This skill should be used when the user asks to "develop requirements framework", "fix requirements framework bug", "sync requirements framework", "deploy requirements changes", "update framework code", "test framework changes", or needs help with the framework development workflow including sync.sh usage, TDD for framework itself, and contributing changes.
Manages the requirements framework development workflow including sync operations, testing, and deployment.
npx claudepluginhub harmaalbers/claude-requirements-frameworkThis skill inherits all available tools. When active, it can use any tool Claude has access to.
examples/claude-driven-workflow.shexamples/tdd-workflow.shreferences/sync-workflow-details.mdreferences/troubleshooting-development.mdscripts/deploy-and-test.shscripts/quick-test.shscripts/sync-status.shGuide for developing, fixing, and maintaining the Claude Code Requirements Framework with proper sync workflow.
Repository: ~/Tools/claude-requirements-framework (git-controlled source of truth)
Deployed: ~/.claude/hooks/ (active runtime)
Remote: https://github.com/HarmAalbers/claude-requirements-framework.git
The framework lives in TWO places that must stay synchronized:
| Location | Purpose | When Changes Take Effect |
|---|---|---|
| Repository | Git source of truth | After ./sync.sh deploy |
| Deployed | Active runtime | Immediately |
→ Full sync details: See references/sync-workflow-details.md
cd ~/Tools/claude-requirements-framework
./sync.sh status # Check sync (ALWAYS run first)
./sync.sh deploy # Repository → ~/.claude/hooks
./sync.sh diff # Show differences
| Symbol | Meaning | Action |
|---|---|---|
✓ | In sync | None needed |
↑ | Out of sync | Run ./sync.sh deploy |
⚠ | Not deployed | Run ./sync.sh deploy |
✗ | Missing in repo | Copy or delete |
Pattern: Edit in repo → Deploy → Test → Commit
cd ~/Tools/claude-requirements-framework
# 1. Edit in repository
vim hooks/lib/requirements.py
# 2. Deploy
./sync.sh deploy
# 3. Test
python3 ~/.claude/hooks/test_requirements.py
# 4. Commit
git add . && git commit -m "feat: Add feature" && git push
Pattern: Fix in deployed → Test → Copy back → Commit
# 1. Fix directly (immediate effect)
vim ~/.claude/hooks/check-requirements.py
# 2. Test immediately
python3 ~/.claude/hooks/test_requirements.py
# 3. Copy to repo
cd ~/Tools/claude-requirements-framework
cp ~/.claude/hooks/check-requirements.py hooks/
# 4. Deploy and commit
./sync.sh deploy
git add . && git commit -m "fix: Bug description" && git push
Pattern: Claude edits deployed → Copy back → Commit
# 1. Claude edited ~/.claude/hooks/lib/some_module.py
# 2. Copy to repo
cd ~/Tools/claude-requirements-framework
cp ~/.claude/hooks/lib/some_module.py hooks/lib/
# 3. Deploy and commit
./sync.sh deploy
git add . && git commit -m "feat: Description" && git push
→ Example script: See examples/claude-driven-workflow.sh
Pattern: Test (RED) → Implement → Test (GREEN) → Commit
# 1. Write failing test in repo
vim hooks/test_requirements.py
# 2. Deploy and run (RED)
./sync.sh deploy
python3 ~/.claude/hooks/test_requirements.py # Fails
# 3. Implement feature
vim hooks/lib/requirements.py
# 4. Deploy and run (GREEN)
./sync.sh deploy
python3 ~/.claude/hooks/test_requirements.py # Passes
# 5. Commit
git add . && git commit -m "feat: TDD feature" && git push
→ Example script: See examples/tdd-workflow.sh
python3 ~/.claude/hooks/test_requirements.py
# Expected: 1079/1079 tests passed ✓
# By name pattern
python3 ~/.claude/hooks/test_requirements.py -k "test_session"
# Verbose output
python3 ~/.claude/hooks/test_requirements.py -v
# 1. Enable in a project
cd ~/some-project
cat > .claude/requirements.yaml <<EOF
version: "1.0"
enabled: true
requirements:
commit_plan:
enabled: true
scope: session
EOF
# 2. Start Claude, try editing → Should block
# 3. Satisfy: req satisfy commit_plan
# 4. Try editing → Should work
# 1. Edit in deployed (immediate effect)
vim ~/.claude/hooks/lib/FILE.py
# 2. Test
python3 ~/.claude/hooks/test_requirements.py
# 3. Copy to repo
cd ~/Tools/claude-requirements-framework
cp ~/.claude/hooks/lib/FILE.py hooks/lib/
# 4. Deploy and commit
./sync.sh deploy
git add . && git commit -m "fix: Bug description" && git push
# 1. Check sync first
cd ~/Tools/claude-requirements-framework
./sync.sh status
# 2. Edit in repo
vim hooks/lib/FILE.py
# 3. Deploy and test
./sync.sh deploy && python3 ~/.claude/hooks/test_requirements.py
# 4. Commit
git add . && git commit -m "feat: Feature description" && git push
# ALWAYS check sync before committing
cd ~/Tools/claude-requirements-framework
./sync.sh status
# If not clean, reconcile before committing
# Check where you edited
pwd
# If in repo, deploy
./sync.sh deploy
# Check file exists
ls -la ~/.claude/hooks/your-file.py
# Check permissions
chmod +x ~/.claude/hooks/*.py
# Check sync status
./sync.sh status
# Run with verbose
python3 ~/.claude/hooks/test_requirements.py -v
# Check registration
cat ~/.claude/settings.local.json | grep hooks
# Check file exists and is executable
ls -la ~/.claude/hooks/check-requirements.py
→ Full troubleshooting: See references/troubleshooting-development.md
./sync.sh statuspython3 ~/.claude/hooks/test_requirements.py./sync.sh deployfeat:, fix:, docs:, test:check-requirements.py
handle-session-start.py
handle-prompt-submit.py
handle-permission-request.py
handle-plan-exit.py
auto-satisfy-skills.py
clear-single-use.py
handle-tool-failure.py
handle-subagent-start.py
handle-pre-compact.py
handle-stop.py
handle-session-end.py
handle-teammate-idle.py
handle-task-completed.py
requirements-cli.py
test_requirements.py
test_branch_size_calculator.py
ruff_check.py
All *.py files in hooks/lib/ directory.
examples/ - Example filesdocs/ - Documentationplugin/ - Plugin (symlinked separately).git/ - Git files~/Tools/claude-requirements-framework/README.md./sync.sh status|deploy|diffpython3 ~/.claude/hooks/test_requirements.pyreferences/sync-workflow-details.md - Detailed sync.sh usage and scenariosreferences/troubleshooting-development.md - Development troubleshootingexamples/tdd-workflow.sh - TDD workflow example scriptexamples/claude-driven-workflow.sh - Claude development workflow scriptActivates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.