ai-agents skills

52,407 tagged ai-agents, measured the same way as everything else here.

Browse within: LLM 360agentic-ai 302agent 225antigravity 218chatgpt 207agentic-skills 192ai-workflows 185coding-agents 164cli 146ai-assistant 133agents 105claude-code-skills 101agent-infrastructure 100claude-cli 100

dsh-community-plugins

2233

HubaKing/dsh-community-plugins

Skill Claude CodeCodex

A guide to finding, checking, installing, updating, and removing community extensions for DeepSeek Harness (dsh), an AI coding-agent framework. It covers plugins distributed through GitHub topics, npm packages, directories, bundles, tarballs, and a graphical interface.

not rated 6 changed 4d ago A 202 tokens original MIT

helm

2234

Jacknelson6/helm

Skill Claude CodeCodex

Advisor-orchestrated in-session build loop. The session model (the strongest model you have, or a new SOTA model you want to evaluate) acts as planner + advisor + reviewer; implementation is delegated to cheaper subagent models. Derives a verifiable completion condition up front and interviews the user if one can't be…

not rated 6 changed 11d ago A 192 tokens original MIT

template-skill

2235

usetemi/skills

Skill Claude CodeCodex

Replace with a clear description of what this skill does and when Claude should use it. Be specific about trigger words and use cases.

not rated 6 2mo ago A 30 tokens original MIT

knowledge-transfer

2236

ferdinandobons/knowledge-transfer

Skill Codex

Use when a colleague is leaving a project and must hand over knowledge, or when someone new joins a project and receives handover.zip or a handover/ folder. Two phases: export (analyze project + agent project memories from Claude, Codex, or another assistant, then produce a transferable handover.zip archive containing…

not rated 6 26d ago A 174 tokens original MIT

prompt-improver

2237

owenob1/prompt-improver

Skill Claude Code

Transform vague prompts into precise, verifiable structured XML prompts that coding agents execute reliably. Modes: execute (default — generate then run) and plan (generate XML for review first). Use when the user says improve prompt, make this work better, prompt engineer, structure a request, plan a complex change…

not rated 6 1mo ago A 104 tokens original MIT

agent-builder

2238

truongpx396/learn-harness-engineering-by-building-mini-claude-code

Skill Claude CodeCodex

Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about Claude Code…

not rated 6 4mo ago A 125 tokens copy · 100% MIT

ai-project-starter

2239

ucsahinn/ai-project-starter

Skill Codex

Use when the user wants to prepare project-specific context engineering documents, AI coding agent instruction files, project starter Markdown files, vibe coding guardrails, PRD/TDD/architecture/security/testing docs, AGENTS.md/CLAUDE.md/Cursor/Windsurf/Continue/Copilot context files, or a complete AI-coding-ready…

not rated 6 1mo ago A 117 tokens original MIT

data-migration-safety

2240

Xipher-Labs/walter-os

Skill Claude CodeCodex

Review database migrations and schema changes for safety — reversibility, lock duration, online-vs-offline behavior, batch-size on backfills, tenant isolation, RLS policies (Supabase), idempotence, audit-log impact. Use this skill on any PR that touches migrations/, supabase/migrations/, .sql, schema files…

not rated 6 4d ago A 140 tokens AGPL-3.0

configflux/weld

Skill Claude CodeCodex

Use this skill when modifying AI agents, skills, prompts, commands, hooks, instructions, MCP configuration, or platform-specific AI customization files.

not rated 6 12d ago A 33 tokens original Apache-2.0

audit-repo

2242

nerviq/nerviq

Skill Claude CodeCodex

Run nerviq on the current repo and summarize the score, top gaps, and next command.

not rated 6 1mo ago A 22 tokens original MIT

agent-builder

2243

lhhiep2204/apple-agent-builder-kit

Skill Claude CodeCodex

Use when: creating, refactoring, auditing, upgrading, or debugging Copilot custom agents, skills, instructions, prompts, or hooks for Apple platform software engineering and agile delivery workflows.

not rated 6 4mo ago A 40 tokens original MIT

sally-skills

2244

a1c-ai-agent/sally-skills

Skill Claude CodeCodex

The full doc is 430 lines, but you only need to paste this section (70 lines) into an agent's system prompt for 95% of requests to route correctly. Everything below it is edge-case reference for the routing layer's authors.

not rated 6 28d ago A 0 tokens

ragmir

2245

jcode-works/jcode-ragmir

Skill Claude CodeCodex

Use Ragmir for local-first retrieval from private project documents, document ingestion, knowledge-base audits, or MCP access to a repository corpus. Prefer it to memory when the answer may be in local documents.

not rated 6 4d ago A 43 tokens AGPL-3.0

picident

2246

HaoyueQin/picture-identification-MCP

Skill Claude CodeCodex

A tool that gives text-only AI agents the ability to understand images, screenshots, charts, and PDFs through vision models.

not rated 6 1mo ago A 100 tokens original MIT

agent-web-search

2247

JerryLiu369/agent-web-search

Skill Claude CodeCodex

Search the live web through the agent-web-search CLI — powered by model-native search grounding and agent search backends. Optimized for complete natural-language questions rather than keyword fragments when online sources or cross-provider web research are needed.

not rated 6 changed 6d ago A SkillSpector: pass 49 tokens original MIT

codemap

2248

Asixa/codemap-skill

Skill Claude CodeCodex

Generate and incrementally maintain an interactive architecture map plus a per-module code-quality audit (health scores 0-100, smell findings, lines-of-code, and a clickable dependency graph) for any codebase. Use when the user wants to visualize a project's functional modules, audit or score code quality, check…

not rated 6 +1 3mo ago A 153 tokens original MIT

bipa

2249

bipa-app/bipa-cli

Skill Claude CodeCodex

Use Bipa CLI to make Pix payments, check balances, analyze transaction history, and decode BR codes for AI agents. MUST use this skill whenever the user mentions paying someone via Pix, checking their balance, reviewing transactions, scanning a Pix QR code, setting up Bipa CLI, or asks the agent to handle any…

not rated 6 changed 4d ago C 139 tokens original MIT

specflo-execute

2250

TacoTakumi/specflo

Skill Claude CodeCodex

Use at a specflo project's execute phase, when turning a validated plan.md into committed, verified code one task at a time. Triggers include "execute the plan", "start building", "work the next task", or specflo status showing the execute phase. Do NOT use before a plan has been validated, or for trivial fixes…

not rated 6 changed 10d ago A 78 tokens

plan

2251

iwe-org/dev-workspace

Skill Claude Code

Create an implementation plan — discovery in the real codebase first, then a plan document with verified code anchors, spec impact, and dependencies, filed under Active in the plans hub. Use when the user says "plan ", "write a plan for ...", or asks to turn a backlog task or accepted feature into work.

not rated 6 1mo ago A 68 tokens original MIT

caveman-research

2252

aidvizhhub/caveman-dvizh-skills

Skill Claude CodeCodex

A research workflow that gathers information from multiple sources, including documentation, web searches, and industry code examples.

not rated 6 21d ago A SkillSpector: warn 252 tokens original MIT

archagent-author-agent

2253

ArchAstro/archagents

Skill Claude Code

Use when the user wants to create or edit an ArchAstro agent's config files before deployment, including AgentTemplate files, Script configs, custom tools, routines, and environment setup. Trigger phrases include "build this agent", "write the template", "create the scripts", "set up the routines", "author this agent…

not rated 6 +1 13d ago A 72 tokens original MIT

termpeek

2254

0xNyk/termpeek

Skill Claude CodeCodex

Preview images, video, PDFs, code files, diffs, and tweets from inside an agent CLI that cannot render them. Use when the user asks to see, view, preview, show, or look at a file — screenshots, generated images, charts, mockups, video clips, PDFs, or a code diff — or says "show me", "let me see it", "preview that"…

not rated 6 21d ago A 129 tokens original MIT

weather-fetcher

2255

ashp15205/scankii

Skill Claude CodeCodex

Fetch weather data for any city using the OpenWeather API.

not rated 6 +1 2mo ago A 16 tokens

glyphtrail

2256

glyphtrail/glyphtrail

Skill Claude CodeCodex

Query this repo's code graph instead of ls/grep/reading files blindly. Use whenever you are understanding the codebase or its architecture, tracing how something works, or searching for a symbol or term; before changing a symbol, to get its blast radius (dependent symbols, tests to run, API surface, and other indexed…

not rated 6 8d ago A 151 tokens EUPL-1.2

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: