feature-tracking — Claude Code skill: what it does, how to install
Maintains feature documentation and decisions inside your repository. Gives AI assistants an operational memory during planning and active implementation.
npx skills add JunsW/feature-track --skill feature-tracking -a claude-codeWhat feature-tracking does
The skill organizes feature documentation under docs/features/. Before writing code, the assistant locates the feature identifier and inspects the existing README.md, or creates a new directory if tracking is missing. The repository stores every specification locally.
During development, the assistant updates records as endpoints, data models, or rollout constraints shift. Once work wraps up, it records the final outcome and synchronizes docs/features/README.md. Running validation requires Python 3: execute python3 cli/feature_track.py validate --root . or use scripts/validate_feature_tracks.py directly from the skill.
What it helps with
- track architecture decisions and API changes directly in the repository
- create structured feature records inside docs/features
- keep documentation synchronized throughout the development lifecycle
- validate feature tracking files with a Python script
Example prompts for the agent
- Create a feature track for payment-gateway and list it in docs/features
- Update docs/features/user-profile/README.md with the latest API changes
- Run feature track validation across the repository
How to install feature-tracking
1Skills CLI (Vercel)
npx skills add JunsW/feature-track --skill feature-tracking -a claude-code2Manually: put the files in place
~/.claude/skills/feature-tracking/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/feature-tracking/
1Skills CLI (Vercel)
npx skills add JunsW/feature-track --skill feature-tracking -a codex2Manually: put the files in place
.agents/skills/feature-tracking/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add JunsW/feature-track --skill feature-tracking -a cursor2Manually: put the files in place
.cursor/skills/feature-tracking/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install JunsW/feature-track feature-tracking2Manually: put the files in place
.github/skills/feature-tracking/SKILL.md1Skills CLI (Vercel)
npx skills add JunsW/feature-track --skill feature-tracking -a gemini-cli2Platform CLI
gemini skills install https://github.com/JunsW/feature-track --path skills/feature-trackingManually: put the files in place
.devin/skills/feature-tracking/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add JunsW/feature-track --skill feature-tracking -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about feature-tracking
How do I install feature-tracking in Claude Code?
Run npx skills add JunsW/feature-track --skill feature-tracking -a claude-code in your terminal.
What does feature-tracking do?
It prompts the assistant to read and update files in docs/features/. The markdown files become the operational memory for decisions, tests, and data models.
How do I validate feature documentation?
Run python3 cli/feature_track.py validate --root . from your project root. If your project lacks this CLI, run scripts/validate_feature_tracks.py from the skill instead.
Source text
SKILL.md · MIT
--- name: feature-tracking description: Maintain portable Feature Track docs for project features. Use when designing, planning, implementing, reviewing, or finishing feature work; creating or updating PRD/API/design/implementation docs; adding a new feature; or validating docs/features. --- # Feature Tracking Use Feature Track as the current operational memory for feature work. The neutral spec is the source of truth; this Codex skill is only an adapter. Read `references/spec.md` before changing feature docs. ## Default Workflow Before feature work: 1. Read `docs/features/README.md` if it exists. 2. Identify the feature id from the request, code module, route, domain name, or existing docs. 3. Read `docs/features/<feature-id>/README.md` if it exists. 4. If no track exists, create one and add it to the index. During work, update the feature track when behavior, decisions, endpoints, data models, dependencies, rollout constraints, tests, or source-of-truth links change. Before completion: 1. Update the feature README for the actual outcome. 2. Update `docs/features/README.md` if status, source-of-truth links, dates, or notes changed. 3. Run validation when available: ```bash python3 cli/feature_track.py validate --root . ``` If the project does not include this CLI, use `scripts/validate_feature_tracks.py` from this skill.
© JunsW · MIT · JunsW/feature-track
