Skill Codex
Independently challenge an engineering brief, plan, investigation, or delivery proposal for correctness, missing requirements, unsafe assumptions, and inadequate validation. Use before execution when risk or workflow policy warrants a fresh review; produce findings for plan revision, never implementation changes.
Skill Codex
Use when an agent needs to publish a self-contained HTML artifact to an Artifact Viewer API and receive an immutable URL or stable named deployment link.
Skill Codex
Edit existing product-document drafts into clear, concise, digestible writing while preserving their intended meaning, facts, product terminology, document type, and authorial voice. Use when asked to improve, polish, tighten, rewrite, or make easier to read a PRD, product spec, user story, decision document, product…
Skill Codex
Review the current branch or pull-request diff for actionable correctness, security, reliability, regression, and test issues before PR creation or after material fixes. Use a fresh reviewer when change risk or size justifies independence; report evidence-backed findings only.
Skill Codex
Validate a delivery branch, create or update its pull request against the intended base, and atomically arm a review watch. Use when shipping changes through PR or when Ship It delegates PR creation; return a structured PR and monitor record.
Skill Codex
Implement and refine interfaces from Aphrodite MCP evidence and visual references through project-aware, screenshot-validated iteration; use when a design handoff needs comparison, clarification, and convergence rather than a one-shot UI build.
Skill Codex
Turn an ambiguous product or feature idea into a durable, repository-owned product specification through a decision-tree interview. Use when feature work lacks an approved spec, when a product owner needs a handoff artifact for engineers, or when kickoff must resolve product ambiguity before planning. Do not use for…
Skill Codex
Drive engineering work autonomously from intent to a verified terminal state. Picks a route (how much process) and a playbook (what kind of work), applies engineering principles, delegates across models, reviews independently, opens and watches PRs, lands them when granted, and closes out. Use for /kickoff or…
Skill Codex
Work with self-hosted Nabu knowledge spaces through native remote MCP first, including owner-agent connection links, bearer authentication, shared-space invites, scoped credentials, note traversal, and revision-aware mutations. Use when an agent must discover, authenticate, read, write, share, redeem, or verify Nabu…
Skill Codex
Create or revise proportionate implementation plans, using inline planning for tiny work and a configured planning worker for fast/full work. Use standalone or when Kickoff delegates planning; produce concise Markdown or a full human-review artifact as warranted.
Skill Codex
Execute an accepted engineering plan through implementation, integrated validation, code review, pull request creation, active review monitoring, and verified closeout. Use after Kickoff approval/review or when the user explicitly asks to ship an existing plan.
Skill Codex
Independently force an engineering plan toward the least machinery that achieves the requested outcome while preserving constraints and safety controls. Use for full plans, or when a fast/tiny plan introduces material complexity; return reconciled plan feedback, not code changes.
Skill Codex
Create and maintain a lightweight file-based delivery board made of milestones, epics, and executable tickets. Use when the user invokes /task-master or asks Codex to break a project into trackable work, set up or update an epic tracker, select the next ticket, coordinate agents, plan safe parallel work, resume an…
Skill Claude Code
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.
Skill Claude Code
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.
Skill Claude Code
Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via the authoring-a-skill playbook + unslop, optionally pulling fresh evidence from recent threads.
Skill Claude Code
Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benchmark or report a speedup or regression you measured.
Skill Claude Code
Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X', 'what could this break', or reviewing a small diff you don't trust.
Skill Claude Code
Restate the last message in plain human language, with no jargon.
Skill Claude Code
Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each time the operator corrects you. Use for /correct.
Skill Claude Code
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.
Skill Claude Code
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions via show-me-your-work. Use for /figure-it-out, 'figure it out', a large migration, or when no…
Skill Claude Code
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.
Skill Claude Code
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: