claude-code-plugins

codex-orchestrate

Claude Code only. Use when the user explicitly invokes /agents-bridge:codex-orchestrate (or /codex-orchestrate) in Claude Code or asks Claude to orchestrate a large multi-slice plan by delegating implementation to the Codex CLI through agents-bridge. In native Codex, use $slice-runner instead.

codex

Invoke OpenAI Codex CLI for cross-model collaboration

critique

Critical second opinion from Codex (OpenAI) on a proposal Claude just made — confirms what is sound, challenges what is genuinely weak, and suggests a better path with clear reasoning when one exists. Constructive, not contrarian. Use to cross-check a Claude design, refactor, API, or fix with a non-Claude model before acting on it.

imagegen

Generate or edit images with the Codex CLI's built-in image_gen tool. Use when the user asks to create, generate or draw an image, icon, logo, favicon, illustration or mockup, or to edit an existing image file — restyle, retouch, upscale, add or remove elements.

pair-planning

Start a session in pair-planning mode where Claude and Codex (read-only) each draft an independent implementation plan for a task, then cross-review through an open-point ledger until consensus, escalating remaining disagreements to the user. Produces one agreed plan; does not write code. Use at the start of a task to align two frontier models on the approach before implementation.

greenfield-audit

Read-only architecture audit that grants the existing code no authority: derive the requirements, design the minimal from-scratch architecture, then classify every important component KEEP / SIMPLIFY / REPLACE / DELETE. Diagnostic in the chat, no file edited.

null-as-error-cc

Audit an Effect codebase for silent error swallowing -- catchAll patterns that collapse errors into sentinel values (null, [], false, void) in the success channel. Runs a scanner script, spawns a read-only auditor, and produces a classified report. NOT for: non-Effect projects, React/frontend code, plain TypeScript without Effect.

refactorlib-cc

Audit a codebase for handcrafted code that duplicates functionality already available in the project's dependencies. Reads package.json, launches parallel exploration agents, verifies replacement feasibility, and produces a structured refactor plan. Audit only -- does not execute changes.

structured-plan

Rigorous planning workflow with research validation, task breakdown, dependency mapping, and post-implementation verification. Use when: (1) planning complex features touching 5+ files, (2) architectural changes or major refactors, (3) unfamiliar tech requiring doc research, (4) user says "thorough plan", "rigorous plan", or "structured plan". Invoke with /structured-plan before or during plan mode.

ship

Ship a feature branch: prepare a clean PR (strip working files with intelligent suggestions), create/update the GitHub PR, then merge to main with GPG signing when ready. Detects lifecycle stage automatically. Use when: "ship", "prep pr", "create pr", "open pr", "merge to main", "submit for review", "push for review", "ship this branch".

skill-creator

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

meta-prompt

Turn a rough request or the preceding conversation into a clean prompt for another agent, carrying the user's intention at the user's level of certainty. Use when the user asks to write a prompt, meta-prompt, briefing, or handoff for a separate agent session, or wants to delegate a task just discussed to a fresh instance.

Show all 42 bundled skills

clean-comments

Audit and clean code comments with four actions: REFACTOR (comment compensates for unclear code), KEEP (why / external constraint / trap), REMOVE (paraphrase, decorative banners), FIX-VERIFY (factual claim checked against the code). Protects why and constraint comments; hunts comments that lie — stale cited paths, wrong hard-coded numbers, guarantees the code refutes. Use when the user wants to clean, audit, review or deslop comments, remove comment slop, or suspects stale or misleading comments.

verify-no-regressions

Verify no behavioral regressions after implementation. Spawns parallel subagents for semantic diff review + test execution. Use when: user says "verify no regressions", "check for regressions", "make sure nothing broke".

t-plan

Thorough planning for complex features via delegated subagents. Turn discussions into executable, self-contained implementation plans. USE for multi-file features, architectural changes, unfamiliar tech requiring research. SKIP for quick fixes or single-file changes.

context-audit

Audit and improve CLAUDE.md, AGENTS.md and .claude/rules/ for instruction budget, anti-patterns and stale references, then apply approved REMOVE/MOVE/REWRITE/ADD fixes

revise-claude-md

Capture this session's learnings (commands, gotchas, patterns) into CLAUDE.md or .claude/rules/

sync-claude-md

Sync project CLAUDE.md with codebase evolution, using git history since the file last changed to motivate every proposed update

git-sweep

Clean stale git branches and worktrees interactively. Audits local/remote branches, proves which ones the base already contains (including after a squash or rebase), frees finished worktrees, and confirms before deleting. Use when: "git sweep", "sweep branches", "branch cleanup", "prune stale branches", "clean up agent worktrees".

commit

Commit the current work with a message that follows the repo's convention, closing the branch's issue when its name carries a number. Use when the user asks to commit, to record the work, or to save a change to history.

rebase

Interactive rebase of the current branch with a visual plan and reworked commit messages, no editor. Use when the user asks to rebase, rewrite, reorder, reword, or clean up commits, or to continue, skip, or abort a paused rebase.

squash

Squash git commits by pattern, hash list, or the last N, without opening an editor. Use when the user asks to squash, fold, or combine commits, or to collapse fixup and WIP commits.

await-merge

Wait for a PR's checks, merge it with linear history, update the local base branch.

commit-push-pr

Commit the current work, push the branch, then open or update its pull request.

dispatch

Hand ready GitHub issues to issue-worker subagents that implement, verify and open their own pull request, one worker per issue. Use when the user asks to dispatch, assign, or hand issues to agents, or to turn issues into PRs.

issue

Write or rewrite a GitHub issue as a context-rich prompt for another agent. Proves the problem with evidence from the code, gives hints instead of a plan, ends with observable acceptance criteria. Use when the user asks to file, write, draft, open, or rewrite an issue.

pr

Open or update the pull request of the current branch with a body sized to the change and images attached through gh. Use when the user asks to open, create, submit, update, or rewrite a PR, or to push and open one.

shift

Run one pass of the issue-to-PR loop: triage the open issues, dispatch the ready ones to agents, keep the loop's pull requests green, and return a digest. Use when the user asks to run a shift, to work the backlog on its own, or to run the issue loop.

stacked-prs

Run a stack of pull requests on GitHub with `gh stack`: create, grow, submit, sync, land, repair, and cut a per-layer worktree with its handoff. Use when the user talks about stacked PRs, a stack or pile of PRs, `gh stack`, wants to split a large change into reviewable PRs that land together, or debugs a stack (empty PR "No commits between X and Y", "Needs rebase", local/GitHub divergence, a commit stuck under someone else's).

triage

Verify an open GitHub issue or PR against the current code and act on the verdict: close or comment with a factual proof, or report work that is still valid. Use when the user asks to triage, verify, check, handle, or clean up an issue, a PR, or the tracker.

goalify

Convert rough coding, product, architecture, audit, review, migration, cleanup, debugging, or orchestration intent into the smallest useful goal payload to hand to a fresh Claude Code agent (a new session, a subagent, or /loop). Invoke with /goalify, or "/goalify interactive" to be questioned one point at a time before the goal is written. Produces goal text only, never the downstream implementation.

mermaid-diagrams

Create Mermaid diagrams. ONLY use when user explicitly says "Mermaid". NOT for general diagrams, schemas, ASCII art, or wireframes.

Testing & QA Listed

layer-testing

Generate comprehensive tests for architectural layers with coverage-first analysis. Use when testing specific layers (core, domain, application, infrastructure, boundary). Reads testing strategy from playbook or uses interactive template selection.

plugin-cache-sync-usage

Show plugin-cache-sync status and explain sync workflow

linear-flow

Migrate a repo to the dev-trunk/main-release fast-forward model (no merge commits) and load its doctrine. One-shot setup; day-to-day rules live in each repo's CLAUDE.md afterwards.

submodule-setup

This skill should be used when the user asks to "set up submodules", "migrate branches to submodules", "automate submodule sync", "create submodule architecture", "convert branches to repos", or mentions setting up git submodules with GitHub Actions automation for multi-repo synchronization.

search-claude-docs

Search the official Claude Code docs through the claude-code-docs MCP server with progressive disclosure, and date a behavior with the changelog.

Web & Frontend Listed

cli-design

Create distinctive, user-respecting command-line interfaces with exceptional UX. Use this skill when the user asks to build CLI tools, scripts, or terminal applications. Generates well-crafted CLIs that follow platform conventions and treat users as humans, not machines.

Data & Documents Listed

excellence-skill-creator

Create opinionated, anti-slop skills that encode taste. NOT for: general skill structure, reference guides, procedural docs (use skill-creator instead). USE for: frontend-design, cli-design, system-architecture style skills. Triggers: "anti-slop skill", "opinionated skill", "make Claude less generic", "skill like frontend-design", "design-excellence skill".

iaqi

Iteratively improve artifacts via parallel reviewers with anchor-based drift prevention. NOT for: one-shot edits, simple fixes, tasks without measurable quality. USE for: skills, prompts, commands, agents needing iterative refinement with score targets. Triggers: "iterate to 9.0", "quality loop", "IAQI", "reviewer loop", "improve until threshold", "iterative quality".

system-architecture

Design systems with appropriate complexity—no more, no less. Use this skill when the user asks to architect applications, design system boundaries, or make structural decisions. Generates pragmatic architectures that solve real problems without premature abstraction.

thorough-plan

Adaptive pre-planning exploration loop. Builds sufficient context before committing to a detailed plan. Use when: (1) brief is ambiguous or underspecified, (2) task touches unfamiliar code or libraries, (3) multiple valid approaches exist and the right one isn't obvious, (4) user says "thorough plan" or invokes /thorough-plan. NOT for trivial tasks where the path is obvious — triage will skip exploration in those cases.