agents skills

8,796 tagged agents, measured the same way as everything else here.

Browse within: LLM 422agentic-ai 271azure 179sdk 178tool-use 177ai-scientists 176reasoning-agent 176reasoning-language-models 176foundry 167agentskills 148cortex 147cortexai 147snowflake 147agent 139

skill-evaluator

193

HeshamFS/materials-simulation-skills

Skill Claude CodeCodex

Rigorously evaluate an Agent Skill end-to-end across ANY coding-agent CLI — verify its scripts emit the documented numbers (deterministic checks), test whether its description triggers on the right prompts, and measure whether an agent following the SKILL.md beats a no-skill baseline (with/without pass-rate delta…

not rated 66 +1 2mo ago A 181 tokens original Apache-2.0

ctf-crypto

194

DekaPrayoga/AurixAgent

Skill Claude Code

Provides cryptography attack techniques for CTF challenges. Use when attacking encryption, hashing, signatures, ZKP, PRNG, or mathematical crypto problems involving RSA, AES, ECC, lattices, LWE, CVP, number theory, Coppersmith, Pollard, Wiener, padding oracle, GCM, key derivation, or stream/block cipher weaknesses.

not rated 63 +1 1mo ago A 78 tokens

dagr-producer

195

aemrebarut/herdr-dagr

Skill Claude CodeCodex

Emit and maintain a dagr run file — a live, contract-valid JSON description of recursive projects, tasks, attempts, gates, evidence, policies, events, and operator-message resolutions that dagr view renders as a DAG. Use when orchestrating agents or tracking multi-step work that a dagr pane should display.

not rated 62 +4 15d ago A SkillSpector: pass 70 tokens original Apache-2.0

api-interface-design

196

MohitGoyal09/AgentForge

Skill Claude CodeCodex

Use when designing public APIs, module boundaries, provider adapters, tool schemas, or data contracts.

not rated 61 2mo ago A 23 tokens original MIT

behavioral-analysis

197

HuTa0kj/vetix

Skill Claude CodeCodex

Analyzes security risks in the AI Agent/MCP Skill catalog. Used when users request to inspect, audit, review, or scan the Skill catalog for potential security risks, including command injection, data leakage, prompt word attacks, stealth access, remote execution, or other malicious activities within the SKILL package.

not rated 61 1mo ago C 65 tokens original MIT

add-mcp-server

198

oguzbilgic/kern-ai

Skill Claude CodeCodex

Add a Model Context Protocol (MCP) server to extend your toolbox with external tools.

not rated 62 today A 22 tokens

computer-basics

199

thomasbek3/hermes-bot-kit

Skill Claude CodeCodex

How this bot uses its pinned Orgo cloud computer (opt-in load).

not rated 61 +4 4d ago A SkillSpector: pass 19 tokens original MIT

find-awesome-tools

200

bh-rat/context-awesome

Skill Claude CodeCodex

Discovers curated tools, libraries, frameworks, and resources across thousands of awesome-lists. Use this skill whenever the user is shopping for options in a technology space — "what are good Rust CLI argument parsers", "recommend React state management libraries", "popular Python web frameworks", "tools for building…

not rated 59 2mo ago A 195 tokens original MIT

triaging-mutants

201

mattwynne/yaks

Skill Claude CodeCodex

Use when mutation testing reveals survived mutants — guides deep analysis of whether each mutant signals a missing test, a design improvement opportunity, or an equivalent mutation.

not rated 58 +2 26d ago A SkillSpector: warn 34 tokens original MIT

agent-board-routing

202

DanWahlin/ai-agent-board

Skill Claude CodeCodex

Use when Dan explicitly asks Claude, Codex, Copilot, Grok, Hermes, OpenCode, or OpenClaw to perform coding work. Route it through the shared AI Agent Board instead of launching the coding agent directly.

not rated 57 13d ago A SkillSpector: pass 50 tokens original MIT

loom-plan-writer

203

cosmix/loom

Skill Claude Code

REQUIRED skill for creating Loom execution plans.

not rated 54 changed today A SkillSpector: warn 14 tokens original MIT

jackson-3-migration

204

navikt/copilot

Skill Claude CodeCodex

Migrer Jackson 2.x til Jackson 3.x (tools.jackson) i Kotlin/Java-prosjekter — automatisert OpenRewrite-pass pluss manuell Kotlin-spesifikk opprydding og verifisering.

not rated 54 today A SkillSpector: warn 53 tokens original MIT

hr-kpi

205

tuanductran/hr-skills

Skill Claude CodeCodex

Help HR managers, people analytics teams, and HR business partners understand, select, calculate, and act on HR KPIs and workforce metrics. Use when asked to build an HR KPI dashboard, choose strategic HR KPIs, analyze turnover rate, benchmark cost per hire, explain HR metrics, create an HR report for leadership…

not rated 55 today A SkillSpector: pass 98 tokens original MIT

allinherog-star/ai-skills

Skill Codex

A risk-review guide for marketing, sales, operations, and legal work. It uses provided material to identify concerns and turn them into clear findings and next steps.

not rated 51 3mo ago A 71 tokens

cortex-memory

208

Fozikio/cortex-engine

Skill Claude CodeCodex

Persistent cognitive memory for AI agents — query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and NLI contradiction detection.

not rated 49 19d ago A SkillSpector: pass 36 tokens original MIT

js-gof

209

metarhia/metaskills

Skill Claude CodeCodex

Apply Gang of Four and related design patterns in JavaScript and TypeScript. Use when implementing creational, structural, or behavioral patterns, or when the user mentions factories, builder, prototype, flyweight, singleton, object pool, adapter, wrapper, decorator, proxy, bridge, composite, facade, chain of…

not rated 49 +1 1mo ago A SkillSpector: pass 107 tokens original MIT

t2a-memory

210

t2a-protocol/T2A

Skill Codex

Use to install T2A Memory, remember a fact in local memory, and resolve the emitted T2A handoff without LLM API keys.

not rated 48 1mo ago A 35 tokens original Apache-2.0

web-components

211

AdamBien/airails

Skill Claude Code needs its repo

Architecture and coding rules for single-page applications using web components, BCE layering, lit-html templating, unidirectional Redux-style state management (reduction.js, standards-based), and standards-based client-side routing (Navigation API + URLPattern). Web standards and web platform first, minimal external…

not rated 48 +1 3d ago A SkillSpector: warn 160 tokens original MIT

instancez

212

instancez/instancez

Skill Claude CodeCodex

Use when building, changing, or deploying an instancez backend - editing instancez.yaml (tables, RLS, auth, storage, rpc, functions), running the inz CLI, or debugging why a query is denied. instancez is a single-binary Supabase-compatible backend defined by one YAML file.

not rated 47 yesterday C 64 tokens original Apache-2.0

csv-analyzer

213

everruns/everruns

Skill Claude Code

Analyze CSV files to generate summary statistics, detect data quality issues, and produce formatted reports.

not rated 47 yesterday A SkillSpector: pass 22 tokens original MIT

write-mini-app-code

214

hunmer/agent-spaces

Skill Claude CodeCodex

Write, edit, or review Agent Spaces Workflow UI project code from a user-provided project path while looking up Workflow UI renderer, host component, and plugin source from the current working directory instead of MCP/runtime agent tools. Use when an external agent needs to work on Workflow UI React or HTML preview…

not rated 47 3d ago A 102 tokens

gdb

215

betab0t/skills

Skill Claude CodeCodex

Debug and trace C/C++/Rust programs with the GNU Debugger (GDB) without blocking the agent. Use when you need to set tracepoints, inspect variables, or monitor a running process while staying responsive to the user.

not rated 47 +1 3mo ago B 50 tokens original MIT

latent-potential

216

petekp/claude-code-setup

Skill Claude CodeCodex

First-principles, team-of-experts assessment of a software project that surfaces latent potential; underexploited assets, a sharper north star, missing high-leverage capabilities, better framing and messaging. Produces a prioritized, evidence-grounded report with cheap probes, a reframe candidate, a stop-doing list…

not rated 47 +2 changed 3d ago A SkillSpector: pass 191 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: