Claude Code skills

49,654 tagged Claude Code, measured the same way as everything else here.

Browse within: agentic-ai 302antigravity 267agentic-skills 191ai-workflows 185coding-agents 155agentic-framework 109agentic-workflow 109swarm 109Autonomous Agents 106claude-code-skills 100ci 97actions 96cai 96gh-extension 96

whiteboard-voice-notes

2065

CocoRoF/Geny

Skill Claude Code

When the user shares a voice recording on the whiteboard, naturally recognize the auto-generated transcript and bring it up in conversation. If the transcript is missing/empty or the user explicitly asks for re-transcription, recover it with the whiteboardtranscribe tool.

not rated 11 15d ago A SkillSpector: pass 59 tokens original Apache-2.0

local-search

2066

KempnerInstitute/hpc-agentic-recipes

Skill Claude CodeCodex

Search the web, arxiv, Crossref, PubMed, OpenAlex, or Wikipedia, and fetch page text, using common/tools/search.sh. Use whenever the user asks to search online, look something up, or find papers while served by a local model, and whenever the built-in WebSearch tool fails or is silently dropped by the endpoint.

not rated 11 18d ago A 73 tokens original MIT

no-slop

2067

Byk3y/no-slop

Skill Claude CodeCodex

Avoid AI writing patterns when producing prose. Use when writing articles, blog posts, documentation, emails, proposals, reports, README content, PR descriptions, release notes, or any long-form text. Activates for drafting, composing, or writing tasks.

not rated 11 +1 5mo ago A 54 tokens original MIT

interactive-learning

2068

CyanDR21/Cyanskill

Skill Claude CodeCodex

An interactive learning system based on Bloom's 2 Sigma learning theory, which adapts lessons to a student's answers and progress.

not rated 11 +1 changed 10d ago A 163 tokens

agent-teams

2069

maystudios/maxsimcli

Skill Claude Code

Coordinates Tier 2 Agent Teams with TeamCreate, SendMessage, competitive implementation, multi-reviewer code review, and collaborative debugging patterns. Used when workflows require inter-agent communication, adversarial debate, or shared task lists.

not rated 11 +1 5mo ago A 48 tokens

eval

2070

julienamorgan/signal-prospecting-kit

Skill Claude Code

Test harness for the Signal Prospecting Kit v4.1. Runs deterministic checks and rubric-based grading against all 6 skills including tool connections, multi-batch flow, LinkedIn outreach, channel selection, self-improvement loop, enrichment tiers, bridge/CTA variation, variation planning, and fallback tool detection.…

not rated 11 +1 3mo ago A 99 tokens

write-detection-rule

2071

akasecurity/ai-tc

Skill Claude CodeCodex

This skill teaches Claude Code how to write detection rules for the AI Traffic Control rule engine. Read this before creating or modifying anything in rules/. The full rule schema is Rule in packages/schema/src/zod/rule.ts — it is the source of truth for every field below.

not rated 11 yesterday A SkillSpector: warn 0 tokens original Apache-2.0

302ai-api-integration

2072

302ai/302AI-API-Integration-Skill

Skill Claude CodeCodex

ALWAYS use this skill when user needs ANY API functionality (AI models, image generation, video, audio, text processing, etc.). Automatically search 302.AI's 1400+ APIs and generate integration code. Use proactively whenever APIs or AI capabilities are mentioned.

not rated 11 4mo ago A 60 tokens original Apache-2.0

md-triage

2073

pwya/md-paper

Skill Claude Code

A tool that turns scattered revision requests into a checked list of separate, actionable changes in md_triage.md. Revision requests can come from reviews, emails, meeting transcripts, PDFs, images, or personal notes.

not rated 11 +1 8d ago A SkillSpector: pass 320 tokens original Apache-2.0

ui-framework

2074

wangjianqi/AppStore

Skill Claude CodeCodex

A set of rules for building iOS interfaces with UIKit, Apple's interface framework. It defines choices for layout, navigation, colors, fonts, dark mode, keyboard handling, and related views.

not rated 11 3mo ago A 36 tokens original MIT

ai-advisory-board

2075

evoputa/ai-advisory-board

Skill Claude CodeCodex

AI-powered advisory board of 100+ real-world business leaders spanning 18 domains, 4 continents, and balanced gender representation. Each leader speaks in their authentic voice using their documented frameworks and principles. Convenes boardroom sessions with 3-5 relevant advisors, allows disagreement, and delivers a…

not rated 11 +1 5mo ago A 125 tokens original MIT

release-notes

2076

xyiqq/skilldoctor

Skill Claude CodeCodex

Drafts concise release notes from merged pull requests and conventional commits. Use when the user asks for a changelog, release notes, or a GitHub release body.

not rated 11 28d ago A 37 tokens original MIT

learning-from-outcomes

2077

romainsimon/skills-for-decision-making

Skill Claude CodeCodex needs its repo

Turns past decisions into calibrated judgment - scoring old predictions against what happened, assigning credit for delayed results, and separating a bad decision from a good decision that lost. Use during a retrospective, postmortem, quarterly or monthly review, when reviewing decisions taken 30+ days ago, when…

not rated 11 +2 1mo ago A 79 tokens original MIT

qovery-policy-token

2078

Qovery/qovery-skills

Skill Claude CodeCodex

Creates a scoped Qovery API Policy Token from a user's intent — authors a least-privilege Open Policy Agent (Rego) policy, tests it locally with OPA and live against the API, creates the token, and verifies it allows exactly what the user wants and denies everything else. Use when the user wants a restricted…

not rated 11 changed 9d ago A 109 tokens

bastra-recall

2079

n0mad-ai/bastra-recall

Skill Codex

Persistent external brain for ChatGPT, Codex, Claude, and other MCP clients — documents (PDFs, contracts, scans with OCR), personal facts (appointments, decisions, items, amounts), AND code lessons / preferences / project topology. USE PROACTIVELY in three modes. (1) RECALL — whenever the user asks about anything from…

not rated 11 +2 changed today A SkillSpector: pass 0 tokens original MIT

jeremylongshore/plugins-nixtla

Skill Claude Code

Generate production-ready MCP server implementations from PRD tool specifications with schema validation, error handling, and testing infrastructure. Use when building MCP servers for Nixtla plugins, implementing tool handlers, or scaffolding server infrastructure. Trigger with 'build MCP server', 'generate MCP…

not rated 11 4d ago A 70 tokens

chanlun-engine-skill

2081

adsorgcn/chanlun-engine-skill

Skill Claude CodeCodex

A Chinese-language stock-analysis skill based on Chan theory, a method for interpreting price-chart structures such as turning points and trading ranges.

not rated 11 +2 19d ago A 128 tokens original MIT

agent-handoff

2082

sifxprime/kodelyth-ecc

Skill Claude CodeCodex

How to chain ECC specialist agents for multi-step problems — pair-programmer → tdd-guide → code-reviewer → security-reviewer. Use when one agent finishes its job and the next logical step needs a different specialist. Documents the standard handoff protocol so agents pass context cleanly.

not rated 11 4d ago A SkillSpector: pass 61 tokens original MIT

adjust

2083

rlacombe/switchback-running

Skill Claude Code

Adapt upcoming training to symptoms, recovery, schedule, or changing goals.

not rated 10 changed 5d ago A 13 tokens original MIT

ptrade-dev

2084

kay-ou/ClaudeSkills

Skill Claude Code

PTrade/SimTradeLab strategy development guardrails. Auto-loads PTrade API reference, enforces platform constraints (no f-string, no import io/sys), validates lifecycle function usage, and prevents common API misuse. Use when writing, editing, or reviewing any PTrade strategy code or SimTradeLab backtest code. TRIGGER…

not rated 10 +1 5mo ago A 126 tokens original MIT

release

2085

narlei/claudecodenotify

Skill Claude Code

Cut and publish a new GitHub release for the ClaudeCodeNotify macOS app. Use this whenever the user wants to release, ship, publish, cut, or tag a new version — phrases like "create a release", "ship the release", "publish v1.0.x", "tag and release the app", "cut a new version", or "make a release". It builds the…

not rated 10 2mo ago A 147 tokens original MIT

cost-audit

2086

berkcangumusisik/claude-code-practices

Skill Claude Code

Analyzes the current session's token usage, pinpoints where tokens were wasted, and produces concrete optimization actions.

not rated 10 4mo ago A 25 tokens original MIT

gatling-best-practices

2087

rcampos09/performance-testing-skills

Skill Claude CodeCodex

Guides developers and testers in writing, fixing, and structuring Gatling load test scenarios. Use this skill whenever the user mentions load testing, performance testing, stress testing, Gatling, virtual users, VUs, ramp-up, injection profiles, simulations, JMeter migration, k6 migration, throughput, response time…

not rated 10 6mo ago A 99 tokens

sql-expert

2088

hmohamed01/SQL-Expert

Skill Claude CodeCodex

Write, optimize, and debug T-SQL queries for Microsoft SQL Server. Covers CTEs, window functions, PIVOT, MERGE, APPLY operators, execution plan analysis, indexing strategies, and stored procedures. Use when working with SQL Server, T-SQL scripts, .sql files, stored procedures, query optimization, or database…

not rated 10 5mo ago A 75 tokens

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: