_API`.
- **Misc Commands**: `CORTEX_STEP_TYPE_GIT_COMMIT`,
`CORTEX_STEP_TYPE_GENERATE_IMAGE`, `CORTEX_STEP_TYPE_COMPILE`,
`CORTEX_STEP_TYPE_CLIPBOARD`, `CORTEX_STEP_TYPE_ERROR_MESSAGE`, etc.
</details>
## 5. Session Resumption
Once converted:
@@ -61,37 +146,90 @@ compatibility.
### When to Update
- If new step types are added to Antigravity that the CLI should support.
- If new step types are added to Antigravity that the CLI should support in
`converter.ts`.
- If the binary format of the `.pb` files changes.
- If the encryption key or algorithm is rotated.
### How to Regenerate the Bundle
To keep the CLI up to date:
To keep the CLI up to date, you can run the automated build script:
1. Update `packages/core/src/teleportation/trajectory_teleporter.ts` with any
logic changes.
2. To build a new minified bundle, you must run it from within the Antigravity
`Exafunction` workspace because it depends on the complex Protobuf schema
definitions there
(`exa/proto_ts/dist/exa/gemini_coder/proto/trajectory_pb.js`).
3. If the Protobuf JS definitions haven't been generated in your `Exafunction`
project yet, build them first:
```bash
pnpm --dir exa/proto_ts build
```
4. Inside the `Exafunction` project root, run:
```bash
pnpm dlx esbuild /path/to/orions-belt/packages/core/src/teleportation/trajectory_teleporter.ts \
--bundle \
--minify \
--format=esm \
--platform=node \
--outfile=/path/to/orions-belt/packages/core/src/teleportation/trajectory_teleporter.min.js
```
5. Verify the new `trajectory_teleporter.min.js` works locally in the CLI.
```bash
npm run build:teleporter
```
This runs `packages/core/scripts/build-teleporter.sh`, which automatically:
1. Navigates to the neighboring `Exafunction` directory.
2. Generates the latest Protobuf JS schemas (`pnpm --dir exa/proto_ts build`).
3. Uses `esbuild` to re-bundle the CLI's teleporter script
(`trajectory_teleporter.ts`) against the fresh schemas.
4. Outputs the new `trajectory_teleporter.min.js` directly into the `gemini-cli`
source tree.
> [!TIP] In the long term, this logic could be moved to a shared NPM package
> published from the Antigravity repository, allowing the Gemini CLI to stay
> updated via simple `npm update`. 3. Users can continue the conversation
> seamlessly via the `/chat resume` command.
> updated via a simple `npm update`.
## Productionization Roadmap
To safely and seamlessly bring the Jetski trajectory teleportation feature to a
fully production-ready state in the Gemini CLI, several key areas need to be
addressed:
### 1. Security & Key Management
- **Dynamic Key Exchange:** Instead of a hardcoded key in the CLI source code,
the CLI should retrieve the encryption key securely (e.g., from the OS
Keychain, a local Jetski config file, or by querying the local Jetski daemon).
- **Permission Scoping:** Ensure the CLI enforces the same file-access
permission rules (`file_permission_request`) that Jetski enforces so the AI
doesn't suddenly gain destructive permissions when transitioning to the
terminal.
### 2. Architecture & Build Process Decoupling
- **Shared NPM Package:** Publish the compiled Protobufs and parsing logic as a
private internal package (e.g., `@google/cortex-teleporter`). The Gemini CLI
should simply `npm install` this, rather than generating `.min.js` blobs
manually.
- **Schema Versioning:** Add version checks. If the CLI encounters a trajectory
from a newer version of Jetski with breaking protobuf changes, it should
gracefully prompt the user to update the CLI.
### 3. User Experience (UX)
- **Clear UI Indicators:** In the CLI's `/chat resume` menu, Jetski sessions
should be visually distinct from native CLI sessions (e.g., using a 🛸 icon
and a "Jetski" tag next to the session name).
- **Missing Context Warnings:** Because we intentionally drop 75+ step types
(browser actions, IDE UI clicks, etc.), the CLI conversation history might
look like it has "gaps." The UI should render a small placeholder like:
`[ ⚠️ Jetski browser action dropped for CLI compatibility ]` so the user
understands the model did something in the IDE that isn't shown in the
terminal.
- **Seamless Handoff Prompt:** If the user has a currently active (running)
Jetski session, the CLI could intelligently prompt them on startup: _"You have
an active session in Jetski. Type `/resume` to bring it into the terminal."_
### 4. Data Fidelity & Error Handling
- **Graceful Degradation:** If the CLI fails to parse a specific `generic` step
or misses a tool argument, it shouldn't crash the entire resume process. It
should skip the broken step and append a system message warning the model.
- **File State Synchronization:** If a user made uncommitted file edits in
Jetski (e.g., `fileChange` steps that haven't been saved to disk), the CLI
needs to ensure it doesn't accidentally overwrite or hallucinate disk state.
It might be worth requiring a file save before teleporting.
### 5. Performance
- **Lazy Loading / Streaming:** When populating the list of sessions for
`/chat resume`, the CLI shouldn’t decrypt and parse the _entire_ history of
every file. It should only read the `metadata` headers to render the UI
picker, and only parse the full multi-megabyte `ConversationRecord` when a
specific session is selected.
- **Memory Limits:** Set an upper limit on how many historical tool turns the
CLI loads into memory when teleporting to avoid OOM (Out of Memory) crashes in
Node.js.

56
packages/core/src/teleportation/discovery.ts
View File

@@ -4,6 +4,7 @@
* SPDX-License-Identifier: Apache-2.0
*/
/* eslint-disable @typescript-eslint/no-unsafe-type-assertion */
import fs from 'node:fs/promises';
import path from 'node:path';
import os from 'node:os';
@@ -17,6 +18,7 @@ export interface AgySessionInfo {
mtime: string;
displayName?: string;
messageCount?: number;
workspaceUri?: string;
}
const AGY_CONVERSATIONS_DIR = path.join(
@@ -28,8 +30,11 @@ const AGY_CONVERSATIONS_DIR = path.join(
/**
* Lists all Antigravity sessions found on disk.
* @param filterWorkspaceUri Optional filter to only return sessions matching this workspace URI (e.g. "file:///...").
*/
export async function listAgySessions(): Promise<AgySessionInfo[]> {
export async function listAgySessions(
filterWorkspaceUri?: string,
): Promise<AgySessionInfo[]> {
try {
const files = await fs.readdir(AGY_CONVERSATIONS_DIR);
const sessions: AgySessionInfo[] = [];
@@ -40,7 +45,7 @@ export async function listAgySessions(): Promise<AgySessionInfo[]> {
const stats = await fs.stat(filePath);
const id = path.basename(file, '.pb');
let details = {};
let details: ReturnType<typeof extractAgyDetails> = {};
try {
const data = await fs.readFile(filePath);
const json = trajectoryToJson(data);
@@ -49,6 +54,14 @@ export async function listAgySessions(): Promise<AgySessionInfo[]> {
// Ignore errors during parsing
}
if (
filterWorkspaceUri &&
details.workspaceUri &&
details.workspaceUri !== filterWorkspaceUri
) {
continue; // Skip sessions from other workspaces if we have a filter
}
sessions.push({
id,
path: filePath,
@@ -68,6 +81,7 @@ export async function listAgySessions(): Promise<AgySessionInfo[]> {
function extractAgyDetails(json: unknown): {
displayName?: string;
messageCount?: number;
workspaceUri?: string;
} {
try {
const record = convertAgyToCliRecord(json);
@@ -79,9 +93,47 @@ function extractAgyDetails(json: unknown): {
? partListUnionToString(firstUserMsg.content).slice(0, 100)
: 'Antigravity Session';
// Attempt to extract authoritative workspace object from top-level metadata first
let workspaceUri: string | undefined;
const agyJson = json as Record<string, unknown>;
const metadata = agyJson['metadata'] as Record<string, unknown> | undefined;
if (metadata) {
const workspaces = metadata['workspaces'] as
| Array<Record<string, unknown>>
| undefined;
const firstWorkspace = workspaces?.[0];
if (firstWorkspace && firstWorkspace['workspaceFolderAbsoluteUri']) {
workspaceUri = firstWorkspace['workspaceFolderAbsoluteUri'] as string;
}
}
// Fallback: Attempt to extract workspace object from raw JSON steps (e.g. older offline trajectories)
if (!workspaceUri) {
const steps = (agyJson['steps'] as Array<Record<string, unknown>>) || [];
for (const step of steps) {
const userInput = step['userInput'] as
| Record<string, unknown>
| undefined;
if (userInput) {
const activeState = userInput['activeUserState'] as
| Record<string, unknown>
| undefined;
const activeDoc = activeState?.['activeDocument'] as
| Record<string, unknown>
| undefined;
if (activeDoc && activeDoc['workspaceUri']) {
workspaceUri = activeDoc['workspaceUri'] as string;
break;
}
}
}
}
return {
displayName,
messageCount: messages.length,
workspaceUri,
};
} catch (_error) {
return {};

98286
packages/core/src/teleportation/trajectory_teleporter.min.js vendored
View File

File diff suppressed because it is too large Load Diff