Skills

Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.

claude-brain

10489

Brainwires/rullama-framework

Skill Claude Code

Check Claude Brain status — shows whether hooks, MCP server, and memory are working.

not rated 20 6d ago A 21 tokens original Apache-2.0

gaia-full-pipeline

10490

gaia-research/gaia-skill-tree

Skill Claude CodeCodex

End-to-end Gaia curation pipeline orchestrator. Routes each phase to its dedicated skill and keeps you on track from first discovery to closed intake. Use when starting a fresh curation run or when you want a single skill to hold the sequence together without duplicating each phase's instructions. Trigger phrases…

not rated 20 +1 changed 9d ago A 171 tokens

create-ppt

10491

aws-samples/sample-ai-assistant-on-agentcore

Skill Claude CodeCodex ✓ vendor

Creates polished PowerPoint presentations with dark-first design, custom palettes, charts, and tables. Use when creating, designing, or generating PPTX slide decks or presentations.

not rated 20 +1 1mo ago A 37 tokens MIT-0

syncause-debugger

10492

Syncause/debug-skill

Skill Claude CodeCodex

Diagnose and fix bugs using runtime execution traces. Use when debugging errors, analyzing failures, or finding root causes in Python, Node.js, or Java applications.

not rated 20 5mo ago A 37 tokens

debugging

10493

thixpin/pitway

Skill Claude CodeCodex

Investigate failures whose root cause is still unknown — narrow the search space, instrument, and test falsifiable hypotheses. Use for intermittent or environment-dependent behavior, unexplained stack traces, regressions with no known trigger, or any symptom without a confirmed cause. Ends once the root cause is…

not rated 20 +1 5d ago A 86 tokens original MIT

deepspider

10494

ma-pony/deepspider

Skill Claude CodeCodex

Use when tracing browser requests, recovering JavaScript-generated request outputs, diagnosing anti-bot runtime gaps, or delivering independently verified scraping modules.

not rated 20 +1 changed 2d ago A 32 tokens

scaffold-skill

10495

a-tokyo/aiworkspace

Skill Claude CodeCodex

Scaffold new AI agent skills with proper symlinking across all IDE tools (Cursor, Claude Code, Codex, etc.). Use when creating a new skill, adding a local skill, or when the user wants to write a custom skill -- either workspace-wide or for a specific project.

not rated 20 +1 1mo ago A SkillSpector: warn 63 tokens original Apache-2.0

mysql-tools

10496

huangzt/my-agent-skills

Skill Claude CodeCodex

A set of command-line tools for connecting to MySQL databases, inspecting tables, and running SQL. MySQL is a database system, and SQL is the language used to read and change database data.

not rated 20 9mo ago A 86 tokens original MIT

project-init

10497

linshidream/skill-hub

Skill Claude CodeCodex

Initialize a project scaffold into an empty directory (or add a new child module to an existing Java project). Two engineering families: Java (java-web / java-mcp → maven + Docker image) and frontend (web-pc = vite+React+antd PC web / taro-mobile = Taro3.6+NutUI3.0 multi-end H5+WeChat miniprogram → pnpm exact-version…

not rated 20 changed 6d ago A SkillSpector: pass 0 tokens original MIT

foundry-vtt-module-dev

10498

fcsouza/agent-skills

Skill Claude CodeCodex

Covers building, extending, debugging, and maintaining Foundry VTT modules for v14+. This skill applies when scaffolding a new module, writing custom Actor/Item types with TypeDataModel, building ApplicationV2 sheets, dialogs, or detached windows, registering hooks or settings, implementing socket communication…

not rated 20 changed 12d ago A 216 tokens GPL-3.0

ms-access-vcs

10499

paramountsoftware/ms-access-ai-skill

Skill Claude Code

Working with Microsoft Access databases exported via VCS (Version Control System for Access). Use when editing Access form definitions (.bas), report definitions, query files, VBA modules, linked table definitions, or VCS configuration files. Covers structural rules, common gotchas, and safe editing practices for the…

not rated 20 1mo ago A SkillSpector: pass 78 tokens original MIT

stock-analysis

10500

shaohk/TradingAgents-CN-SKILL

Skill Claude Code

A multi-agent framework for analysing stocks, meaning publicly traded company shares. It can run a full analysis with 16 cooperating analysts or run selected analysts separately.

not rated 20 2mo ago A 39 tokens

gromacs-protein-analysis

10501

CharlesHahn/DuIvySkills

Skill Claude CodeCodex

A workflow guide for analysing protein molecular-dynamics simulations, which model how atoms move over time. It describes procedures for correcting periodic-boundary artefacts, measuring motion and flexibility, and studying structural changes and interactions.

not rated 20 27d ago A 284 tokens GPL-3.0

effect-best-practices

10502

betalyra/effect-skills

Skill Claude CodeCodex

Enforces Effect-TS patterns for services, errors, layers, and atoms. Use when writing code with Effect.Service, Schema.TaggedError, Layer composition, or effect-atom React components.

not rated 20 1mo ago A 45 tokens original MIT

conductor-setup

10503

vasilistsavalias/conductor_for_codex

Skill Claude Code needs its repo

Scaffolds the project and sets up the Conductor environment interactively.

not rated 20 1mo ago A SkillSpector: pass 19 tokens original Apache-2.0

sapiom-agent-authoring

10504

sapiom/sapiom-js

Skill Claude CodeCodex

Build, test, and deploy a Sapiom agent — a controlled, multi-step, deployable automation defined in TypeScript. Use when the user wants to automate a multi-step, scheduled, recurring, or deployable task ("build an agent that checks competitor prices every morning", "automate our weekly report", "make a bot that…

not rated 20 changed 10d ago A SkillSpector: warn 157 tokens original MIT

clarity-session-review

10505

BayramAnnakov/clarity-session-review

Skill Claude CodeCodex

Review Microsoft Clarity session recordings the way that produces findings, not anecdotes: question-scoped triage → attribution → replay-watch → database/source triangulation → a verifiable evidence appendix. Use for funnel investigations ("why did users drop off / churn / not click X"), post-ship verification ("watch…

not rated 20 2mo ago A 165 tokens original MIT

pr-overview

10506

ArjenSchwarz/agentic-coding

Skill Claude CodeCodex

Pull a PR from GitHub, run parallel review agents (code reuse, quality, efficiency, spec adherence) in read-only mode, surface unresolved comments, and write a self-contained HTML overview page to the repo root. Use whenever the user wants a read-only summary of a PR before deciding what to do — phrases like "overview…

not rated 20 changed 16d ago A 111 tokens

create-widget

10508

sampaio-tech/iOS-design-system

Skill Claude Code needs its repo

Guide to creating new widgets following iOS Design System patterns and conventions.

not rated 20 +1 2mo ago A 16 tokens original MIT

eval

10509

ai-analyst-lab/ai-analyst-plus

Skill Claude Code

Run the held-out gold suite live against the analyst and score it. Use when the user types "/eval", or asks to "run the eval suite", "score the system", "run the train split", "check the test split", "what's our accuracy on the gold cases", or wants the system-level eval number (accuracy + query-similarity + cost).…

not rated 20 2mo ago A 134 tokens original MIT

build-flowise

10510

context-foundry/context-foundry

Skill Claude Code

Build or update a Flowise AgentFlow v2 JSON file with selective retrieval, validation, and audit. Use when asked to create or modify audited Flowise flows.

not rated 20 3mo ago A 37 tokens original MIT

document-to-mindmap

10511

processonai/processon-skills

Skill Claude CodeCodex

A tool for turning long or scattered material into an editable mind map, a visual outline that shows topics and their relationships. It can work with text, Markdown, documents, web content, images, books, and meeting notes through ProcessOn.

not rated 20 today A 336 tokens

galaxy-tool-wrapping

10512

Delphine-L/claude_global

Skill Claude CodeCodex

Expert in Galaxy tool wrapper development, XML schemas, Planemo testing, and best practices for creating Galaxy tools.

not rated 20 4mo ago A 28 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: