Lumi

Smoke-test fixture for the stdio MCP integration tests. Returns a constant body when called.

Multi-AI requirements scoping using Codex and Gemini CLIs (Double Diamond Define phase). Use when: AUTOMATICALLY ACTIVATE when user requests clarification or scoping:. "define the requirements for X". "clarify the scope of Y"

Multi-AI validation, scoring, and review using Codex and Gemini CLIs (Double Diamond Deliver phase). Use when: AUTOMATICALLY ACTIVATE when user requests validation, scoring, or review:. "review X" or "validate Y" or "test Z". "score this", "quality check", "validate before shipping"

Multi-AI implementation using Codex and Gemini CLIs (Double Diamond Develop phase). Use when: AUTOMATICALLY ACTIVATE when user requests building or implementation:. "build X" or "implement Y" or "create Z". "develop a feature for X"

Multi-AI research using Codex and Gemini CLIs (Double Diamond Discover phase). Use when: AUTOMATICALLY ACTIVATE when user requests research or exploration:. "research X" or "explore Y" or "investigate Z". "what are the options for X" or "what are my choices for Y"

NLSpec authoring — structured specification from multi-AI research

System architecture and API design with multi-AI consensus

Quick execution for ad-hoc tasks without workflow overhead. Use when: Use this skill when user says "quick fix", "ad-hoc task", or explicitly. requests fast execution without full workflow overhead.

Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review. Use when: AUTOMATICALLY ACTIVATE when user requests auditing:. "audit and check the entire app". "audit X for Y" or "check for broken features"

OpenClaw instance administration — manage hosts across macOS, Ubuntu/Debian, Docker, OCI, and Proxmox. Use when: AUTOMATICALLY ACTIVATE when user asks about:. "manage openclaw" or "openclaw status" or "openclaw health". "update openclaw" or "upgrade openclaw" or "openclaw doctor"

Expert multi-AI code review with quality and security analysis

Extract patterns and anatomy from URLs — use to reverse-engineer content strategies from live pages. Use when: Use PROACTIVELY when user wants to:. "analyze this article", "analyze this content". "deconstruct this content", "break down this post"

Auto-detect work context (Dev vs Knowledge) for workflow tailoring

GitHub Copilot CLI as optional zero-cost provider via copilot -p programmatic mode. Use when: AUTOMATICALLY ACTIVATE when user says:. "copilot provider" or "add copilot" or "github copilot" or "use copilot"

Project remaining workflow cost from per-phase averages — warns on budget ceiling overruns. Use when: AUTOMATICALLY ACTIVATE when user asks about workflow costs:. "cost projection", "estimate remaining cost". "budget forecast", "how much will this cost"

Trace codepaths in diffs, map against tests, auto-generate missing coverage. Use when: AUTOMATICALLY ACTIVATE when user requests coverage analysis:. "check test coverage" or "coverage audit". "what's not tested" or "find untested code"

Structured four-way AI debates between Claude, Sonnet, Gemini, and Codex. Use when: AUTOMATICALLY ACTIVATE when user says:. "/debate <question>". "run a debate about X"

Debug issues methodically — use when stuck on errors, test failures, or unexpected behavior. Use when: AUTOMATICALLY ACTIVATE when encountering bugs or failures:. "fix this bug" or "debug Y" or "troubleshoot X". "why is X failing" or "why isn't X working" or "why doesn't X work"

Present options with trade-offs for informed decision-making. Use when: AUTOMATICALLY ACTIVATE when user requests options or choices:. "fix or provide options" or "fix them or provide me options". "give me options" or "what are my options"

Generate slide decks from briefs with optional multi-AI research. Use when: AUTOMATICALLY ACTIVATE when user requests:. "create a deck", "build slides", "make a presentation". "generate a pitch deck", "create board presentation"

Persist design documents with branch tracking, revision chains, and cross-session discovery. Use when: AUTOMATICALLY ACTIVATE when user says:. "save design" or "save this design". "design document" or "create a design doc"

Convert markdown to DOCX, PPTX, XLSX office documents. Use when: AUTOMATICALLY ACTIVATE when user requests:. Export knowledge work to office formats (e.g., "export to Word", "create PowerPoint", "convert to DOCX"). Generate professional documents from research (e.g., "create presentation from this synthesis")

Post-ship doc sync across project markdown. Use when: "sync docs", "update docs", "document changes", "release notes".

Environment diagnostics — check providers, auth, config, hooks, scheduler, and more. Use when: AUTOMATICALLY ACTIVATE when user asks about:. "doctor" or "run doctor" or "diagnostics". "check my setup" or "is everything working"

The lead's recipe for forming a planning team, running an adversarial debate with the plan-challenger, writing one plan markdown per Epic to the team's plans dir, surfacing it for user approval, and only THEN creating sprint Epic / Story / Task objects.

Reverse-engineer design systems, tokens, and components from live products or screenshots (beta — token extraction, component analysis, and URL modes are in progress)

Wrap up a branch — run tests, create PR, merge or discard — use when implementation is done. Use when: AUTOMATICALLY ACTIVATE when user requests task completion with git operations:. "commit and push" or "git commit and push". "complete all tasks and commit and push"

Lock in user goals upfront and validate outputs against them — use to prevent scope drift

Track project blockers, bugs, and gaps across sessions — use when issues pile up or need triage. Use when: AUTOMATICALLY ACTIVATE when user mentions:. "issue" or "issues" or "problem". "track this" or "remember this blocker"

Run tasks in a loop until goals are met — use for iterative refinement, polling, or convergence. Use when: AUTOMATICALLY ACTIVATE when user requests iterative execution:. "loop X times" or "loop around N times". "loop around 5 times auditing, enhancing, testing"

Switch to Knowledge Work mode for research and writing — use when task is non-code focused

Craft better prompts using proven optimization techniques — use when your prompt needs refinement. Use when: Use PROACTIVELY when user wants to:. "create a prompt for", "write a prompt for". "optimize this prompt", "improve this prompt"

Multi-tentacled orchestration using Double Diamond methodology. Use when: PRIORITY TRIGGERS (always invoke immediately):. "/octo:multi" (explicit command). "run this with all providers", "run with all providers"

AI-optimized PRD creation with 100-point scoring framework

Pick up where you left off from a previous session — use after context resets, compaction, or new conversations. Use when: AUTOMATICALLY ACTIVATE when user mentions:. "resume" or "continue" or "pick up where I left off". "what was I doing" or "restore session"

Roll back to a previous checkpoint via git — use when a change went wrong and you need to revert. Use when: AUTOMATICALLY ACTIVATE when user mentions:. "rollback" or "revert" or "undo". "go back to" or "restore checkpoint"

URL validation and content wrapping for untrusted sources. Use when: This skill provides SECURITY UTILITIES - it should be referenced by other skills,. not invoked directly by users. Auto-integrate when:. Fetching content from URLs

Review code in two passes: spec compliance then quality — use for thorough PR or feature reviews. Use when: Use when completing a major feature, preparing a PR, or when user says. "staged review", "full review", "review against spec", or "two-stage review".

Show where you are in the workflow and what to do next — use for progress checks and orientation. Use when: AUTOMATICALLY ACTIVATE when user asks about:. "status" or "progress" or "where am I". "what's next" or "next step"

Manage tasks with Claude Code native tools — use to track TODOs, delegate work, and monitor progress. Use when: AUTOMATICALLY ACTIVATE when user requests task management:. "add to the todo's" or "add this to todos". "resume tasks" or "continue tasks" or "pick up where we left off"