agents skills

10,566 tagged agents, measured the same way as everything else here.

Browse within: azure 180sdk 178tool-use 175ai-scientists 174reasoning-agent 174reasoning-language-models 174foundry 167agentskills 148cortex 147cortexai 147snowflake 147skills 132agent-framework 127cocoplus 120

oracle

49

steipete/oracle

Skill Claude CodeCodex

Oracle second-model review: bundle prompts/files, debug, refactor, design.

not rated 3.9k +130 yesterday A 18 tokens original MIT

kagent-dev

50

kagent-dev/kagent

Skill Claude CodeCodex

Development guide for kagent's v1alpha3 Harness and AgentTemplate CRDs, AgentInstance gRPC control plane, upstream A2A integration, Substrate runtime provisioning, tests, generation, and PR workflow. Use for any implementation, debugging, review, or CI task in the kagent repository.

not rated 3.7k +40 changed today A 65 tokens original Apache-2.0

pipeline-conductor

51

kirodotdev/KiroCrew

Skill Claude CodeCodex

Operating procedure for the kirocrew-pipeline-conductor agent - run one issue/PR pipeline on one repository as a supervised fleet. Auto-pick items, preflight every candidate to one deterministic claim verdict, stand up one worker session per item in a dedicated folder, probe them each cycle with one script call…

not rated 3.6k +233 changed today A 142 tokens original Apache-2.0

agent-browser

52

superagent-ai/grok-cli

Skill Claude CodeCodex

Use the host-side agent-browser CLI for local browser smoke tests, screenshots, snapshots, and simple UI validation against forwarded localhost URLs.

not rated 3.5k +15 2mo ago A 31 tokens original MIT

release-validation

53

Mesh-LLM/mesh-llm

Skill Claude CodeCodex

Use this skill when validating a MeshLLM release candidate or current HEAD against the last GitHub release, assembling the canonical feature/fix/modification inventory, testing locally built release bundles on user-approved real hosts and private meshes, deciding release readiness, or producing a formal…

not rated 3.4k +27 today A 62 tokens original Apache-2.0

awslabs/agentcore-samples

Skill Claude CodeCodex ✓ vendor

Analyzes cost structure, cost efficiency, and expense management from P&L data. Use when the user asks about costs, expenses, COGS, operating expenses, cost ratios, cost control, spending efficiency, margin compression from cost side, or wants to understand where money is going. Also use for "are we spending too…

not rated 3.3k +15 yesterday A 98 tokens original Apache-2.0

Sumanth077/Hands-On-AI-Engineering

Skill Claude CodeCodex

Fetches articles from 92 Karpathy-curated RSS feeds, scores them with an LLM, selects the top 3, and delivers a formatted digest to Telegram every morning.

not rated 3.1k +162 11d ago A 42 tokens

aiox-data-engineer

56

SynkraAI/aiox-core

Skill Claude CodeCodex

Activate Dara (data-engineer) for Database Architect & Operations Engineer. Use for database design, schema architecture, Supabase configuration, RLS policies, migrations, query optimization, data modeling, operations, and monitoring.

not rated 3.1k +10 yesterday A 48 tokens

no-mistakes

57

mnemosyne-oss/mnemosyne

Skill Claude CodeCodex

Validate your code changes through the no-mistakes pipeline - automated code review, tests, lint, docs, push, PR, and CI - before they reach upstream. Use when the user asks to run no-mistakes, gate or ship or validate their changes, push safely, asks you to do a task and then validate it, or invokes /no-mistakes.

not rated 3.0k +78 yesterday A 81 tokens original MIT

regulatory-analysis

58

open-gitagent/opengap

Skill Claude CodeCodex

Analyzes documents and processes against FINRA, SEC, Federal Reserve, and CFPB regulatory frameworks. Identifies compliance gaps, classifies findings by severity, and recommends remediation. Use when performing compliance audits, regulatory reviews, gap analyses, or verifying policy adherence to financial regulations.

not rated 2.9k +4 2mo ago A 59 tokens original MIT

ax-agent-rlm

59

ax-llm/ax

Skill Claude CodeCodex

This skill helps an LLM generate correct AxAgent RLM/runtime code using @ax-llm/ax. Use when the user asks about RLM code execution, AxJSRuntime, contextFields, contextPolicy, liveRuntimeState, promptLevel, stage prompt controls, executorModelPolicy, maxRuntimeChars, agent.test(...), llmQuery(...), recursionOptions…

not rated 2.9k +3 4d ago A 88 tokens original Apache-2.0

mobile-use-setup

60

minitap-ai/mobile-use

Skill Claude CodeCodex

Set up a local-first Minitap mobile-use SDK project for iOS or Android, including local devices, BrowserStack, Minitap cloud devices, and supported LLM providers.

not rated 2.8k +13 7d ago A 42 tokens original Apache-2.0

claude

61

bergside/awesome-design-skills

Skill Claude CodeCodex

A research-journal aesthetic printed on warm stone — authoritative, editorial, almost achromatic. Pages live on warm ivory parchment (never pure white), with near-black slate as the dominant ink.

not rated 2.7k +86 2mo ago A 41 tokens original MIT

docker

63

AtomicBot-ai/atomic-agent

Skill Claude CodeCodex

Manage Docker containers, images, volumes, and Compose stacks via the docker CLI — list, inspect, logs, run, build, stop, remove, compose up/down. Use for local container ops.

not rated 2.5k +66 today A 44 tokens original MIT

observal

64

Observal/Observal

Skill Claude CodeCodex

Operates the Observal CLI for authentication, configuration, setup diagnosis, teamspaces, inbox work, scans, update checks, and authenticated API access. Use when the user wants to log in, configure Observal, inspect local harness setup, manage a teamspace or invitation, process inbox items, check installed registry…

not rated 2.4k +13 yesterday A 79 tokens original Apache-2.0

design

66

Infisical/agent-vault

Skill Claude CodeCodex

Elegant design-system skill — foundations (typography, color, spacing), component families, accessibility (WCAG 2.2 AA), and a structured workflow for authoring implementation-ready UI guidance. Use when designing or specifying Elegant UI, tokens, components, or design-system rules and QA checklists.

not rated 2.2k +19 yesterday A 62 tokens

guizang-ppt-skill

67

proma-ai/Proma

Skill Claude CodeCodex

A skill for creating presentation decks as single HTML files that users can move through horizontally in a browser. It provides templates with WebGL backgrounds, chapter title screens, large data displays, and image grids, in either an editorial or Swiss-style visual direction.

not rated 2.1k +20 today A 161 tokens AGPL-3.0

mistake-reflection

68

a2aproject/a2a-python

Skill Claude CodeCodex

Use when you discover you made a mistake — caught by the user, by a tool result, by your own re-reading, or by a failed check. Appends a structured entry to docs/ai/ailearnings.md and re-reads recent entries to avoid repeats.

not rated 2.1k +9 2d ago A 60 tokens original Apache-2.0

frankfurter

69

a2aproject/a2a-samples

Skill Claude CodeCodex

Fetch currency exchange rates from the frankfurter.dev API.

not rated 1.8k +7 2d ago A 14 tokens original Apache-2.0

normal-skill

70

google/adk-java

Skill Claude CodeCodex ✓ vendor

A normal skill with a hyphen.

not rated 1.7k +5 today A 11 tokens original Apache-2.0

devtu-docs-quality

71

mims-harvard/ToolUniverse

Skill Claude CodeCodex

TOP PRIORITY skill — find and immediately fix or remove every piece of wrong, outdated, or redundant information in ToolUniverse docs. Wrong code, broken links, incorrect counts, and overlapping instructions must be fixed or removed — never left in place. Runs five phases: (D) static method scan, (C) live code…

not rated 1.7k +12 today A 140 tokens original Apache-2.0

newsletter

72

masamasa59/ai-agent-papers

Skill Claude CodeCodex

Write a monthly trend newsletter for this ai-agent-papers repo. Use when asked to create/update a monthly trend report, summarize a category's recent papers, or "make a newsletter". Encodes the house procedure: cover every coherent category with enough papers that month (no fixed number of issues; overlap between…

not rated 1.6k +5 6d ago A 120 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: