git-helpers
Git workflow helper for conventional commits, confidence-scored code review (lens fan-out: security, bugs, data-loss, performance, guidelines), pull request creation, and branch lifecycle. Use when committing staged or unstaged changes, reviewing diffs, opening or pushing pull requests, merging branches, or cleaning up after a merge. Not for acceptance-criteria verification, visual design review, or session wrap-up.
What this skill does
# Git Helpers
Git workflow with conventional commits, confidence-scored code review,
and automated PR management.
## Triggers
- **Commit changes** ("commit this", "create commit", "ready to commit",
"all done") → [commit.md](references/commit.md)
- **Code review** ("review code", "check changes", "review my diff")
→ [code-review.md](references/code-review.md) (loads
[guidelines-audit.md](references/guidelines-audit.md) as a lens prompt)
- **Push and open PR** ("push this", "create PR", "open pull request",
"ready to push") →
[create-pull-request.md](references/create-pull-request.md)
- **Merge and clean up** ("finish branch", "merge branch", "merge PR",
"cleanup branch") → [finish-branch.md](references/finish-branch.md)
`guidelines-audit.md` is not a direct trigger — it is the lens prompt
loaded by `code-review.md` during the guidelines lens fan-out.
## Workflow
```text
commit --> review --> create-pull-request --> finish-branch
```
Each step is independent. Use any workflow in isolation or chain them
together.
## Code Review Fan-Out
`code-review.md` parallelizes via lens fan-out. After the main agent
annotates the diff and clears the size gate, it selects active lenses
based on changed files (minimum 3, maximum 5), then dispatches them in a
**single turn** — each reads the same annotated diff under a focused
scope and returns markdown findings.
| Lens | Scope | When active |
|------|-------|-------------|
| `security` | SQL injection, XSS, auth bypass, secrets, PII | always |
| `bugs` | Logic errors, runtime failures, swallowed errors | always |
| `guidelines` | Violations of project guideline files | always |
| `data-loss` | Destructive migrations, wrong delete predicates | when diff matches data patterns |
| `performance` | N+1 queries, sequential awaits, unbounded find | when diff matches perf patterns |
After the fan-out, the main agent consolidates: dedup on `file:line`,
severity sort, gap detection, partial-run handling. Cross-lens
visibility cannot be split across sub-agents.
Commit, create-pull-request, and finish-branch run inline on the main
agent (single-output workflows, no fan-out value).
## Guidelines
- Preview commit messages before committing — always show and ask for
confirmation
- Use confidence scoring: only report findings with confidence ≥ 80
- Default base branch: `main` (user can override)
- Use HEREDOC format for multi-line commit messages
- Analyze the actual diff and staged files, not conversation context
- Prefer single-line commit messages — only add a body for complex or
breaking changes
## Anti-Pattern: Conversation-Driven Commits
Writing the commit message from chat context produces fabricated quotes,
restated diff content, and missing rationale. The staged diff is the
single source of truth. Discard prior context, run `git diff --cached`,
and write the message from what the diff shows.
## Anti-Pattern: Confidence Inflation in Code Review
Reporting findings below 80 confidence buries real issues under noise.
The rubric is calibrated: <80 means speculation or style preference, not
a real bug. When unsure, drop down — gather more context, re-read the
diff — instead of pushing a low-confidence finding through.
## Anti-Pattern: Default GitHub Merge Subject
The default `Merge pull request #N from {branch}` message strips
intent and conventional commit type. Always pass a custom subject:
`{type}: {description} (#{pr-number})`.
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.