claudeframework

Create well-structured atomic commits with conventional commit messages. Use when ready to commit working changes.

Write a feature spec from requirements in .claude/input/. Use when starting a new feature, before implementation begins.

Orchestrate the full spec → implement → review → fix → commit pipeline. Use when shipping a complete feature end-to-end.

Break a concept document, draft, or product brief into independent PRDs that each feed into /ship. Use when input contains multiple features or a big-picture vision.

Ship decomposed PRDs in parallel. Analyzes file conflicts, groups into batches, runs /ship in isolated worktrees, merges results. Use after /decompose.

Implement a feature from a spec file in .claude/specs/. Use after a spec is written and approved.

Audit dependencies for vulnerabilities and scan for committed secrets. Use periodically or when security alerts flag a dependency.

Resume work from a handoff file. Use at the start of a new session to pick up where a previous session left off.

Scaffold a Claude Code hook (command or HTTP) for this project. Use when you want to automate quality checks, formatting, or notifications on tool events.

Diagnose and fix a failing test, type error, or runtime error. Use when a specific test or build step is failing.

Deploy the framework to a target project by replacing shared dirs with symlinks (junctions) back to the framework repo. Run once after copying .claude/ to a new project.

Regenerate .claude/docs/ from current skills and context. Use after adding or modifying skills, context files, or framework structure.

Capture current session state to a handoff file. Use before /clear, when context is getting full, or when ending a session mid-task.

Scan Docker container logs for errors, crashes, and warnings. Use when services are misbehaving or after a deployment to verify health.

Analyze blast radius of a code change — find all call sites, test mocks, and consumers. Use before modifying shared functions, interfaces, or modules.

Process references into skill/rule improvement proposals. Use after adding blog posts, repos, or docs to .claude/references/, or pass a URL to fetch and ingest directly.

Write and run smoke tests against the Docker stack from a spec. Use after deploying to a Docker environment to verify end-to-end behavior.

Run the full verify suite and report results — no fixes applied. Use to check baseline health before starting work, after a merge, or when CI is red.

Review implementation changes and write a report to .claude/reviews/. Use after implementation is complete, before merging or committing.

Clone and analyze a Git repo's Claude Code setup. Discovers adoptable skills, hooks, agents, and patterns, then generates adoption proposals. Use after /scout finds interesting repos, or directly with a repo URL.

Fix issues found in a review report in .claude/reviews/. Use after a review identifies issues that need fixing.

Review and apply accepted proposals from learn-proposals.md to skill and rule files. Closes the scout→learn→apply loop. Use after reviewing proposals and marking them as accepted.

Search the web for new Claude Code patterns, release notes, and community skills. Use periodically to check for framework optimization opportunities.