util
claudeUtility skills: documentation, context, handoffs
8 skills · 2 agents
Agentic workflow: plan → implement → align → quality → test → review → fix
Plugin wf from marketplace claude-tooling in JSai23/claude-tooling. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
builder-conventions-kImplementation practices — deviation protocol, progress tracking, code standards, codebase reflection
builder-living-docs-kALWAYS USE if you are the builder. Use after every implementation pass — update living docs, maintain diagrams (Mermaid for formal, ASCII for loose), reconcile plan with reality, update ARCHITECTURE.md when system shape changes. Documentation is a core output, not an afterthought.
common-design-docs-kThe agent documentation system — doc types, folder structure, frontmatter conventions, agent roles, lifecycle
common-doc-audit-kALWAYS USE if you are the verifier or gardener. Use after any build cycle to audit documentation accuracy — check diagram drift, living doc freshness, ARCHITECTURE.md currency, cross-link integrity, and plan status. Gardener uses broadly across the full doc tree; verifier uses post-build to confirm
common-testing-kTesting philosophy — what good tests look like, anti-patterns, coverage priorities, naming
doc-aGenerate or update standard code documentation — docstrings, rustdoc, API references, READMEs
logging-aLog decisions, progress, deviations, and discoveries during any workflow phase
planner-design-kHow to think about design — product outcomes, system architecture, code structure, tradeoffs
planner-implementation-kHow to write implementation plans — code structure, module layout, component connections, with execution blocks at the end
verify-design-aArchitecture review in hindsight — what to question, dependency analysis, abstraction assessment
verify-larp-aFake code detection — performative implementations, test theater, misleading patterns, red flags
verify-quality-aQuality verification framework — dimensions, severity levels, grading criteria
verify-style-aCode cleanliness — AI-generated slop, naming, dead code, over-engineering, simplification
builderImplementation session — execute milestones from a plan, write production code and tests, follow codebase patterns, surface deviations, maintain living docs. Launched via: claude --agent wf:builder - common-design-docs-k - builder-conventions-k - builder-living-docs-k - common-testing-k
gardenerMaintenance session — continuous cleanup of LLM-generated technical debt in code and documentation. Keeps docs current, prunes stale plans, fixes drift. Launched via: claude --agent wf:gardener - common-design-docs-k - common-doc-audit-k
plannerPlanning and design session — everything before code. Use when starting a feature, designing a system change, or breaking down complex work into an execution plan. Launched via: claude --agent wf:planner - common-design-docs-k - planner-design-k - planner-implementation-k
verifierVerification session — end-of-cycle quality review covering design, integrity, cleanliness, and production readiness. Delegates to specialized agents via Task tool. Launched via: claude --agent wf:verifier - common-design-docs-k - common-doc-audit-k - verify-quality-a - verify-larp-a - verify-design
python3 ${CLAUDE_PLUGIN_ROOT}/hooks/block-pip.py
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.