ai-agents skills

52,405 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

prove-it

1849

Pablo-aps/prove-it

Skill Codex

Adversarially verify claims that code, fixes, tests, CI, deployments, logs, or systems are correct, complete, healthy, or safe to merge. Use when asked to prove, verify, validate, confirm, double-check, review the agent's own work, check whether a bug is actually fixed, or decide whether green signals justify a…

not rated 9 +2 28d ago A SkillSpector: pass 120 tokens original Apache-2.0

Shoko-official/Claude-Science-System-Prompts

Skill Claude CodeCodex

Conduct rigorous, reproducible multi-step scientific work with literature, databases, local files, Python, R, shell, artifacts, reviewers, and approved compute. Use for evidence synthesis, data or statistical analysis, machine learning, simulation, study design, scientific figures or manuscripts, reproduction audits…

not rated 9 +1 1mo ago A 99 tokens original Apache-2.0

install

1851

hehee9/codex-compressor

Skill Codex

Installation instructions for codex-compressor, a tool that manages Codex settings and hooks. They describe standalone setup and plugin-hook setup on macOS, Linux, and Windows.

not rated 9 21d ago A 14 tokens original Apache-2.0

agents

1852

itaywol/adeptability

Skill Claude CodeCodex needs its repo

Guidance for AI coding agents working on the adeptability (adept) codebase. Humans: see README.md for usage and CONTRIBUTING.md for the contributor workflow.

not rated 9 1mo ago A 5 tokens original MIT

conclave

1853

tommasinigiovanni/conclave

Skill Claude CodeCodex

Conclave — Multi-LLM Council with anonymized debate. Orchestrates multiple AI models (Claude, Gemini, GPT, Grok, Llama, etc.) in a Karpathy-style council with 3 depth levels: quick (parallel answers), standard (parallel + synthesis), deep (parallel + anonymized cross-critique with ranking + debate synthesis). Inspired…

not rated 9 5mo ago A 171 tokens original Apache-2.0

mcp-memory-query

1854

internetyev/cross-agent-memory-kit

Skill Claude Code

Query the mcp-memory-service to retrieve stored facts, decisions, notes, and session learnings. Use this skill whenever the user asks what you remember, wants to recall past decisions or conventions, asks "do you know anything about X", references "last time we discussed", says "check your memory", "look in memory"…

not rated 9 2mo ago A 121 tokens original MIT

argus

1855

realsee-developer/skills

Skill Claude CodeCodex

Use this skill to process one to 99 local exact 2:1 equirectangular panorama images with Realsee Argus, producing depth maps, a merged GLB point cloud, camera poses, optional intrinsics, and a validated local output index. Trigger for Argus panorama reconstruction, Argus ZIP input, or explicit Argus…

not rated 9 6d ago C 105 tokens

caching-strategies

1856

vanara-agents/skills

Skill Claude CodeCodex

Deep reference for caching — what to cache, cache-aside vs read/write-through/write-behind, TTLs with jitter, eviction (LRU/LFU/FIFO), invalidation, and surviving stampedes (thundering herd / dogpile). Worked examples and a runnable jitter check.

not rated 9 28d ago A 64 tokens original Apache-2.0

tdm-daos-agent

1857

ToDealMarket/tdm-daos-agent

Skill Codex

Handle the current public TDM DaOS payment contract and recovery guidance. Use when a TDM service returns HTTP 402 from POST /authorize, when the user needs help with Session Gas Tank behavior, or when the user should be guided toward tdm connect, tdm fuel, tdm sweep, or tdm cashout.

not rated 9 2mo ago A 72 tokens original MIT

brain-plan

1859

SanderMoon/local-brain

Skill Claude CodeCodex

Plan a project by breaking goals into concrete tasks with priorities and deadlines. Use when the user says "let's plan", "break this down", "I need to figure out how to", "help me plan", or when starting a new project.

not rated 9 5mo ago A 53 tokens original MIT

agentic-payments

1861

inflowpayai/inflow-cli

Skill Claude Code

Authenticate with InFlow and pay HTTP 402-protected resources via MPP (the Payment auth scheme) or x402. Use when the user invokes the inflow CLI or asks to log in / connect to InFlow.

not rated 9 changed 8d ago C 54 tokens original MIT

use-sapiom

1863

sapiom/skills

Skill Claude CodeCodex

Access 97 cloud-service tools via Sapiom MCP server — scrape websites, run code in sandboxes, store data (Redis/Vector/Postgres), search the web, call LLMs, generate images and audio, send messages, and manage agent governance. Use when user says "use sapiom", "scrape this page", "search the web", "run this code in…

not rated 9 11d ago A SkillSpector: warn 140 tokens original MIT

seshat

1864

KSDaemon/seshat

Skill Claude CodeCodex

Use Seshat MCP tools BEFORE writing or modifying any code. Triggers on: implementing features, fixing bugs, refactoring, modifying functions, creating files, editing files, choosing patterns, adding dependencies, building components, making any change to the codebase.

not rated 9 2mo ago A 56 tokens original MIT

skill-router

1866

AnamKwon/agent-skill-router

Skill Claude CodeCodex

Use when organizing a large local skill library into category router skills, refreshing a compact skill inventory, or deciding which leaf skill bodies need to be read before agent classification.

not rated 9 2mo ago A 36 tokens

image-read-cache

1867

ParthJadhav/image-read-cache

Skill Claude Code

Optimizes image reading by caching LLM-generated content as XMP metadata inside image files. Use BEFORE reading any image file (.png, .jpg, .jpeg, .webp, .gif, .bmp). Reduces token usage by 90% on repeated image reads. Triggers on: image, screenshot, picture, photo, .png, .jpg, .jpeg, read image, view image, look at…

not rated 9 5mo ago A 91 tokens original MIT

security-kb

1868

dinosn/security-knowledge-base

Skill Codex

Read, search, and inspect evidence in a Security Knowledge Base v1 repository, then validate or stage evidence-cited, revision-bound claim and finding proposals. Use when a task refers to a repository containing kb.json and the kb CLI, asks to check or update the security KB, or supplies an skb.context-packet/v1. Stop…

not rated 9 1mo ago A 92 tokens original MIT

imbalanced-data

1869

param087/agent-ml-skills

Skill Claude CodeCodex

Use when the target is rare (fraud, churn, disease, anomalies). Covers correct metrics, resampling (SMOTE/undersampling), class weights, threshold tuning, and avoiding the accuracy trap and resampling leakage.

not rated 9 3mo ago A 49 tokens original MIT

livewire-reference

1870

olgunozoktas/livewire-alpine-skills

Skill Claude CodeCodex

Use for all Laravel Livewire work. Covers Livewire v4 components, page routes, wire directives, PHP attributes, forms, validation, uploads, pagination, tables, modals, events, islands, performance, JavaScript, Alpine integration, Volt, Pest tests, upgrades, and debugging. Use it before you create, change, review…

not rated 9 18d ago A 225 tokens

symphony

1872

broomva/symphony

Skill Claude CodeCodex

Expert guidance for Symphony — the Rust orchestration engine for coding agents. Use when users ask about installing Symphony (cargo install, curl|bash, docker), initializing projects (symphony init), configuring WORKFLOW.md for Linear or GitHub trackers, running in daemon or one-shot mode, setting up the control…

not rated 9 2mo ago C 147 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: