ngocsangyem

Unified verification: build→lint→test→type-check→coverage. Use for 'is everything green', 'run all checks', 'verify build'. Auto-called by mk:cook. NOT for lint/format only (see mk:lint-and-validate); NOT for test-to-requirement coverage mapping (see mk:nyquist).

AI-agent-driven browser automation (long autonomous sessions, Browserbase-capable). Use when the user needs to interact with websites across many steps, automate complex browser tasks, or run unattended flows. Triggers include 'open a website', 'fill out a form', 'automate browser actions', 'login to a site', or any task requiring programmatic web interaction. NOT for manual E2E test generation (s

Detects task agent, complexity tier, and model automatically at Phase 0 orient. Invoked first in every workflow. NOT for runtime agent routing inside a single skill (see orchestration-rules.md).

REST/GraphQL API design: resource naming, HTTP methods, status codes, pagination, versioning, error formats. Use for 'design API', 'endpoint patterns'.

Use when exploring technical solutions, comparing approaches, or generating alternatives for a validated problem. Triggers on "brainstorm solutions", "explore approaches", "compare options", "trade-off analysis", "how should we build". Do NOT use for product validation ("is this worth building?" → use mk:office-hours instead). Do NOT use when a plan already exists (→ use mk:plan-ceo-review instead

Manage Confluence collaboration surface via the confluence-as wrapper: comments, attachments, labels, watchers. Triggers: 'add comment to page 12345', 'upload attachment to page 12345', 'label page 12345 as urgent', 'watch page 12345'. Inline-vs-footer comment safety enforced. NOT for page CRUD (mk:confluence-page); NOT for bulk ops (mk:confluence-bulk).

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.

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: "sec

Use when a project has no docs/ directory or needs initial documentation generated from codebase analysis. Triggers on "init docs", "create documentation", "generate docs", "docs init", or when docs/ is empty. Do NOT use for updating existing docs (use mk:document-release).

Fetch a URL and return clean markdown. Use when the agent needs an arbitrary external page (blog, RFC, GitHub issue, vendor doc) not covered by mk:docs-finder. Triggers on URLs in chat. Static-only by default; opt-in JS rendering available.

Use when creating a new project from scratch — orchestrates the full journey from idea to running code. Research → design → plan → scaffold → implement → docs. Explicit invocation only — never auto-activates. CLI = project infrastructure (.claude/), bootstrap = application code + full pipeline. NOT for autonomous multi-hour builds of specified products (see mk:autobuild); NOT for single-task featu

Use when measuring harness changes against ground truth — runs a small canary suite (5 quick tasks, 6 with --full) and records scores in trace-log.jsonl. Backs the dead-weight audit with measured deltas. Triggers on /mk:benchmark, "run benchmark", "measure harness", or before/after a harness change.

Session-scoped safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Active for the current session only. Use when touching prod, debugging live systems, or working in a shared environment. Use when asked to "be careful", "safety mode", "prod mode", or "careful m

Enforces KISS/DRY/YAGNI during authoring and ad-hoc quality reviews. Pragmatic standards: concise, direct, no unnecessary comments. NOT for post-hoc diff/PR review (see mk:review); NOT for behavior-preserving simplification passes (see mk:simplify).

Database patterns: schema design, migrations, query optimization, indexing. PostgreSQL primary. Use for 'database schema', 'migration', 'SQL optimization'.

Use when grading a running build behaviorally — drives the artifact via browser/curl/CLI and grades against rubric criteria with concrete evidence. Triggers on /mk:evaluate, "evaluate this build", "grade the running app", "check the running site against the spec", or after a generator iteration completes. NOT for structural code audit of a diff/PR (see mk:review); NOT for static linting (see mk:li

Production ready. AI Agent Workflow System for Claude Code

Confluence page CRUD via the confluence-as wrapper. Triggers: 'create page in SPACE', 'show me page 12345', 'update title of page 12345', 'delete page 12345', 'page hierarchy under 12345', 'copy page 12345 to SPACE'. NOT for bulk ops on 10+ pages (mk:confluence-bulk); NOT for spec analysis (mk:confluence-spec-analyst); NOT for comments/attachments/labels (mk:confluence-collaborate).

Read-only audit of `.claude/` structural overhead. Reports prioritized "remove X save Y tokens" recommendations against the model context window. NOT for monetary cost tracking — that's /mk:budget. NOT for transcript size monitoring — long-session continuity defers to Claude Code native compaction. Use when planning to add context capacity, diagnosing perceived slowdowns, or auditing health.

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 merged or code is shipped.

Session-scoped directory edit restriction. Blocks Edit and Write outside the allowed path for the current session only. Use when debugging to prevent accidentally "fixing" unrelated code, or when you want to scope changes to one module. Use when asked to "freeze", "restrict edits", "only edit this folder", or "lock down edits". NOT for blocking destructive shell commands (see mk:careful).

Full Jira ticket context analysis via the jira-analyst agent — including media (attached images / PDFs / screenshots) and linked issues. Produces structured findings suitable for posting back as a Jira comment. Read-only. Triggers: 'analyze KEY', 'rca for KEY', 'describe KEY with media'. NOT for complexity scoring (mk:jira-evaluator); NOT for story-point estimation (mk:jira-estimator).

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 "

Sample skill for fixture purposes — small enough to land below noise floor.

Bulk Confluence operations on 10+ pages via the confluence-as wrapper: bulk-label / bulk-move / bulk-delete. Dry-run is MANDATORY first. Triggers: 'bulk update N pages', 'mass label', 'delete all pages matching CQL', 'bulk-move pages to PARENT'. NOT for single-page ops (mk:confluence-page); NOT for comment/attachment ops (mk:confluence-collaborate).

Deep spec analysis on a Confluence page. Reads page (+ children) via the confluence-as wrapper, produces a structured Spec Research Report with requirements, acceptance criteria, gaps, ambiguities, and suggested user stories for human review. Read-only — does NOT create Jira tickets. Triggers: 'analyze spec for PAGE-ID', 'extract requirements from confluence page', 'spec research on URL'. NOT for

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]",

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).

JIRA project / user / group / scheme / automation administration via the jira-as wrapper (11 sub-domains, ~65 verbs). Triggers: 'create JIRA project', 'list users', 'delete user USERNAME', 'list permission schemes', 'create group NAME'. Requires admin role. Destructive ops (project/user/group delete) require 2-step token confirmation. NOT for per-issue ops (mk:jira-issue / mk:jira-lifecycle); NOT

Bulk JIRA operations on 10+ issues via the jira-as wrapper: bulk transition / assign / set-priority / clone / delete. Dry-run is MANDATORY first. Triggers: 'bulk update N issues', 'mass transition', 'transition 50+ issues to Done', 'bulk-clone', 'bulk-delete'. NOT for single-issue ops (mk:jira-issue / mk:jira-lifecycle).

Confluence CQL search + space list + saved-filter + export via the confluence-as wrapper. Triggers: 'search confluence', 'find pages where X', 'cql for ...', 'export search results', 'list spaces', 'manage saved filters'. CQL injection-safe via the shared sanitizer. NOT for single-page CRUD (mk:confluence-page); NOT for bulk write ops (mk:confluence-bulk).

Orchestrates single-task implementation pipeline: plan → test → build → review → ship. Use for feature work, plan execution, or fixes scoped to a single task. NOT for green-field product builds (see mk:autobuild); NOT for auto-invoked workflow orchestration (see mk:workflow-orchestrator).

Operational decision frameworks: triage, escalation, case management, billing ops. Use for 'how to handle X cases', 'build triage', 'escalation protocol'.

Structured second-pass reasoning after code review or plan evaluation. Offers named reasoning methods (pre-mortem, inversion, red team, Socratic, etc.) to re-examine findings through a specific lens. Use after /mk:review verdict or any time deeper analysis is needed on an existing output. NOT for initial review (see mk:review); NOT for creating implementation plans (see mk:plan-creator).

Figma design analysis and implementation via Figma MCP. Parse Figma links, extract design specs, translate to code. Triggers: 'figma', 'design link', 'implement this design', 'design tokens'.

Use when designing UI components, reviewing visual design, building design systems, or checking accessibility. Auto-activates on frontend design tasks and UI reviews.

Generate developer artifacts from Jira tickets via the jira-as wrapper: branch names, PR descriptions, parsed commits, commit/PR-to-issue links. Triggers: 'branch name for KEY', 'PR description for KEY', 'parse commits for issue keys', 'link PR to KEY'. NOT for executing git/gh commands directly (mk:ship); NOT for issue CRUD (mk:jira-issue).

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.

Use when implementing features or writing code. TDD enforcement is opt-in via --tdd / MEOWKIT_TDD=1. Provides code patterns, skill loading, and coding standards.

Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. 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

JIRA custom field discovery + configuration via the jira-as wrapper. Triggers: 'field ID for X', 'list custom fields', 'check fields for project PROJ', 'configure agile fields for board'. Read ops are open; create/configure-agile require admin. NOT for setting per-issue field values (mk:jira-issue update).

JIRA-side cache + project-context discovery via the jira-as wrapper. Triggers: 'jira cache status', 'clear jira cache', 'discover project context for PROJ'. Diagnostic-only — no Atlassian state changes. NOT for issue CRUD; NOT for project admin (mk:jira-admin).

Use when transforming existing code into agent-consumable surfaces — CLI (npm-publishable), MCP server (stdio/SSE/Streamable HTTP), and a companion skill. Triggers on 'agentize', 'henshin', 'expose as MCP', 'wrap as CLI', 'publish to npm', 'make LLM-accessible', 'turn into agent tool', 'expose feature as tool'. Runs when the user has existing code and wants to ship it to agents. NOT for building n

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 agile via the jira-as wrapper: epics, sprints, backlog, ranking, story points, subtasks, velocity. Triggers: 'create sprint', 'add KEY to sprint', 'set story points on KEY', 'rank KEY before KEY', 'velocity for board', 'epic add'. Board ID ≠ project key. NOT for issue CRUD (mk:jira-issue); NOT for time tracking (mk:jira-time).

Manage JIRA collaboration surface via the jira-as wrapper: comments, attachments, watchers, notify. Triggers: 'comment on KEY', 'add attachment to KEY', 'watch KEY', 'notify KEY watchers'. Internal-vs-public comment safety enforced. NOT for issue CRUD (mk:jira-issue); NOT for issue links (mk:jira-relationships).

Heuristic story-point estimation for a single Jira ticket via the jira-estimator agent. Read-only. Triggers: 'estimate KEY', 'story points for KEY', 'how complex is KEY'. NOT for complexity-only analysis (mk:jira-evaluator); NOT for full RCA (mk:jira-analyst).

Evaluate Jira ticket complexity + inconsistencies via the jira-evaluator agent. Read-only. Triggers: 'evaluate KEY', 'analyze ticket complexity for KEY', 'check ticket quality for KEY'. NOT for estimation (mk:jira-estimator); NOT for full RCA (mk:jira-analyst).