MeowKit

Workflow navigation assistant. Scans project state (plans, reviews, tests, git) and recommends the next step in the 7-phase pipeline. Use when asked "what should I do next?", "where am I?", "help", or at session start. NOT for domain complexity routing (see mk:scale-routing); NOT for skill discovery (descriptions handle that automatically).

Workflow navigator: scans project state (plans, reviews, tests, git) and recommends the next pipeline step. Use for 'what next?' or 'where am I?'. NOT for complexity routing (mk:scale-routing).

Workflow navigator: scans project state (plans, reviews, tests, git) and recommends the next pipeline step. Use for 'what next?' or 'where am I?'. NOT for complexity routing (mk:scale-routing).

Routing skill — recommends the correct mk:confluence-* leaf for any Confluence Cloud task. Triggers: 'confluence', 'wiki page', 'spec page', ambiguous Confluence intent. NOT an executor — every actual operation forks via a leaf skill.

Retrieve up-to-date library, framework, and project documentation using scripts + MCP tools (Context7, Context Hub) with intelligent fallback. Use this skill whenever the user or agent needs documentation for any library, framework, API, SDK, or internal project spec. Triggers on "docs for [X]", "how does [library] work", "find documentation", "API reference for", "look up [feature] in [library]", "latest docs", "what's the API for", "find our [internal spec]", or any request that requires current, accurate documentation rather than relying on training data. Always prefer this skill over raw WebSearch for documentation retrieval — it returns structured, context-efficient results.

Ticket/PRD intake: product area classification, completeness scoring, RCA, technical assessment. Works with Jira (via mk:jira-issue / jira-as), Linear (via MCP), GitHub (via gh CLI), or manual paste. Triggers: 'analyze ticket', 'intake PRD', 'triage issue', 'classify ticket', 'check ticket'.

JIRA search + filter management via the jira-as wrapper. Triggers: 'search jira', 'find issues where X', 'jql for ...', 'export search results', 'manage saved filters'. JQL injection-safe via the shared sanitizer. NOT for single-issue CRUD (mk:jira-issue); NOT for bulk write ops (mk:jira-bulk).

Routing skill — recommends the correct mk:jira-* leaf for any Jira task. Triggers: 'jira', 'jira ticket', ambiguous Jira intent. NOT an executor — every actual operation forks via a leaf skill.

Process images, video, audio, PDFs with Gemini API. Generate images (Nano Banana 2), videos (Veo 3), speech (MiniMax TTS), music (MiniMax). Convert documents to Markdown. Multi-provider fallback (Gemini → MiniMax → OpenRouter). Activate when task references media files, asks to analyze/describe/transcribe/extract/generate/convert, or involves non-text binary files.

Analyzes ticket complexity and maps dependencies against an existing codebase before sprint planning. Triggers on 'how complex is this ticket', 'what should we work on first', 'can we fit this in the sprint', 'tech review before planning', 'plan the sprint'. NOT for writing implementation plans (see mk:plan-creator); NOT for scope/ambition review (see mk:plan-ceo-review).

Generate novel UI from a text prompt via Stitch AI. Exports Tailwind/HTML, produces DESIGN.md for mk:frontend-design handoff. NOT for implementing existing designs — use mk:figma or mk:frontend-design for that.

Process images/video/audio/PDFs via Gemini API; generate images/video/speech/music; convert docs to Markdown. Multi-provider fallback. Use for analyze/transcribe/generate/convert on media files.

Process images/video/audio/PDFs via Gemini API; generate images/video/speech/music; convert docs to Markdown. Multi-provider fallback. Use for analyze/transcribe/generate/convert on media files.

Use when autonomously improving a measurable scalar metric through bounded, git-tracked iterations: modify one scoped change, verify, keep or revert. Triggers on /mk:loop, 'optimize coverage/bundle size/lint count', 'iterate until the metric improves'. NOT for subjective cleanup (see mk:cook), known-root-cause bugs (see mk:fix), behavioral grading (see mk:evaluate), or shipping (see mk:ship).

Turn a raw idea into ONE honest recommendation: interview one question at a time until the problem, requirements, goals, non-goals, and constraints are CONFIRMED, then deliver a single verdict — do, don't, cheaper alternatives, trade-offs, ordered checklist, success metrics. Required: the user wants exactly ONE recommendation — not options, not a debate — and their framing is open to challenge (advise may answer a different question than the one asked). Triggers on "what should I do about X", "advise me on X", "am I approaching this right", "is this the right move". Do NOT use to be interrogated with no recommendation (→ mk:grill) — advise also interviews one question at a time, but only to reach a verdict. Do NOT use when the framing is settled and only the options are open (→ mk:brainstorming). Do NOT use to decide whether something is worth building (→ mk:office-hours). Do NOT use when you want several perspectives to argue it out (→ mk:party).

Chief Security Officer mode. Infrastructure-first security audit: secrets archaeology, dependency supply chain, CI/CD pipeline security, LLM/AI security, skill supply chain scanning, plus OWASP Top 10, STRIDE threat modeling, and active verification. Two modes: daily (zero-noise, 8/10 confidence gate) and comprehensive (monthly deep scan, 2/10 bar). Trend tracking across audit runs. Use when: "security audit", "threat model", "pentest review", "OWASP", "CSO review".

Post-ship documentation update. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped, polishes CHANGELOG voice, cleans up TODOS, and optionally bumps VERSION. Use when asked to "update the docs", "sync documentation", or "post-ship docs". Proactively suggest after a PR is created and before it merges.

Systematic debugging with root cause investigation. Produces a diagnostic report; mk:fix owns remediation and mk:build-fix owns compile/build failures. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root cause analysis". Proactively suggest when the user reports errors, unexpected behavior, or is troubleshooting why something stopped working. NOT for applying fixes without investigation (see mk:fix); NOT for step-by-step evidence-based reasoning (see mk:sequential-thinking).

YC Office Hours — product validation for a new product, feature, or side-project concept. Startup mode tests demand; Builder mode develops an unvalidated product idea. Use when the user asks whether something is worth building or has an idea whose problem/value is not yet validated. Proactively suggest when the user describes a new product idea or is exploring whether something is worth building — before any code is written. Use BEFORE a plan exists. For reviewing an existing plan, use /mk:plan-ceo-review.

CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick expansions), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Use when asked to "think bigger", "expand scope", "strategy review", "rethink this", or "is this ambitious enough". Proactively suggest when the user is questioning scope or ambition of a plan, or when the plan feels like it could be thinking bigger. Use AFTER a plan exists. For validating the idea itself before planning, use /mk:office-hours first.

Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Proactively suggest when the user says a feature is ready for testing or asks "does this work?". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and a ship-readiness summary.

Weekly-cadence engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas. Use when asked to "weekly retro", "what did we ship", or "engineering retrospective". Proactively suggest at the end of a work week or sprint. NOT for per-session or per-task reflection (see mk:memory / Phase 6 Reflect).

Multi-pass structural code review with adversarial analysis, scope-aware dispatch, adversarial persona passes, and forced-finding protocol. Supports input modes: branch diff (default), PR number (#123), commit hash, pending changes (--pending). Use when asked to "review this PR", "code review", "pre-landing review", "check my diff", or "review #123". Proactively suggest when the user is about to merge or land code changes. NOT for behavioral verification against a running build (see mk:evaluate); NOT for post-implementation simplification (see mk:simplify).

Ship workflow with explicit scopes: prepare stages and commits locally; release pushes and creates a PR; publish manages issues and versioning. Use when asked to "ship", "deploy", "push to main", "create a PR", or "merge and push". Proactively suggest when the user says code is ready or asks about deploying. Supports official (→ main) and beta (→ dev/develop) ship modes with auto-detection.

Use when negotiating a file-based sprint contract between the generator (developer) and evaluator before code is written. Translates a product-level spec into testable acceptance criteria with rubric tie-ins. Triggers on /mk:sprint-contract, "draft a sprint contract", "negotiate scope for sprint", or before any harness-driven sprint kicks off.

Runs autonomous multi-hour green-field builds: planner, contract, generator/evaluator loop, scaffolding density per model tier. NOT for scoped tasks (mk:cook); NOT for scaffolding only (mk:bootstrap).

Experimental/manual harness canary procedure. It records benchmark manifests and scores but does not provide a fully automated runner.

Session-scoped guardrails warning before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, etc; user can override. NOT for scoping edits to a directory (mk:freeze).

Read-only audit of .codex/ structural overhead: 'remove X save Y tokens' vs the context window. NOT for cost tracking (budget skill); NOT for runtime read/compact decisions (mk:context-engineering).

Chief Security Officer mode: infrastructure-first audit of secrets, dependency supply chain, CI/CD, LLM/AI security, OWASP Top 10, STRIDE, active verification. Daily/comprehensive, trend tracking.

Post-ship docs sync: cross-reference the diff and update README/ARCHITECTURE/CONTRIBUTING/AGENTS.md + CHANGELOG to match what shipped. Use on 'update/sync docs'; suggest after a PR opens.

Session-scoped edit restriction: blocks Edit/Write outside an allowed path, to scope changes to one module or prevent unrelated fixes. NOT for blocking destructive shell commands (mk:careful).

Systematic root-cause debugging that produces a diagnostic report (mk:fix applies the fix; mk:build-fix owns compile failures). Use for 'debug this', 'why is this broken', 'root cause'.

JSON-canonical session memory in .meowkit/memory (Markdown is a generated view). Capture learnings, patterns, costs; loads at Orient, persists at Reflect. NOT for retrospectives (mk:retro).

YC Office Hours-style validation for a new idea before code exists: tests demand (Startup mode) or develops an unvalidated idea (Builder mode). For reviewing an existing plan use mk:plan-ceo-review.

CEO/founder-mode plan review: rethink the problem, find the 10x product, challenge premises, expand scope. Four modes, dream-big to strip-to-essentials. Use to rethink ambition or scope.

Refine a draft prompt before sending to a coding agent: decomposes goal/context/constraints, flags ambiguity, emits a model-agnostic rewrite. NOT for prompts from scratch (mk:brainstorming).

Systematically QA-tests a web app and fixes bugs: test, then iteratively fix, re-verify, commit each fix. Tiers: Quick, Standard, Exhaustive. Produces before/after health scores and fix evidence.

Weekly engineering retrospective from commit history, work patterns, and code-quality metrics, with trend tracking and per-person breakdown. NOT for per-session reflection (mk:memory / Phase 6).

Multi-pass structural code review with adversarial personas. Input: branch diff (default), PR #123, commit, --pending. Use for 'review this PR/diff'. NOT for behavioral verification (mk:evaluate).