github-issue
Comprehensive GitHub issue lifecycle management from creation through resolution. Use when creating/viewing/editing/managing GitHub issues, writing issue descriptions, creating sub-issues, linking parent/child issues, dumping issue trees to markdown, or pushing issues from files. Covers the full issue lifecycle - creating issues with conventional commit titles, managing sub-issues and cross-repo references, editing issue content, viewing and listing issues, dumping issue trees with YAML frontmatter, round-trip workflows (dump→edit→push), linking issues, commenting, labeling, and closing. Supports meta-tickets, component issues, and cross-repo sub-issue tracking.
What this skill does
# GitHub Issue Management Skill This skill provides a structured approach to writing GitHub issues that communicate context, scope, and direction clearly. ## Title Format (Required) Issue titles **must** follow conventional commit format: ``` <type>(<scope>): <description> ``` **Valid types:** `feat`, `fix`, `docs`, `style`, `refactor`, `perf`, `test`, `build`, `ci`, `chore`, `revert` **Examples:** - `feat(auth): add OAuth2 login support` - `fix(api): resolve race condition in request handler` - `chore(deps): update dependencies to latest versions` - `docs(readme): add installation instructions` The script validates this format automatically. Use `--skip-validation` only if the repository uses a different convention. --- ## The Why/What/How Framework Every issue should answer three questions for the reader: - **Why** does this matter? - **What** exactly needs to happen? - **How** should it be approached? This framework ensures issues are actionable and provide enough context for anyone picking them up. --- ## Issue Template ### Why Explain the background and motivation: - **Current state**: What exists today? How does it work? - **Bottleneck/Problem**: What specific issue or limitation was identified? - **Value**: Why is solving this valuable? What insights, metrics, or improvements does it unlock? ```markdown ## Why Currently, [describe current state/behavior]. This causes [specific problem or bottleneck], which [impact on users/system/workflow]. Addressing this will [concrete benefit - improved metrics, unlocked capabilities, better UX]. ``` ### What Define the scope concretely: - **Specific deliverable**: What exactly needs to be built, fixed, or changed? - **Boundaries**: What is explicitly out of scope? - **Success criteria**: How do we know when this is done? ```markdown ## What [Verb] [specific thing] to [achieve outcome]. Scope: - [In scope item 1] - [In scope item 2] Out of scope: - [Explicitly excluded item] ``` ### How Provide implementation direction: - **Approach**: High-level strategy or pattern to follow - **Key files/components**: Where changes will likely occur - **Architecture sketch**: Skeleton of the solution structure (not implementation details) ```markdown ## How Approach: [brief strategy - e.g., "Extend existing X pattern", "Add new Y component"] Key areas: 1. [Component/file] - [what changes here] 2. [Component/file] - [what changes here] Skeleton: - [High-level step 1] - [High-level step 2] - [Integration point] ``` --- ## Acceptance Criteria Keep acceptance criteria focused on integration and observable behavior: ```markdown ## Acceptance Criteria - [ ] [Observable behavior or state that confirms completion] - [ ] [Integration with existing system works as expected] - [ ] [Edge case or error condition handled] ``` Tips: - Write criteria that can be verified by running the system - Focus on "what" not "how" - avoid implementation details - Include integration points with existing functionality --- ## Testing Plan Keep testing plans succinct and focused on verification: ```markdown ## Testing Plan - [ ] [How to manually verify the change] - [ ] [Key integration scenario to test] - [ ] [Regression check if applicable] ``` Tips: - Tests added should integrate within existing test architeture - Prioritize integration testing over isolated unit tests - Include the command or steps to run verification - Note any existing tests that should continue passing --- ## Scripts Reference This skill includes Python scripts in `scripts/` that wrap GitHub API operations. Run them with `uv`: ### Available Commands | Command | Description | |---------|-------------| | `create` | Create a new issue | | `create-sub` | Create a sub-issue linked to a parent | | `edit` | Edit an existing issue's title or body | | `view` | View issue details | | `list` | List issues in a repository | | `list-subissues` | List all sub-issues of a parent (GraphQL API) | | `dump-tree` | Dump issue and sub-issues to markdown with frontmatter | | `push` | Push/sync issue from markdown file to GitHub | | `link` | Link two issues (parent/child relationship) | | `close` | Close an issue | | `comment` | Add a comment to an issue | | `labels` | Manage issue labels | | `init` | Initialize an issue body file with template | ### Usage Examples ```bash # Initialize a template file uv run scripts/gh_issue.py init --template default uv run scripts/gh_issue.py init --template bug uv run scripts/gh_issue.py init --template feature # Create an issue from a body file uv run scripts/gh_issue.py create owner/repo \ --title "Brief, descriptive title" \ --body-file /tmp/issue-body.md # Create with labels and assignees uv run scripts/gh_issue.py create owner/repo \ --title "Add caching layer" \ --body-file /tmp/issue-body.md \ --labels "enhancement,performance" \ --assignees "@me" # Create a sub-issue linked to parent uv run scripts/gh_issue.py create-sub owner/repo \ --parent 10 \ --title "Implement caching middleware" \ --body-file /tmp/sub-issue.md # Edit an issue's body uv run scripts/gh_issue.py edit owner/repo 123 \ --body-file /tmp/updated-body.md # Edit an issue's title uv run scripts/gh_issue.py edit owner/repo 123 \ --title "feat(api): updated title" # View an issue uv run scripts/gh_issue.py view owner/repo 123 # List open issues uv run scripts/gh_issue.py list owner/repo # List issues by label uv run scripts/gh_issue.py list owner/repo --labels "bug" # List all sub-issues of a parent (handles cross-repo references) uv run scripts/gh_issue.py list-subissues owner/repo 123 uv run scripts/gh_issue.py list-subissues owner/repo 123 --json # Dump issue and all sub-issues to markdown files uv run scripts/gh_issue.py dump-tree owner/repo 123 thoughts/shared/issues/ # Link existing issues uv run scripts/gh_issue.py link owner/repo --parent 10 --child 42 # Add a comment uv run scripts/gh_issue.py comment owner/repo 123 "Progress update: ..." # Close an issue uv run scripts/gh_issue.py close owner/repo 123 --reason completed ``` --- ## Creating Issues ### Preview Before Creation By default, the script shows a preview and asks for confirmation before creating: ``` ============================================================ ISSUE PREVIEW ============================================================ Repository: owner/repo Title: feat(api): add caching to API responses Labels: enhancement, performance Body: ---------------------------------------- ## Why ... ---------------------------------------- Create this issue? y = create issue n = cancel e = edit (saves to /tmp/issue-body.md for editing) ``` - Press `y` to create the issue - Press `n` to cancel - Press `e` to save body to `/tmp/issue-body.md` for editing, then re-run Use `--yes` or `-y` to skip confirmation (for automation). ### Basic Creation ```bash # Initialize template uv run scripts/gh_issue.py init --output /tmp/issue-body.md # Edit the template with your content # ... edit /tmp/issue-body.md ... # Create the issue (will show preview first) uv run scripts/gh_issue.py create owner/repo \ --title "feat(api): add caching layer" \ --body-file /tmp/issue-body.md ``` ### With Labels and Assignment ```bash uv run scripts/gh_issue.py create owner/repo \ --title "feat(api): add caching layer to API responses" \ --body-file /tmp/issue-body.md \ --labels "enhancement,performance" \ --assignees "@me" \ --milestone "v2.0" ``` ### Adding to a Project ```bash uv run scripts/gh_issue.py create owner/repo \ --title "Issue title" \ --body-file /tmp/issue-body.md \ --project "Project Name" ``` --- ## Linking Issues ### Create a Sub-issue ```bash # Create a new issue linked to parent #10 uv run scripts/gh_issue.py create-sub owner/repo \ --parent 10 \ --title "feat(cache): implement caching middleware" \ --body "## Why Part of the caching initiative (#10). ## What Implement the middleware layer for request
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.