Skills for Claude Code

241,142 that install into Claude Code. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.

pomasa

5977

eXtremeProgramming-cn/pomasa

Skill Claude CodeCodex

Generate declarative multi-agent systems (MAS) using POMASA pattern language. Use when building agent pipelines, orchestrating multiple AI agents, or creating research automation workflows. Supports patterns like Prompt-Defined Agent, Orchestrated Pipeline, Filesystem Data Bus, and Verifiable Data Lineage.

not rated 56 +1 18d ago A 62 tokens

UCSC-VLAA/VisualClaw

Skill Claude CodeCodex

When asked to identify critical actions in a video, distinguish between preparatory/support actions and core actions that directly contribute to the main objective, and rank them by significance to the end goal.

not rated 56 +1 3mo ago A 44 tokens original MIT

create-arc-game

5979

theredbluepill/arc-interactive

Skill Claude CodeCodex needs its repo

This skill guides the creation of ARC-AGI-3 games based on established patterns from environmentfiles/.

not rated 56 +1 3mo ago A 0 tokens original MIT

fix-ci

5980

CliMA/CloudMicrophysics.jl

Skill Claude Code

Fix CI failures and performance regressions for a Julia package PR by iterating - triage the latest CI results, fix one root cause, verify locally, push. Use when a PR's GitHub Actions or Buildkite CI is failing, or when CI jobs run slower than they do on the main branch. Verifies CPU and GPU compilation locally…

not rated 56 +1 yesterday A 84 tokens copy · 100% Apache-2.0

ai_detect_for_sanqian

5982

houlaisan/deai-academic-zh

Skill Claude CodeCodex

A Chinese-language tool for detecting and rewriting wording that may appear AI-generated in academic papers. It focuses on changing expression without adding data, sources, or conclusions.

not rated 56 +2 5mo ago A 78 tokens original MIT

osint-investigator

5983

dkyazzentwatwa/osint-ai

Skill Claude CodeCodex

OSINT Investigator v2.1 — comprehensive open-source intelligence skill. Triggers on: OSINT, recon, digital footprint, dorking, social media investigation, username lookups, email tracing, domain recon, entity mapping, OPSEC, image verification, metadata analysis, threat intel, people search, background research. Slash…

not rated 56 +2 6mo ago A 256 tokens

agentdebug

5984

AgentDebugX/AgentDebugX

Skill Claude CodeCodex

Use AgentDebugX for trajectory diagnosis only when the user explicitly asks to use AgentDebug, AgentDebugX, or the agentdebug skill. Do not invoke for generic debugging, diagnosis, inspection, or trajectory-review requests.

not rated 56 +1 changed 14d ago A SkillSpector: pass 47 tokens original MIT

package-release

5985

dannote/dot-pi

Skill Claude CodeCodex

Prepare, publish, repair, or verify package releases and changelogs. Always use for package/version release, publish, ship, tag, changelog, release notes, registry publication, documentation publication, or GitHub Release work. Distinguish package releases from application deployments before acting.

not rated 56 +5 13d ago A SkillSpector: pass 60 tokens original MIT

open-tabletop-gm

5986

Bobby-Gray/open-tabletop-gm

Skill Claude CodeCodex

You are a seasoned, atmospheric Game Master running a persistent tabletop RPG campaign. Your tone is immersive and descriptive — paint scenes with sensory detail, give NPCs distinct voices, and let choices have real consequences. You lean toward "yes, and..." rulings and fun over rigid rule enforcement, but the world…

not rated 57 +1 yesterday A 0 tokens

afsim-skill

5987

qingzhoupro/afsim-skill

Skill Claude Code

A set of instructions for creating and fixing AFSIM scenarios. AFSIM is software used to simulate military operations, such as aircraft, sensors, weapons, movement and routes.

not rated 56 +2 3mo ago A 90 tokens original MIT

recallium-guidance

5988

recallium-ai/recallium

Skill Claude CodeCodex

Use when you have access to Recallium MCP tools. Provides guidance on memory storage, search, and knowledge management. CRITICAL - invoke the MCP tool recallium at session start, store memories after EVERY substantive interaction, and honor global rules.

not rated 56 +1 4mo ago A 57 tokens

fleet-audit

5989

gke-labs/kube-agents

Skill Claude CodeCodex

Publish the findings of an autonomous fleet audit as one continuously-rewritten GitHub issue per audit stream, and propose fixes as narrow remediation pull requests.

not rated 60 +3 changed today A SkillSpector: pass 33 tokens original Apache-2.0

huashu-design

5990

itgoyo/hermes-skills

Skill Claude CodeCodex

A design skill for making high-fidelity prototypes, interactive demos, slides, animations, and design variations with HTML. It can also provide design-direction advice and expert reviews.

not rated 57 +1 4mo ago A 503 tokens

pr-captain-land

5991

the-agency-ai/the-agency

Skill Claude Code

Captain-only. Land an agent's prepared branch LOCAL-FIRST — integrate and validate in a scratch worktree cut from origin/ , then bump agencyversion, sign a landing receipt, open the PR, confirm CI, merge, release, notify. The single-writer serialization point for agencyversion and PR creation. Companion to /pr-submit.…

not rated 57 +3 14d ago A 0 tokens

fastapi

5992

youlaitech/youlai-skills

Skill Claude CodeCodex

Development guidance for FastAPI, a Python framework for building backend web APIs. It covers asynchronous database access with SQLAlchemy, data validation with Pydantic v2, login tokens using JWT and Redis, and the youlai-fastapi admin backend.

not rated 56 +1 27d ago A 49 tokens

omp-fleet

5993

avenoxai/avenoxskills

Skill Claude CodeCodex needs its repo

Standalone runner + fleet orchestrator for Oh My Pi (omp), a coding-agent CLI that reaches your existing OpenAI Codex subscription through a different harness. Does THREE things and always EXECUTES them (never just describes): (1) general code tasks via omp -p, (2) cheap high-volume context gathering on the…

not rated 56 +8 changed 5d ago A SkillSpector: warn 0 tokens original MIT

agent-optimize

5994

skillberry-ai/cap-evolve

Skill Claude Code

Free-form optimization algorithm for agent orchestration mode: the conversational agent owns the whole search — proposing capability edits itself, screening them cheaply, gating each on full val, and sealing test once. Use when orchestrationmode is agent and algorithmskill is agent-optimize. For a deterministic loop…

not rated 56 changed 8d ago A SkillSpector: pass 73 tokens original Apache-2.0

cn-patent-drafter

5995

handsomeZR-netizen/cn-patent-drafter

Skill Claude Code

A drafting and checking assistant for Chinese invention-patent applications filed with CNIPA, China's patent office. It works with LaTeX files for the request form, abstract, claims, description, and drawings.

not rated 56 +6 4mo ago A 133 tokens original MIT

mcp

5996

wynsyl1014/open-watch-cinema

Skill Claude CodeCodex

Use this skill whenever you are connected to Open Watch Cinema through its MCP server.

not rated 56 +5 1mo ago A 0 tokens original MIT

xuansenpa1/skillrevise

Skill Claude CodeCodex

Generate structured CSV security audit reports from vulnerability data with proper filtering and formatting. This skill covers CSV schema design for security reports, using Python csv.DictWriter, severity-based filtering, and field mapping from JSON to tabular format.

not rated 56 12d ago A SkillSpector: pass 52 tokens original MIT

tricorder-cli

5998

tweag/tricorder

Skill Claude Code needs its repo

Full CLI reference for the tricorder daemon (build diagnostics, test results, source lookup, eval comments, logs). This is the fallback invoked by the tricorder skill when the tricorder-mcp MCP tools aren't available or aren't working — invoke tricorder first; it decides whether this is needed.

not rated 56 changed 2d ago A 67 tokens original MIT

vrooli-ui-interop

5999

Vrooli/Vrooli

Skill Claude CodeCodex

Ensure scenario UIs work reliably across all three Vrooli deployment contexts — localhost development, Cloudflare tunnel, and app-monitor proxy/iframe — by adopting @vrooli/api-base and @vrooli/iframe-bridge with consistent file-level conventions.

not rated 56 today A 0 tokens AGPL-3.0

crow-cli

6000

crow-cli/crow-cli

Skill Claude CodeCodex

The crow-cli map — where the source lives, how a running agent was spawned, and how to change, upgrade, or repair crow-cli itself. Use when the task touches crow-cli's own code or install ("fix crow-cli", "upgrade crow-cli", "reinstall", "where is the source", "the checkout", "crow-cli init", "project agent", "why is…

not rated 56 3d ago A 137 tokens AGPL-3.0

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: