Claude Code skills

50,349 tagged Claude Code, measured the same way as everything else here.

Browse within: agentic-ai 337antigravity 270agentic-skills 191ai-workflows 185coding-agents 175agentic-framework 109agentic-workflow 109swarm 109Autonomous Agents 106LLM 103ci 97actions 96cai 96gh-extension 96

project-context

3961

r00tbear/project-context-skill

Skill Codex

Audit, bootstrap, refresh, visualize, review, or upgrade technology-neutral Project Context for a Git repository shared by Claude Code and Codex. Use for repository audits and greenfield planning; PROJECTCONTEXT.md/CLAUDE.md/AGENTS.md setup; architecture, stack, debt, security, testing, UI, and data guidance…

not rated 2 28d ago A 192 tokens original MIT

labor-law-guide

3962

chouenchieh/labor-law-guide

Skill Claude CodeCodex

A process for creating country-specific labour-law compliance guides. It uses NotebookLM, a tool for researching and working with source documents, through a browser connection, then creates a Word document.

not rated 2 4mo ago C 65 tokens

architecture-review

3963

korbinjoe/TeemAI

Skill Claude Code

Architecture review skill. Provides a complete 9-dimension review model, 4 analysis techniques, 8 major anti-pattern detection checklists, and structured report templates. Triggers when user says "review architecture", "architecture health check", "analyze module dependencies", "evaluate evolvability".

not rated 2 2mo ago A 62 tokens original MIT

kanban-dev-lane

3964

epicsagas/plugins

Skill Claude CodeCodex

Use when a Hermes Kanban worker wants to run an autonomous implementation delegation lane with a 3-tier fallback chain across claudy -> codex (--yolo) -> agyd (agy --dangerously-skip-permissions) -> Hermes direct on quota exhaustion.

not rated 2 4d ago A 58 tokens original Apache-2.0

handoff

3965

scottbaggett/agent-bus

Skill Claude CodeCodex

Hand work to — or pick up work from — an agent running in another window (Codex pane, other Claude Code session) via agent-bus. Use when the user says "hand this off", "what's the other agent doing", "check the bus", "tell codex about this", "pick up where the other window left off", or when coordinating edits so two…

not rated 2 yesterday A 88 tokens

wwdc-skills

3966

cruisediary/wwdc-skills

Skill Claude CodeCodex

Reference skill for Apple WWDC developer sessions (WWDC18–WWDC25). Covers Swift, SwiftUI, SwiftData, Swift Concurrency, UIKit, ARKit, RealityKit, visionOS, Xcode, and all Apple frameworks. Use when asked about Apple APIs, iOS/macOS/visionOS development, WWDC session content, API migration, or any Apple developer…

not rated 2 5mo ago A 107 tokens original MIT

cursor-reveal-hero

3967

sergekostenchuk/mouse-trail-masking-reveal

Skill Codex

Build, repair, tune, and validate interactive cursor-trail mask reveal hero effects in frontend projects. Use when implementing canvas-based base/reveal compositing, soft radial cursor masks, fading cursor trails, reveal debug controls, full-screen hero scenes without site text, or browser smoke checks for cursor…

not rated 2 3mo ago A 80 tokens copy · 92% MIT

hot-start

3968

yogsoth-ai/north-star-crystallization

Skill Claude CodeCodex

Minimal crystallization strategy for users who already have a specific research topic or problem (e.g., "I want to improve CoT faithfulness in LLMs") and need structuring into a formal North Star. Heavily simplifies or skips exploration tactics, focusing on obstacle analysis, goal decomposition, and synthesis. Use…

not rated 2 3mo ago A 80 tokens original Apache-2.0

parcel-kau-a

3969

AugustusW/parcel-kau-a

Skill Claude CodeCodex

A command-line tool for checking Taiwanese parcel deliveries by tracking number. It supports several Taiwanese courier services and can show current status, pending parcels, and lookup history.

not rated 2 15d ago A 309 tokens original MIT

compass

3970

Aether-liusiqi/compass

Skill Claude CodeCodex

An AI assistant workflow for choosing university applications in China's Gaokao system, the national college entrance examination. It compares scores and rankings with school and major choices while accounting for regional admission rules.

not rated 2 2mo ago A 132 tokens original MIT

transcript-to-epub

3971

forsvn-labs/transcript-to-epub

Skill Claude Code

Turn a YouTube URL or a local timestamped transcript into a designed, attributed EPUB reading edition. Auto-detects speakers/channel, cleans timestamps, always credits the original creators, and builds both a clean Markdown book and a book.epub.

not rated 2 23d ago A 56 tokens original MIT

ai-loop-cycle

3972

s977043/PlanGate

Skill Claude CodeCodex needs its repo

A runbook for one cycle of an AI-assisted change review: collect files, run checks, make a decision, save a record, and follow the result.

not rated 2 changed 7d ago A 140 tokens original MIT

ogr2ogr-recipes

3973

buildmoonshot/skillpacks

Skill Claude CodeCodex

Use when converting, reprojecting, filtering, or loading vector data between formats with GDAL/OGR (ogr2ogr) — shapefile, GeoJSON, GeoPackage, PostGIS, and similar. Makes the agent use correct, safe ogr2ogr invocations instead of guessed flags, and prefer robust formats over fragile ones.

not rated 2 3mo ago A 73 tokens original MIT

high-plains-drifter

3974

alexconner-79/high-plains-drifter

Skill Claude CodeCodex

Align a design to your real Storybook components instead of reconstructing it. Use when turning a Figma frame into React built from an existing component library (Build mode), or when pulling scrappy exploratory code into line with the library once a direction feels right (Align mode). Triggers include "build this…

not rated 2 3mo ago A 148 tokens original MIT

twofold

3975

ducquoc-gft/twofold

Skill Claude CodeCodex

Compacted communication mode. Cuts token usage 50%90% by speaking like Feynman while keeping full technical accuracy. Intensity levels: short, long, cc. Use when user says "twofold mode", "2f mode", "sl mode", "use 2f", "use twofold", "use sl", "be brief", "trả lời ngắn", "shorthand longform", "simple lengthy" or…

not rated 2 2mo ago A 123 tokens

kempt-checkup

3977

xz1220/Kempt

Skill Claude CodeCodex

Run a read-only Kempt health check on the local AI-coding-agent state (/.claude, /.codex) and explain the agent-debt report. Use when the user asks why their coding agent feels slow, confused or inconsistent, mentions "agent debt" / "agent 体检" / "agent health", or wants to know what junk has piled up in their Claude…

not rated 2 3mo ago A 89 tokens original MIT

luma-event-promo

3978

Haili321/haili-auto-mkt

Skill Claude CodeCodex

End-to-end Luma event launch: research comparable events in the target city, draft copy that doesn't read like AI slop, create a Private draft via the admin API, fix the startat / duration / capacity traps, and polish theme, font, and cover. Use this whenever the user wants to publish, edit, or shape an event for…

not rated 2 3mo ago A 111 tokens original MIT

saas-cybersecurity

3979

YankielDBC2/saas-cybersecurity

Skill Codex

Audit and safely harden authorized SaaS web applications across frameworks and hosting providers. Use for OWASP-aligned reviews, runtime browser checks, HTTP headers, XSS/CSRF, access control, secrets, payments, uploads, privacy, abuse controls, supply-chain risk, link injection, or security remediation; do not use…

not rated 2 19d ago A 86 tokens original MIT

ponytail-help

3980

tarunag10/ai-switchboard

Skill Claude Code

Quick-reference card for all ponytail modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /ponytail-help, "ponytail help", "what ponytail commands", "how do I use ponytail".

not rated 2 23d ago A 56 tokens copy · 91% MIT

cognitive-kernel

3981

d-wwei/cognitive-kernel

Skill Claude CodeCodex

A skill for setting up and installing the Cognitive Kernel system. It reads a manifest, which is a file describing what needs to be installed, and checks whether it is already present.

not rated 2 5mo ago A 37 tokens

code-review

3982

sansec-ai/codeclaw-vscode

Skill Claude CodeCodex

Systematic code review patterns covering security, performance, maintainability, correctness, and testing — with severity levels, structured feedback guidance, review process, and anti-patterns to avoid. Use when reviewing PRs, establishing review standards, or improving review quality.

not rated 2 5mo ago A 54 tokens original MIT

adversarial-spec

3983

chpomob/adversarial-spec

Skill Claude CodeCodex

Adversarial specification writer. Takes a brief (from grill-me or user) and produces a structured spec.md with YAML frontmatter, requirements, acceptance criteria, and target files. Git-aware pipeline: each run on its own branch, squash-merge on approval.

not rated 2 1mo ago C 58 tokens

resume-any-chat

3984

adarshnagrikar14/resume-any-chat

Skill Codex needs its repo

Use when the user wants to inspect, search, normalize, resume, hand off, or optionally import local Codex, Claude, or Antigravity CLI conversation history. This skill provides a local viewer, provider-specific parsers, native resume commands, a Codex handoff flow, and an explicit experimental Codex-history import path.

not rated 2 3mo ago A 71 tokens original MIT

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: