From claude-project-flow
Close the active feature — generate final docs (overview, implementation, edge-cases), optionally merge branch, mark status=closed in context.md.
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-project-flow:close-featureThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Finalize a feature: generate documentation, optionally merge, archive.
Finalize a feature: generate documentation, optionally merge, archive.
/project-flow:close-feature — runs on the currently active featurepf context --json → feature != null)context.md, all requirements/*, all plans/*, git log since branch created<feature_dir>/docs/overview.md — what this feature does, why it exists<feature_dir>/docs/implementation.md — how it was built, key files, patterns<feature_dir>/docs/edge-cases.md — edge cases handled, known limitationsAsk user which option:
gh pr create if gh is installed)For option 1 or 2: announce irreversible action, ask confirmation:
"Ready to merge feature/ to main. Confirm? (y/N)"
If confirmed, execute via git commands or gh.
Update <feature_dir>/context.md frontmatter:
status: closed
closed_at: YYYY-MM-DD
Append under ## Sessions:
YYYY-MM-DD — feature closed# Overview: <slug>
## Purpose
<one paragraph: what this feature achieves, for whom>
## Scope
<what it does and doesn't do>
## User-facing summary
<plain language, no jargon>
# Implementation: <slug>
## Architecture
<2-3 paragraphs describing approach>
## Key files
- `path/file1.ts` — <role>
- `path/file2.ts` — <role>
## Patterns used
<design patterns, conventions followed>
## Dependencies added
<new libraries, external services>
# Edge cases: <slug>
## Handled
- <case 1>: <mitigation>
- <case 2>: <mitigation>
## Known limitations
<what's explicitly not covered>
## Future considerations
<items for v2 or later>
Summary of docs created + merge outcome + path to context.md for final status check.
npx claudepluginhub matteovisca/claude-project-flowGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.