Official agent skill

Generate Snapshot

by microsoft in microsoft/vscode-python-environments

Generate a codebase health snapshot for technical debt tracking and planning.

OfficialMITAuto-check passedDevelopment

Install Generate Snapshot

skills CLI

$ npx skills add microsoft/vscode-python-environments --skill generate-snapshot -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install microsoft/vscode-python-environments generate-snapshot --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/microsoft/vscode-python-environments.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/generate-snapshot .claude/skills/generate-snapshot && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "generate-snapshot" agent skill from https://github.com/microsoft/vscode-python-environments/tree/main/.github/skills/generate-snapshot into .claude/skills/generate-snapshot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "generate-snapshot", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/microsoft/vscode-python-environments/tree/main/.github/skills/generate-snapshot

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add microsoft/vscode-python-environments --skill generate-snapshot -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install microsoft/vscode-python-environments generate-snapshot --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/microsoft/vscode-python-environments.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.github/skills/generate-snapshot .agents/skills/generate-snapshot && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "generate-snapshot" agent skill from https://github.com/microsoft/vscode-python-environments/tree/main/.github/skills/generate-snapshot into .agents/skills/generate-snapshot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "generate-snapshot", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add microsoft/vscode-python-environments --skill generate-snapshot -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install microsoft/vscode-python-environments generate-snapshot --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/microsoft/vscode-python-environments.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.github/skills/generate-snapshot .cursor/skills/generate-snapshot && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "generate-snapshot" agent skill from https://github.com/microsoft/vscode-python-environments/tree/main/.github/skills/generate-snapshot into .cursor/skills/generate-snapshot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "generate-snapshot", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/microsoft/vscode-python-environments.git --path .github/skills/generate-snapshot

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add microsoft/vscode-python-environments --skill generate-snapshot -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install microsoft/vscode-python-environments generate-snapshot --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/microsoft/vscode-python-environments.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.github/skills/generate-snapshot .gemini/skills/generate-snapshot && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "generate-snapshot" agent skill from https://github.com/microsoft/vscode-python-environments/tree/main/.github/skills/generate-snapshot into .gemini/skills/generate-snapshot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "generate-snapshot", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install microsoft/vscode-python-environments generate-snapshot

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add microsoft/vscode-python-environments --skill generate-snapshot -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/microsoft/vscode-python-environments.git skills-src && mkdir -p .github/skills && cp -r skills-src/.github/skills/generate-snapshot .github/skills/generate-snapshot && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "generate-snapshot" agent skill from https://github.com/microsoft/vscode-python-environments/tree/main/.github/skills/generate-snapshot into .github/skills/generate-snapshot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "generate-snapshot", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add microsoft/vscode-python-environments --skill generate-snapshot -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install microsoft/vscode-python-environments generate-snapshot --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/microsoft/vscode-python-environments.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.github/skills/generate-snapshot .opencode/skills/generate-snapshot && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "generate-snapshot" agent skill from https://github.com/microsoft/vscode-python-environments/tree/main/.github/skills/generate-snapshot into .opencode/skills/generate-snapshot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "generate-snapshot", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: generate-snapshot
GitHub stars: 141
Token cost: ~1.1k tokens
SKILL.md length: 344 words
Files: 1
Skills in repo: 9
Repo updated: Oct 8, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Generate a codebase health snapshot for technical debt tracking and planning.

Works in 3 steps: Sort by priority_score descending → Top items = files that change often AND… → These are prime candidates for
Tasks that involve Technical debt
SKILL.md covers When to Use, How to Generate, Snapshot Structure and Interpreting Results, plus 1 more section
Calls python

What it does

Generate Snapshot is an agent skill from microsoft/vscode-python-environments, published by the product's own GitHub organization. Generate a codebase health snapshot for technical debt tracking and planning. Analyzes git history, code complexity, debt markers, and dependencies to identify hotspots and refactoring priorities.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Technical debt, Refactoring and Git workflow. It works with TypeScript. The repository describes itself as: VS Code extension for Python environment and package management. The licence is MIT.

When your agent uses it

Tasks that involve Technical debt
Tasks that involve Refactoring
Tasks that involve Git workflow

Example prompts

“/generate-snapshot”

Requirements

Python 3

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

Sort by priority_score descending
Top items = files that change often AND are complex
These are prime candidates for

What it can do on your machine

Read from SKILL.md and the folder at commit e4f9939. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Generate Snapshot loads about 1.1k tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 344 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~54
When it runs · the whole SKILL.md, loaded when a task matches: ~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from microsoft/vscode-python-environments at commit e4f9939, republished under its MIT licence (© microsoft). 344 words, ~1,078 tokens.

Download SKILL.mdSave it as .claude/skills/generate-snapshot/SKILL.md (or your agent's skills folder).

name: generate-snapshot
description: Generate a codebase health snapshot for technical debt tracking and planning. Analyzes git history, code complexity, debt markers, and dependencies to identify hotspots and refactoring priorities.
argument-hint: --output path --pretty

Generate Codebase Snapshot

This skill generates a comprehensive code health snapshot using the analysis modules in analysis/.

When to Use

During planning phase to identify work items
To find refactoring hotspots (high churn + high complexity)
To track technical debt over time
Before major releases to assess code health
To identify knowledge silos (bus factor risks)

How to Generate

powershell

# From repository root
python -m analysis.snapshot --output analysis-snapshot.json

Add --pretty flag to also print the JSON to stdout.

Note: The snapshot is written to the repository root (analysis-snapshot.json). This path is ignored by .gitignore.

Snapshot Structure

The snapshot contains these sections:

`summary` - High-level metrics dashboard

files_with_changes: Number of files with git changes
total_churn: Total lines added + deleted
high_complexity_files: Count of files with high complexity
todo_count, fixme_count: Debt marker counts
circular_dependency_count: Architectural issues
single_author_file_ratio: Bus factor indicator

`priority_hotspots` - Top 20 refactoring candidates

Files sorted by priority_score = change_count × max_complexity

json

{
    "path": "src/features/terminal/terminalManager.ts",
    "change_count": 45,
    "churn": 1200,
    "max_complexity": 18,
    "priority_score": 810
}

High priority_score = frequently changed AND complex = prime refactoring target.

`git_analysis` - Change patterns

hotspots: Most frequently changed files
temporal_coupling: Files that change together (hidden dependencies)
bus_factor: Knowledge concentration risks

`complexity` - Code complexity metrics

by_language.typescript: TypeScript file metrics (max_complexity, avg_complexity, function_count)
high_complexity_functions: Functions with cyclomatic complexity > 10

`debt_indicators` - Technical debt markers

debt_markers.by_type: TODO, FIXME, HACK comments by type
large_files: Files exceeding 500 lines of code
long_functions: Functions exceeding 50 lines

`dependencies` - Module coupling analysis

circular_dependencies: Cycles in import graph
highly_coupled_modules: Modules with fan-out > 10
hub_modules: Modules with fan-in > 10
layer_violations: Lower layers importing from higher layers

Interpreting Results

Priority Hotspots

Sort by priority_score descending
Top items = files that change often AND are complex
These are prime candidates for:
- Breaking into smaller modules
- Adding tests before changes
- Simplifying complex functions

Temporal Coupling

Files with coupling_ratio > 0.8 changing together indicate:

Hidden dependencies not visible in imports
Copy-paste code that should be shared
Features spread across unrelated files

Knowledge Silos

Files with author_count = 1 and change_count >= 3:

Single point of failure for knowledge
Consider documentation or pair programming
Higher risk for bugs during that author's absence

Circular Dependencies

Any cycles in the import graph:

Indicates tight coupling
Makes testing difficult
Consider introducing interfaces or restructuring

Example Usage in Planning

User: What should we work on next?

Agent: Let me generate a snapshot and analyze it...
[generates snapshot]

Based on the snapshot:

Top 3 priority items:
1. **src/features/terminal/terminalManager.ts** (priority: 810)
   - 45 changes, complexity 18
   - High churn indicates active development area
   - Recommend: Split terminal concerns into separate modules

2. **src/managers/common/nativePythonFinder.ts** (priority: 540)
   - 30 changes, complexity 18
   - Multiple FIXME markers found
   - Recommend: Address type guards and cache issues

3. **src/features/interpreterSelection.ts** (priority: 360)
   - 24 changes, complexity 15
   - Temporal coupling with settings files
   - Recommend: Reduce coupling with settings module

Files

Just SKILL.md in .github/skills/generate-snapshot of microsoft/vscode-python-environments.

Open the folder on GitHubat commit e4f9939

Compare with similar skills

Generate Snapshot next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Generate Snapshot compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Generate Snapshot this skillmicrosoft/vscode-python-environments	141	—	~1.1k	Automated safety check: Pass	MIT	today
DRY Refactoring With jscpdkucherenko/jscpd	6.4k	—	~2.1k	Automated safety check: Pass	MIT	today
jscpd Duplicate Code Detectorkucherenko/jscpd	6.4k	—	~4.5k	Automated safety check: Pass	MIT	today
Dead Code Removal with Knipshift-editor/shift	347	—	~1.8k	Automated safety check: Pass	Apache-2.0	today
Code RefinerMathews-Tom/armory	328	—	~3.1k	Automated safety check: Pass	MIT	2 days ago
Systematic Code Refactoringluongnv89/claude-howto	42k	—	~3k	Automated safety check: Pass	MIT	8 days ago

Similar skills

DRY Refactoring With jscpd
kucherenko/jscpd
Removes copy-paste duplication found by jscpd, starting with exact clones and hotspots, then renamed and near-miss copies, using proven refactoring strategies.
6.4k GitHub stars~2.1k tokensUpdated today
DevelopmentAuto-check passed
jscpd Duplicate Code Detector
kucherenko/jscpd
Finds duplicated code in 220+ languages with jscpd, reports exact, renamed and near-miss clones in a compact agent-friendly format and measures duplication.
6.4k GitHub stars~4.5k tokensUpdated today
DevelopmentAuto-check passed
Dead Code Removal with Knip
shift-editor/shift
Finds unused files, exports and class members with Knip, then verifies each candidate through reference tracing before removing anything, never using knip --fix.
347 GitHub stars~1.8k tokensUpdated today
DevelopmentAuto-check passed
Code Refiner
Mathews-Tom/armory
Deep code simplification and refactoring preserving behavior across Python, Go, TypeScript, Rust.
328 GitHub stars~3.1k tokensUpdated 2 days ago
DevelopmentAuto-check passed
Systematic Code Refactoring
luongnv89/claude-howto
Guides refactoring in phases based on Martin Fowler's method: research, test coverage check, planning and small tested steps, with your approval at each phase.
42k GitHub stars~3k tokensUpdated 8 days ago
DevelopmentAuto-check passed
Code Simplification for ego-lite
citrolabs/ego-lite
Finds and implements evidence-backed simplifications in the ego-lite repository, such as dead code, duplicated state and speculative abstractions, without hiding behavior changes.
17k GitHub stars~1.2k tokensUpdated 15 days ago
DevelopmentAuto-check passed

Questions about Generate Snapshot

What does Generate Snapshot do?

Generate a codebase health snapshot for technical debt tracking and planning. Generate Snapshot is an agent skill from microsoft/vscode-python-environments, published by the product's own GitHub organization. Generate a codebase health snapshot for technical debt tracking and planning.

When should I use Generate Snapshot?

Generate Snapshot fits situations like: tasks that involve Technical debt; tasks that involve Refactoring; tasks that involve Git workflow.

How do I install Generate Snapshot in Claude Code?

Run `npx skills add microsoft/vscode-python-environments --skill generate-snapshot -a claude-code`. Or copy the skill folder (.github/skills/generate-snapshot in microsoft/vscode-python-environments) into .claude/skills/generate-snapshot in your project. Claude Code loads it when a task matches its description.

How do I install Generate Snapshot in Codex?

Run `npx skills add microsoft/vscode-python-environments --skill generate-snapshot -a codex`. Or copy the skill folder (.github/skills/generate-snapshot in microsoft/vscode-python-environments) into .agents/skills/generate-snapshot in your project. Codex loads it when a task matches its description.

Can I use Generate Snapshot in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add microsoft/vscode-python-environments --skill generate-snapshot -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/generate-snapshot, .gemini/skills/generate-snapshot, .github/skills/generate-snapshot and .opencode/skills/generate-snapshot in your project.

What does Generate Snapshot need to run?

Going by SKILL.md and its folder, Generate Snapshot needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Generate Snapshot access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Generate Snapshot safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Generate Snapshot use?

Generate Snapshot is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Generate Snapshot use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Generate Snapshot?

Skills that share tags, products or a category with Generate Snapshot: DRY Refactoring With jscpd (kucherenko/jscpd, 6.4k stars), jscpd Duplicate Code Detector (kucherenko/jscpd, 6.4k stars), Dead Code Removal with Knip (shift-editor/shift, 347 stars) and Code Refiner (Mathews-Tom/armory, 328 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Generate Snapshot?

microsoft (a GitHub organization, an official publisher) maintains it in microsoft/vscode-python-environments, which has 141 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 8, 2026.

Source: microsoft/vscode-python-environments on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Generate Snapshot

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Generate Codebase Snapshot

When to Use

How to Generate

Snapshot Structure

summary - High-level metrics dashboard

priority_hotspots - Top 20 refactoring candidates

git_analysis - Change patterns

complexity - Code complexity metrics

debt_indicators - Technical debt markers

dependencies - Module coupling analysis

Interpreting Results

Priority Hotspots

Temporal Coupling

Knowledge Silos

Circular Dependencies

Example Usage in Planning

Files

Compare with similar skills

Similar skills

More from microsoft/vscode-python-environments

Related

Questions about Generate Snapshot

`summary` - High-level metrics dashboard

`priority_hotspots` - Top 20 refactoring candidates

`git_analysis` - Change patterns

`complexity` - Code complexity metrics

`debt_indicators` - Technical debt markers

`dependencies` - Module coupling analysis