workflow-cli
Reference for modifying workflow.py or managing ~/.codex/docs/. Use when the user asks about workflow CLI commands, adding or updating docs, alias registration, workflow registry or lint issues, or fixing workflow command behavior. NOT for general CLI design principles (/cli-for-agents).
What this skill does
# Workflow CLI **EXECUTE this skill now.** Follow the workflow steps below using the provided $ARGUMENTS. Do not summarize the skill itself. The `workflow` CLI is the global context retrieval tool for AI agents and humans. It serves owner docs from `~/.codex/docs/` with progressive disclosure so the reader gets the minimum context needed at the point of need. ## Canonical Sources Use the live CLI and implementation as source of truth when command behavior matters: - `workflow --help` - `workflow knowledge --help` - `workflow read workflow-cli` - `~/.codex/bin/workflow.py` If you edit `workflow.py`, also load `workflow summary workflow-cli-quality-gate` before changing it. ## Why This Exists Agents waste context by loading whole docs when only a small slice is relevant. The previous direct-read pattern in entry docs was all-or-nothing. The workflow CLI inserts a retrieval layer between the agent and the docs: - `list` to see what exists - `summary` to triage relevance - `read --section` to load only what is needed - `read` for the full document as a last resort ## Architecture ```text ~/.codex/bin/workflow.py Single-file CLI ~/.local/bin/workflow PATH wrapper ~/.codex/docs/ Owner docs served by the CLI ~/.codex/pyproject.toml Ruff config ~/.codex/.rumdl.toml Markdown lint config ``` The CLI is intentionally low-dependency and supports both human-readable output and `--json` output for agent use. ## Commands Use the retrieval ladder: ```text workflow doctor workflow list workflow summary <doc> workflow read <doc> --section <heading> workflow read <doc> ``` For knowledge: ```text workflow knowledge list workflow knowledge search "query" --tag <domain> workflow knowledge summary <article> workflow knowledge read <article> ``` For maintenance: ```text workflow add <type> <name> workflow update <doc> --section <heading> workflow registry workflow lint workflow version ``` Knowledge maintenance: ```text workflow knowledge ingest <path> workflow knowledge reindex workflow knowledge stats ``` Global options: ```text workflow --no-input ... workflow --docs-dir <path> ... ``` `workflow context <task>` returns the compact pack by default; use `workflow context <task> --full` when you need the full bundled docs. ## Adding or Updating Docs 1. Decide the right doc type first: principle, workflow, reference, or pattern. 2. Scaffold with `workflow add <type> <name>` or create the file directly in `~/.codex/docs/`. 3. Ensure the doc has a `## Control Owner` section. 4. Register an alias in `~/.codex/bin/workflow.py` only when the doc should be a first-class short-name target such as `workflow summary <name>`. 5. Add or update the trigger in `AGENTS.md` only after the target exists. 6. Run `workflow registry` and `workflow lint`. Docs do not use a reindex step. They are discovered from the filesystem. `reindex` is only for the knowledge base via `workflow knowledge reindex`. Every doc should have a `## Control Owner` section with: - `Owner for:` - `Should contain:` - `Should not contain:` ## Common Issues - No doc match: check `workflow list` or `workflow search` - Section not found: use the exact `##` heading shown by `workflow summary` - Missing alias after a rename: update `ALIASES` in `workflow.py` - Doc exists but no short name works: either use the direct discovered name/path or add an alias in `workflow.py` - Confusing docs vs knowledge maintenance: docs use `workflow registry`; knowledge uses `workflow knowledge reindex` - Lint failures: run `workflow lint --full` and fix the surfaced file ## Design Principles - progressive disclosure - dual-audience output - context window protection - deterministic, non-interactive commands - actionable errors with next steps - reference doc for command details, skill for execution workflow
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.