Agent skill
gathering-feature
The drum sounds. Bloodhound, Elephant, Beaver, Raccoon, Deer, Fox, and Owl gather for complete feature development. Use when building a full feature from exploration to documentation.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/gathering-feature
SKILL.md
Gathering Feature đ˛đž
The drum echoes through the forest. One by one, they come. The Bloodhound scouts the territory. The Elephant builds with unstoppable momentum. The Beaver tests what was built. The Raccoon audits for security. The Deer ensures all can travel the paths. The Fox optimizes for speed. The Owl documents what was learned. When the gathering completes, a feature stands where before there was only forest.
When to Summon
- Building a complete feature from scratch
- Major functionality spanning frontend, backend, and database
- Features requiring exploration, implementation, testing, and documentation
- When you want the full lifecycle handled automatically
The Gathering
SUMMON â ORGANIZE â EXECUTE â VALIDATE â COMPLETE
â ⲠⲠⲠâ
Receive Dispatch Animals Verify Feature
Request Animals Work All Ready
Animals Mobilized
- đ Bloodhound â Scout the codebase, understand patterns
- đ Elephant â Build the multi-file feature
- đĻĢ Beaver â Write comprehensive tests
- đĻ Raccoon â Security audit and cleanup
- đĻ Deer â Accessibility audit
- đĻ Fox â Performance optimization
- đĻ Owl â Document the feature
Phase 1: SUMMON
The drum sounds. The forest listens...
Receive and parse the request:
Clarify the Feature:
- What does this feature do?
- Which users benefit?
- What's in scope? What's out?
- Any existing issues or specs?
Confirm:
"I'll mobilize a gathering for: [feature description]
This will involve:
- đ Bloodhound scouting the codebase
- đ Elephant building across [estimated files] files
- đĻĢ Beaver writing tests
- đĻ Raccoon auditing security
- đĻ Deer checking accessibility
- đĻ Fox optimizing performance
- đĻ Owl writing documentation
Proceed with the gathering?"
Phase 2: ORGANIZE
The animals assemble, knowing their roles...
Dispatch in sequence:
Dispatch Order:
Bloodhound âââ Elephant âââ Beaver âââ Raccoon âââ Deer âââ Fox âââ Owl
â â â â â â â
â â â â â â â
Scout Build Test Security a11y Speed Docs
Patterns Feature Coverage Audit Check Opt Write
Dependencies:
- Bloodhound must complete before Elephant (needs context)
- Elephant must complete before Beaver (tests the built feature)
- Beaver must complete before Raccoon (tests catch security issues)
- Raccoon, Deer, Fox can run in parallel after Beaver
- Owl last (documents everything)
Phase 3: EXECUTE
The animals work. The forest transforms...
Execute each phase:
đ BLOODHOUND â SCOUT
"Scouting the codebase for [feature]..."
Output:
- Files that will need changes
- Patterns to follow
- Integration points identified
- Potential obstacles found
đ ELEPHANT â BUILD
"Building [feature] with momentum..."
Output:
- All required files created/modified
- Frontend components
- Backend API endpoints
- Database schema changes
- Integration wired
đĻĢ BEAVER â TEST
"Building test dams for confidence..."
Output:
- Integration tests for user flows
- Unit tests for complex logic
- Edge case coverage
- All tests passing
đĻ RACCOON â AUDIT
"Rummaging for security risks..."
Output:
- Secrets scan (none found)
- Vulnerability check (clean)
- Input validation verified
- Auth checks confirmed
đĻ DEER â SENSE
"Sensing accessibility barriers..."
Output:
- Keyboard navigation works
- Screen reader compatible
- Color contrast passes
- Reduced motion respected
đĻ FOX â OPTIMIZE
"Hunting for performance gains..."
Output:
- Bundle size optimized
- Database queries fast
- Images optimized
- Caching implemented
đĻ OWL â ARCHIVE
"Archiving knowledge for the forest..."
Output:
- Help documentation written
- API documentation updated
- Code comments added
- README updated
Phase 4: VALIDATE
The work is done. Each animal verifies their contribution...
Validation Checklist:
- Bloodhound: All integration points mapped
- Elephant: Feature functional end-to-end
- Beaver: All tests passing, coverage adequate
- Raccoon: No security issues found
- Deer: WCAG AA compliance verified
- Fox: Performance targets met
- Owl: Documentation complete
Quality Gates:
If any animal finds critical issues:
â Return to that phase
â Fix the issue
â Re-run dependent phases
â Continue validation
If all gates pass:
â Proceed to COMPLETE
Phase 5: COMPLETE
The gathering ends. A feature stands complete...
Completion Report:
## đ˛ GATHERING FEATURE COMPLETE
### Feature: [Name]
### Animals Mobilized
đ Bloodhound â đ Elephant â đĻĢ Beaver â đĻ Raccoon â đĻ Deer â đĻ Fox â đĻ Owl
### What Was Built
- **Files Changed:** [count]
- **New Components:** [list]
- **API Endpoints:** [list]
- **Database Changes:** [summary]
### Quality Verification
- â
Tests: [X] passing, [Y]% coverage
- â
Security: No issues found
- â
Accessibility: WCAG AA compliant
- â
Performance: [metrics]
- â
Documentation: Complete
### Artifacts Created
- Source code (committed)
- Tests ([location])
- Documentation ([location])
- Migration scripts (if applicable)
### Time Elapsed
[Duration]
*The forest grows. The feature lives.*
Example Gathering
User: "/gathering-feature Add a bookmarking system for posts"
Gathering execution:
-
đ˛ SUMMON â "Mobilizing for: Bookmarking system. Allow users to save posts for later."
-
đ˛ ORGANIZE â "Dispatch sequence: Bloodhound â Elephant â Beaver â Raccoon + Deer + Fox â Owl"
-
đ˛ EXECUTE â
- đ Scout: "Found post components, user service patterns, database conventions"
- đ Build: "Created bookmark service, API endpoints, UI components, database schema"
- đĻĢ Test: "Added 15 tests covering CRUD operations, auth checks, edge cases"
- đĻ Audit: "No secrets, input validated, auth enforced"
- đĻ Sense: "Keyboard nav works, screen reader announces, contrast passes"
- đĻ Optimize: "Lazy loaded bookmarks, indexed queries, compressed images"
- đĻ Archive: "Help doc written, API documented, code commented"
-
đ˛ VALIDATE â "All quality gates pass"
-
đ˛ COMPLETE â "Feature deployed, documented, tested, secured"
When the drum sounds, the forest answers. đ˛
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?