Agent skill
bead-implementation
Execute on a Beads issue with proper discovery workflow and mandatory session close protocol. Use when starting work on a bead, during implementation when discovering new work that should be externalized, or when completing a session to ensure all work is properly committed.
Install this agent skill to your Project
npx add-skill https://github.com/moogah/claude_skills/tree/main/bead-implementation
SKILL.md
Bead Implementation Workflow
Execute on beads with narrow focus, proper discovery, and mandatory session close.
Core Principle
One bead per session. Complete only ONE bead per session, then commit immediately. Work is done on a local branch/worktree - do not push or sync with remote.
Finding and Claiming Work
# Find available work
bd ready # All ready work
bd ready --label migration # Ready work with specific label
# Review issue details
bd show beads-xxx
# Claim work
bd update beads-xxx --status=in_progress
During Implementation: Create Follow-Up Beads
Stay narrowly focused. Externalize any unexpected work by creating new beads.
Use the bead-creator skill for guidance on creating follow-up beads for:
- Bugs discovered during implementation
- Unclear requirements needing clarification
- Related work identified
- Dependencies and blocking relationships
Key practices:
- Use
--deps "discovered-from:beads-xxx"to link follow-up beads to their origin - Add appropriate labels:
follow-up,question,blocker,bugfix discovered-fromis non-blocking - tracks relationships without affecting execution
Completing Work
# Mark work complete with review label
bd label add beads-xxx needs-review
bd close beads-xxx
Finding Review Work
# Query beads needing review
bd list --label needs-review --status=closed
# After review, remove the label
bd label remove beads-xxx needs-review
Session Close Protocol (Mandatory)
CRITICAL: Work is NOT complete until changes are committed locally.
Five Steps
1. File Issues for Remaining Work
- Document follow-up tasks as new beads
- Close completed issues:
bd close <id1> <id2> ... - Update in-progress issues with current status
2. Run Quality Gates (if code was modified)
bash scripts/type-check.sh # TypeScript validation
npm test # Run tests (if applicable)
3. Commit Changes
git status # Check what changed
git add <files> # Stage code changes
git commit -m "..." # Commit with descriptive message
4. Verify Completion
- Confirm all changes are committed
- Check
git statusshows clean working tree - Verify commit succeeded without errors
5. Hand Off Context
- Provide summary of what was completed
- Note any issues filed for next session
- Highlight any blockers or dependencies
Critical Rules
- Never stop before committing - Leaves work incomplete
- Work on local branch/worktree - Do not push or sync with remote
- Commit immediately - Execute when work is complete
- Local commit completion is non-negotiable
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
characterization-testing
Guide for characterization testing - capturing current system behavior to enable safe refactoring. Use when working with legacy code, undocumented systems, or code that needs modification but lacks tests. Helps create a safety net before making changes by testing what the code actually does (not what it should do).
architecture-analyzer
Perform in-depth architectural analysis of codebases through iterative dialog and visual diagrams. Use when users want to understand their software architecture, explore design patterns and anti-patterns, evaluate potential architectural changes, or gain deep insights into code structure and relationships. Particularly valuable for onboarding to unfamiliar codebases, assessing technical debt, planning refactoring efforts, or understanding how components interact across system boundaries.
openspec-to-beads
Convert OpenSpec artifacts (proposal.md, design.md, tasks.md, specs/) into self-contained Beads issues for implementation tracking. Use when you have completed OpenSpec planning artifacts and need to create trackable implementation tasks, or when converting any specification or design document into actionable Beads issues.
github-actions-troubleshooting
Troubleshoot and fix failing GitHub Actions pipeline steps. Use when user reports a failing pipeline with error output.
skill-learner
Reviews conversation context to identify learnings and patterns that should be captured in skills. Use when the user asks to review the session for skill creation or updates.
writing-elisp
Comprehensive guidance for writing high-quality, idiomatic, modern Emacs Lisp code with incremental validation. Use when writing or modifying elisp functions, especially complex nested forms with cl-loop, multiple let* bindings, or lambdas. Covers modern features, naming conventions, documentation standards, error handling, code quality, and performance.
Didn't find tool you were looking for?