ai-agents skills

52,396 tagged ai-agents, measured the same way as everything else here.

Browse within: LLM 338agentic-ai 283agent 210antigravity 210chatgpt 199agentic-skills 192ai-workflows 185agents 165coding-agents 153cli 144ai-assistant 126openclaw 95claude-code-skills 91agent-infrastructure 90

slide-design

937

HarnessRouter/starter-kit

Skill Claude CodeCodex

How to plan and design presentation decks — content architecture first, then a deliberate style system, then slide-by-slide craft. Use for EVERY deck request, before touching any slide tool.

not rated 47 +6 15d ago A 39 tokens

MrPunyapal/laravel-auditor

Skill Claude CodeCodex

Audit a Laravel application's performance deeply and safely: unnecessary queries, N+1, collection vs database work, memory amplification, repeated computation, I/O, queues, and rendering cost — verifying that every proposed optimization preserves behavior before reporting it. Use when auditing performance or…

not rated 47 +2 7d ago A SkillSpector: pass 63 tokens original MIT

star-your-harness

939

SpaceZephyr/build-your-harness

Skill Claude CodeCodex needs its repo

A guided setup for creating an AI work folder, sometimes called an AI harness, with organized instructions, background information, memory, tools, and review practices.

not rated 47 +19 28d ago A SkillSpector: pass 190 tokens original MIT

github-scan

940

first-tree-ai/first-tree-legacy

Skill Codex

Operate the first-tree github scan CLI — the GitHub notification daemon and inbox runtime. Use whenever you need to run, start, stop, inspect, poll, or debug github-scan; view or respond to GitHub-triggered work from the terminal; or wire up the github-scan statusline hook.

not rated 46 +1 3mo ago A 68 tokens original Apache-2.0

aistack-sync

941

alp82/aistack

Skill Claude CodeCodex

Publish measured Claude Code usage (rolling 30 days) to the user's aistack stack. Use when the user says "sync my stack", "aistack sync", "publish my usage", or asks to update the measured layer of their stack.

not rated 46 yesterday A SkillSpector: warn 56 tokens original MIT

mandu-mcp-index

942

konamgil/mandu

Skill Claude CodeCodex

A routing guide for choosing among Mandu's many coding-agent tools and workflow instructions. Mandu is a project system with tools for creating features, checking edits, debugging, refactoring, and deploying.

not rated 46 17d ago A SkillSpector: pass 69 tokens original MPL-2.0

fleet-parallel

943

drvoss/everything-copilot-cli

Skill Claude CodeCodex

Use when you need to run the same task across many files, components, or contexts in parallel — triggers /fleet mode for batch refactoring, mass testing, or bulk review. NOT when sequential order matters.

not rated 46 +1 17d ago A SkillSpector: warn 46 tokens original MIT

aura-integration

944

Naridon-Inc/aura

Skill Claude CodeCodex

Automatically captures Gemini CLI intent and writes it to .gemini.intent whenever code changes are made. Use this skill when making any modifications to the codebase so that the local Aura Semantic Version Control system can track the AI's reasoning.

not rated 46 today A SkillSpector: pass 51 tokens original Apache-2.0

tapd

945

joosure/Maestro

Skill Claude CodeCodex

Use Symphony's generated typed TAPD tools for tracker workflow actions. Provides TAPD capability semantics and workpad rules.

not rated 46 2mo ago A 26 tokens AGPL-3.0

migration-reviewer

946

oracle-samples/oracle-aidp-samples

Skill Claude CodeCodex

Review a migrated .ipynb for correctness — NOT just "did it run". Catches latent issues the cell-execute loop missed — wrong write-mode, lost rows, dropped columns, hardcoded paths, dead Databricks-isms, builtins shadowing, format downgrades. Outputs a structured Blockers / Important / Style / Good review report. Use…

not rated 46 yesterday A 100 tokens UPL-1.0

Cloud Billing Analyst

947

Cletrics/finops-agents

Skill Claude CodeCodex

FOCUS-first analyst for cloud billing data across AWS, Azure, GCP, OCI, and SaaS. Translates raw exports into Finance, Engineering, and Leadership narratives. Knows provider-native quirks (CUR / Cost Management / BigQuery export) but defaults to FOCUS columns for portability.

not rated 46 4mo ago A 64 tokens original MIT

meta-ads

948

boringmarketer/kimi-first

Skill Claude CodeCodex

Build and verify Meta (Facebook/Instagram) ad campaigns end to end via the Marketing API — account/app/system-user permission chain, Special Ad Category constraints, crop-safe story creative, campaign creation, and conversion tracking that is actually proven to work. Use when launching or debugging Meta campaigns…

not rated 46 9d ago A SkillSpector: pass 89 tokens original MIT

skill-forge

949

motiful/skill-forge

Skill Claude CodeCodex

Validate, fix, and publish skills as GitHub repos. Structures workflow skills for execution fidelity. Registers skills across platforms via symlinks and guides first-use onboarding. Use when the user says "create a skill", "forge a skill", "review this skill repo", "audit this skill", "audit all my skills", "audit…

not rated 45 2mo ago A 194 tokens original MIT

code-review

950

gridctl/gridctl

Skill Claude CodeCodex

Structured code review prompt with language and focus area.

not rated 45 today A SkillSpector: pass 12 tokens original Apache-2.0

spawn-agent

951

khanhbkqt/spawn-agent

Skill Codex

Spawn worker agents (Gemini CLI or Codex CLI) to keep main context clean. Use for implementation, codebase research, context gathering, or any scoped work that would pollute the orchestrator's context.

not rated 45 6mo ago A 46 tokens original MIT

neuromemory-ai

952

tonitangpotato/engram-ai

Skill Claude CodeCodex

Neuroscience-grounded memory for AI agents. Add, recall, and manage memories with ACT-R activation, Hebbian learning, and cognitive consolidation.

not rated 45 3mo ago A 35 tokens AGPL-3.0

worker-author

953

floomhq/floom

Skill Claude CodeCodex

You are the Worker Author — a meta-worker that writes Floom worker bundles from natural-language descriptions. You are the first worker every operator gets, and you eat your own dogfood: the quality of the bundles you produce is how the platform proves itself.

not rated 45 11d ago A SkillSpector: warn 0 tokens original MIT

apple-bridges

954

more-io/claude-apple-bridges

Skill Claude CodeCodex

Use this skill whenever the user asks about Apple apps — Reminders, Calendar, Contacts, Notes, Mail, Messages (iMessage/SMS), or tmux sessions. This includes creating/completing reminders, checking/adding calendar events, looking up contacts, reading/writing notes, sending/reading email, reading/sending iMessages and…

not rated 45 +1 changed 7d ago A SkillSpector: pass 133 tokens original MIT

chat-skills

955

Pronting/chat-skills

Skill Claude CodeCodex

A Chinese-language guide for analyzing romantic and social conversations, including message screenshots, intentions, distance, invitations, and date planning.

not rated 45 3mo ago A 136 tokens original MIT

anton-abyzov/vskill

Skill Claude CodeCodex

Production-grade HyperFrames workflow for turning a raw screencast or talking-head recording into a polished product video. Covers the smart-cut pipeline (transcript + silence + scene detection with word-boundary buffers), surgical audio scrubbing (con​cat-filter rendering, adeclick, targeted transient mute), the…

not rated 45 6d ago A ✓ AI review 160 tokens original MIT

enterprise-prd-writer

957

skinnerlee1225/enterprise-prd-toolkit

Skill Claude CodeCodex

A detailed product-requirements-document writer for regulated, financial, risk-management, and cross-functional projects. A PRD is a shared plan that explains what a product must do, who it serves, how it will be accepted, and what happens during release.

not rated 45 +1 1mo ago A SkillSpector: pass 603 tokens original MIT

skills

958

Youhai020616/stealth-cli

Skill Claude CodeCodex needs its repo

Anti-detection browser CLI powered by Camoufox. Browse the web, search, extract data, take screenshots, and crawl pages — all with C++ level fingerprint spoofing that bypasses Cloudflare, Google, and most bot detection systems.

not rated 45 5d ago B 0 tokens original MIT

humanizer-vi

959

longhang2004/vietnamese-humanizer

Skill Claude CodeCodex

Biên tập văn bản tiếng Việt máy móc, sáo rỗng hoặc đều giọng để câu chữ tự nhiên, rõ và đúng ngữ cảnh. Dùng khi người dùng yêu cầu làm văn bản bớt khuôn mẫu, chỉnh giọng hoặc bảo toàn giọng tác giả; không dùng để suy đoán tác giả là AI, lách detector, sửa thuần ngữ pháp hay biến văn bản chuyên môn thành văn nói.

not rated 45 1mo ago A 97 tokens original MIT

metier-rh

960

ai-swiss/base

Skill Claude Code

Droit du travail suisse, bonnes pratiques RH, non-discrimination, conventions salariales. À consulter lors de la création d'offres et la préparation d'entretiens.

not rated 45 +1 9d ago A SkillSpector: pass 39 tokens original Apache-2.0

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: