156 tagged hooks, measured the same way as everything else here.
Browse within: agents 219cli 141claude-code-plugin 136ai-workflow 135LLM 103coding-agents 100continuous-improvement 100macos 66code style 65code-style-guide 65agent-harness 53chinese 39prd 39marketplace 38
Skill Codex
The way to answer "how are my production AI agents doing?" and to run the team's agent-observability deployment — reach for it even on casual phrasing that names no tool. Trigger when the user wants to: • inspect agent telemetry — did agents error/fail/go flaky; sessions, events, latency, token usage, slowest models…
Skill Claude CodeCodex
Write captions, on-screen text, hashtags, and CTAs for short-form video that earn saves and sends without tripping engagement-bait penalties. Use when someone asks for a viral caption, an instagram caption or tiktok caption or video caption, wants to fix a weak cta or call to action, asks about hashtag strategy and…
Skill Claude Code
Use before reading whole files or grepping wide. token-goat commands (symbol, read, section, semantic, outline, map, refs, bash-output) return narrow slices at low token cost. /token-goat audit reviews a session for missed savings.
Skill Claude CodeCodex
Scaffolds a new WebMCP tool component using useMcpTool with Zod schema, handler, annotations, and wires it into the WebMCPProvider tree. Use when the user wants to expose functionality as an MCP tool, make something callable by AI, add a new tool, or create an AI-accessible action.
1596941391qq/ai-openclaw-skeletons
Skill Claude CodeCodex
A video post-production workflow that transcribes footage, removes silent sections, edits clips, adds effects and subtitles, and creates animated sections.
Skill Claude CodeCodex
Use when the user explicitly asks to install, uninstall, diagnose, or look up rules in VibeGuard. Ordinary coding, review, build failures, and generic safety requests do not activate this skill.
Skill Claude Code
Skill that manages configuration.
Skill Codex
Gate dependency installs (npm/pip/cargo/go/gem/maven/nuget) with OSV-backed advisory checks, approved-spec ledger, and post-install reorg rollback. Run safedeps check @ before any install command.
Skill Codex
For contributors working inside the B3Pay/ic-reactor repository: create, refactor, review and document the @ic-reactor/react hook layer and how the repository's docs, examples and codegen templates use it (createActorHooks, createQuery/createMutation factories, useActorMethod, TanStack Query cache invalidation…
Skill Claude Code
Claude Engram persistent memory — quick reference for all MCP tools and automatic hook behaviors, plus the /goal bracket commands (/engram run, stop, status, release, report). Use when you need to remember how to store, search, or manage memories, query session history, or supervise a /goal run that engram brackets.
Skill Claude Code
Use when the user asks about Codex Rules behavior, injected project rules, supported rule file locations, matching, or environment configuration.
wxmb01/codex-app-autonomous-runs
Skill Codex
Use when the user asks Codex App to run a project for a duration, keep working automatically, auto-improve a project, continue in the background, use human checkpoints only for risky actions, resume/pause/cancel/status an automation, or run a long autonomous project loop with self-review and reviewer subagents.
Skill Claude Code
Load a compact snapshot of the current repository into context — structure, stack, docs, git state.
naimkatiman/continuous-improvement
Skill Claude CodeCodex
Install structured self-improvement loops with instinct-based learning into Claude Code — research, plan, execute, verify, reflect, learn, iterate. On-demand or weekly analysis to save tokens. Supports multi-agent parallel analysis.
Skill Claude CodeCodex
Regla y catálogo para delegar pasos mecánicos (resumir, clasificar, extraer, boilerplate, mensaje de commit desde un diff, traducir texto o archivo, resumir salida de lint/tests/CI, explicar código, describir una imagen, verificar si el backend local está disponible) a modelos locales vía las tools local del MCP…
Skill Claude CodeCodex
On-demand Gemini quality audit for ANY work: code, videos, stories, advice, research, creative output. Use when user says "audit", "bouncer", "score", "score this", "score using gemini", "check my work", "quality check", "review my changes", "rate this", "how did I do". Quick mode (default): Gemini scores based on…
Skill Codex
Use when the user asks to use Throughline from Codex, continue or restore Throughline memory, export read-only handoff context for a local launcher, prepare a new Codex thread handoff, summarize a captured Codex session, or check whether the Throughline Codex Stop hook captured the current session. Hide long…
Skill Claude Code
Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading)…
Skill Claude Code
Instructions for writing and debugging dsh-hooks-plugin scripts, which run during tool or session events such as before a tool call or after it finishes. These scripts return JSON decisions such as allowing, asking about, or denying an action.
Skill Codex
Resolve credential identities, deliver secrets to a process, or administer entries through the MAINFRAME credential index and helper, without exposing values.
Skill Claude Code
TLA+ formal verification — extracts invariants, models state machines, checks for race conditions. Use after browser tests or manually. Triggers: verify, formal, invariant, TLA, race condition.
Skill Claude Code
Switch to freelance closing mode — mission qualification, scoping, quoting, and client relationship management.
langlanglanglanglang/rules-architect
Skill Claude Code
A set of rules for organizing Claude Code instructions across hooks, personal memory, path-specific rules, shared project instructions, and team lessons. It is written partly in Chinese and includes a five-question placement process.
Sora-bluesky/ja-output-harness
Skill Claude CodeCodex
A Japanese-language workflow for tuning the rules used by ja-output-harness, a checker for unwanted words or patterns in agent output.
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: