agent-skills skills

41,087 tagged agent-skills, measured the same way as everything else here.

Browse within: agentic-ai 457coding-agents 215agents 194ai-skills 188azure 167foundry 167sdk 167agent-plugins 163ai-coding-agent 159claude-plugin 154anthropic-claude 137claude-ai 137geo 129agent-framework 124

design-agent-loop

1297

emaraschio/cursor-commands

Skill Claude CodeCursor

Design a reusable agent loop as a graph before running it. Take a TASK and COMPLETION CRITERIA, draw the node graph (input, plan, act, verify, retry or escalate, done), specify context, tools, expected output, and evidence per node, label every transition trigger, set max retries, budget ceilings, and human approval…

not rated 9 today A 157 tokens original MIT

claude-api

1298

adryanmoldokkr32-pixel/anthropics-skills

Skill Claude CodeCodex

Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks to use the Claude API, Anthropic SDKs, or Managed Agents (/v1/agents, /v1/sessions, /v1/environments). DO NOT TRIGGER when: code…

not rated 10 4mo ago A 0 tokens

sapiom-agent-builder

1299

sapiom/skills

Skill Claude CodeCodex

Build and deploy autonomous agents — scripts that run on a schedule, call LLMs, scrape the web, store data, and act without user intervention. Use when user says "build me an agent", "create a bot", "automate X on a schedule", "monitor this page", "summarize X every day", "alert me when Y changes", or wants to deploy…

not rated 9 10d ago A SkillSpector: pass 114 tokens original MIT

youtube-advisor

1300

AlexanderAbramovPav/youtube-advisor

Skill Claude CodeCodex

A skill that builds an advisor from a YouTube channel, so an agent can answer questions using that creator's videos.

not rated 9 1mo ago D 85 tokens original MIT

b3sty-skill

1302

b3sty191/b3sty-skill

Skill Claude CodeCodex

Use this skill when working on b3sty RedM/FiveM resources or related Lua code. The defaults below are the high-frequency rules applied on every task; open the reference files only when the task touches that area.

not rated 9 2mo ago A 274 tokens

mythkiven/figma-ios-codegen

Skill Cursor

Maps Figma node hierarchy (FRAME/GROUP/INSTANCE) to UIKit UIView containers, preserving parent-child relationships, addSubview order, and coordinate system. Decides which nodes become UIView containers vs leaf views, and how to read relative/absolute coordinates from the data package. Use when generating UIKit code…

not rated 9 2mo ago A 103 tokens original MIT

firmware-scaffold

1304

Jinchen-Yang/diansai-skill

Skill Claude Code needs its repo

A tool for generating the starting structure of control firmware for MSPM0 or STM32 hardware, with optional K230 vision communication. Firmware is the software that runs directly on a device or microcontroller.

not rated 9 1mo ago A 120 tokens original MIT

travel-planner

1305

SquirrelSong5/travel-planner-skill

Skill Claude CodeCodex

A thinking framework that breaks work into five stages: define the problem, explore options, formulate a solution, act, and assess the result. It can be applied fully, partially, or minimally depending on the task.

not rated 9 20d ago A 122 tokens original MIT

ux-ui-design-system

1306

nyldn/claude-dolphin

Skill Claude CodeCodex

Use this skill when the user mentions ANY of: "design", "redesign", "UI", "UX", "styling", "component", "accessibility", "a11y", "WCAG", "contrast", "spacing", "typography", "color", "layout", "responsive", "touch target", "focus", "keyboard", "screen reader", "design system", "shadcn", "refactor UI", "audit", "review…

not rated 9 21d ago A 342 tokens original MIT

code-execution

1307

ggozad/haiku.skills

Skill Claude CodeCodex

Writes and runs Python code in a sandbox. Describe the task in plain English — the skill will write and execute the program.

not rated 9 2mo ago A 29 tokens original MIT

orchestrate

1308

wcgomes/agents-workspace

Skill Claude CodeCodex

Use only in coordinator sessions to orchestrate planning or execution of work, including execute, continue, or resume-plan requests. Covers role definition, specialist discovery, dispatch, review, learning, and synthesis. Never use in Session type: DELEGATED executor sessions; those agents perform their handed scope…

not rated 9 18d ago A 67 tokens

deepvista

1309

DeepVista-AI/deepvista-cli

Skill Claude CodeCodex

DeepVista CLI — knowledge base, notes, chat, and skills from the terminal. One skill for the full deepvista CLI. Load when the user wants to: take a note, jot this down, save a fact, list / edit notes; create, search, pin, archive, edit, or grep knowledge-base cards (person, topic, file, note, todo…) via deepvista…

not rated 9 1mo ago A 204 tokens original Apache-2.0

skill-router

1310

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

1311

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

review-all

1312

paultyng/skill-issue

Skill Claude CodeCodex

Use when the user asks for a deep review, full review, comprehensive review, production readiness assessment, full audit, multi-domain audit, "security and reliability and code review", or "review everything". Also use when the user explicitly requests performance review alongside the comprehensive request (e.g.…

not rated 9 1mo ago A 102 tokens original MIT

risingwave

1313

risingwavelabs/agent-skills

Skill Claude CodeCodex

Use when working with RisingWave — streaming SQL database, materialized views, sources, sinks, CDC from PostgreSQL/MySQL, Kafka ingestion, time windows (TUMBLE/HOP/SESSION), watermarks, EMIT ON WINDOW CLOSE, port 4566, risingwave-mcp, event streaming pipeline design, real-time analytics, stream processing.

not rated 9 5mo ago A 74 tokens

troubleshooting

1314

acquia/acquia-skills

Skill Claude CodeCodex needs its repo

Use when acli commands fail, return unexpected errors, authentication breaks, or the CLI behaves unexpectedly.

not rated 9 changed 10d ago A ✓ AI review 24 tokens original MIT

designbrief

1315

Heiberg-Industries/designbrief

Skill Claude CodeCodex

A library of UI design direction files that provide style guardrails for building tasteful, consistent interfaces. Use when building any UI — select a style or let the AI recommend one based on the project context.

not rated 9 6mo ago A 43 tokens original MIT

imbalanced-data

1316

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

3080-brief

1317

BobbyYue/3080-brief

Skill Codex

Create a new source-grounded decision brief in the source format by default (Feishu/Lark, Word/docx, Markdown, or self-contained HTML) with a reader-fit Pyramid opening, one editable or auditable visual covering at least 80% of value-weighted non-appendix claims, and one key-question table. Use when the user names…

not rated 9 changed 6d ago A SkillSpector: pass 190 tokens original MIT

bmad-retrospective

1318

mouadja02/skills

Skill Claude CodeCodex

Post-epic review to extract lessons and assess success. Use when the user says "run a retrospective" or "lets retro the epic [epic]".

not rated 9 today A 38 tokens

gh-fetch

1319

retlehs/gh-fetch

Skill Claude CodeCodex

Use the GitHub CLI to fetch content from GitHub URLs instead of web fetching. Activate when the user shares a GitHub issue, PR, repo, or discussion link.

not rated 9 5mo ago A 38 tokens

ai901-lab-creator

1320

timothywarner-org/ai901-cert-buddy-claude

Skill Claude Code

Create short AI-901 practice labs (15-25 minutes) that are executable and self-validating. Every lab includes prerequisites, exact tasks, validation steps, expected outputs, and cleanup. Scope covers Microsoft Foundry portal builds, Foundry Python SDK client apps with keyless authentication, Azure AI Services via…

not rated 9 2mo ago A 97 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: