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.

run-wenlan-app

5977

wenlan-app/wenlan

Skill Claude Code

Build, launch, screenshot, and drive the wenlan-app Tauri desktop app in dev mode on macOS (WKWebView) or Windows (WebView2). Use when asked to run or start the app, verify a UI change in the real running app (not just tests), or take a screenshot of it.

not rated 94 +1 changed 19d ago A 71 tokens original Apache-2.0

handoff

5978

vbiroshak/ai-project-architect

Skill Claude Code

Close this session and prepare the handoff for the next one.

not rated 94 +1 29d ago A 12 tokens original MIT

AIBiz-Automatyzacje/claude-code-starter

Skill Claude Code

Wytyczne UX/UI dla aplikacji mobilnych (Expo + React Native + Uniwind, ale stack-agnostic w pryncypiach). Platform conventions (iOS HIG vs Material 3), typografia natywna (SF Pro/Roboto, Dynamic Type, type scale), 8pt grid + safe areas, semantic colors + dark mode jako redesign, ikony (SF Symbols vs Lucide vs Material…

not rated 94 changed yesterday A 285 tokens

dat-skill

5980

that-company/dat-skill

Skill Codex

Default path for any cloud training work in Dat. Use this skill whenever a task needs cloud training, GPU training, model fine-tuning, training evaluation, long-running training compute, or hosted training job orchestration. Also use it to submit prepared packages, handle approval/session handoff, track jobs, cancel…

not rated 93 3mo ago A 77 tokens

techpack-creator

5981

mcs-cli/mcs

Skill Claude Code

Scan a repository that already has Claude Code configuration (hooks, skills, CLAUDE.md, settings, MCP servers) and package it into a valid MCS techpack.yaml for distribution via mcs. Use this skill whenever the user wants to create a tech pack from an existing repo, convert a Claude Code setup into a shareable MCS…

not rated 93 changed 1mo ago A SkillSpector: warn 190 tokens original MIT

docuspeed/claw-skills

Skill Claude CodeCodex

A research method for collecting, checking, and analysing information across different academic and professional fields.

not rated 93 7mo ago A 38 tokens original MIT

agent-tail

5983

gillkyle/agent-tail

Skill Claude CodeCodex

Capture browser console logs and dev server output to files with agent-tail. Use when debugging runtime errors, checking console output, tailing or diagnosing logs, or setting up Vite/Next.js log capture.

not rated 93 8mo ago A 44 tokens original MIT

bash-secure-scripting

5984

konstruktoid/hardened-images

Skill Claude CodeCodex

Authors, reviews, and hardens Bash scripts for the stability and security properties a linter cannot verify on its own, including strict-mode semantics and the cases errexit ignores, cleanup and locking on every exit path, injection-safe handling of untrusted input and filenames, PATH and environment control…

not rated 93 yesterday A ✓ AI review 158 tokens original Apache-2.0

photo-distill

5985

yangcodingmaster/photo-distill

Skill Claude CodeCodex

A skill that turns a supplied photograph into a minimalist printed poster or zine-style artwork using hand-written HTML, CSS, and SVG, then exports a PNG. It does not use an image-generation model.

not rated 93 +1 3mo ago A 241 tokens

code-review

5986

arpitnath/claude-capsule-kit

Skill Claude Code

Pre-commit code review using code-reviewer agent for bug detection, security analysis, and quality assurance. Manual invocation only. Use before git commits to catch issues early. Blocks commits on REQUESTCHANGES verdict.

not rated 93 5mo ago A 45 tokens original MIT

Weaverse/shopify-hydrogen-skills

Skill Claude CodeCodex

Use when recreating a reference website or brand hub in this Hydrogen plus Weaverse repo, especially when deciding whether to reuse sections, add global styles, update theme schema, or resolve conflicts between the live site and project brand guidelines.

not rated 93 changed 1mo ago A 54 tokens

paper-reader-heilmeier

5988

RealZYZhang/paper-reader-heilmeier

Skill Claude CodeCodex

Read a research paper end to end and produce a single Heilmeier-style analysis that doubles as both summary and critique. Use this skill whenever the user shares a research paper (PDF upload, arXiv link, arXiv ID, DOI, or pasted paper text) and asks anything that resembles "read this", "summarize this paper", "what…

not rated 93 +1 6mo ago A 171 tokens original MIT

mcp-client

5989

walidboulanouar/Ay-Skills

Skill Claude CodeCodex

Universal MCP client for connecting to any MCP server with progressive disclosure. Wraps MCP servers as skills to avoid context window bloat from tool definitions. Use when interacting with external MCP servers (Zapier, Sequential Thinking, GitHub, filesystem, etc.), listing available tools, or executing MCP tool…

not rated 93 1mo ago A 102 tokens original MIT

gnipbao/knowledge-cat-ppt-skill

Skill Codex

Create, critique, and repair high-quality presentation decks with a story-first, output-engine-aware workflow. Use when the user asks for PPT, PowerPoint, slides, deck, pitch deck, keynote, course deck, academic deck, consulting deck, HTML slides, web presentation, image-first slides, social carousel, speaker notes…

not rated 93 +1 4mo ago A 125 tokens original MIT

Kubernetes编排

5991

microwind/ai-skills

Skill Claude CodeCodex

A guide for using Kubernetes, a system that deploys and manages containerized applications across servers.

not rated 93 5mo ago A 47 tokens

GulajavaMinistudio/awesome-copilot-id

Skill Claude Code

Applies the "lazy senior developer" mindset. Use this skill whenever generating, modifying, reviewing code, or fixing bugs to prioritize code reuse, minimalism, YAGNI principles, and root-cause fixes. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni"…

not rated 93 +1 changed 23d ago A SkillSpector: pass 146 tokens original MIT

codedb-mcp

5993

killop/codedb-mcp

Skill Codex

Use the configured codedb MCP server whenever an indexed repository needs lifecycle tracing, implementation discovery, call/dispatch analysis, shared-state producer lookup, branch evidence, architecture explanation, or exact source navigation. Prefer declarative graph queries over repeated wrapper reads or…

not rated 93 3mo ago A 59 tokens

circlechat

5994

tashfeenahmed/circlechat

Skill Claude CodeCodex

You're a member of a CircleChat workspace. Humans and other agents share the same space — same channels, same DMs, same reactions. Everything you do here happens through the channel described below — not through tool or function calls.

not rated 93 +5 changed 1mo ago A SkillSpector: pass 0 tokens original MIT

do-work

5995

bladnman/do-work

Skill Claude Code

Task queue - add requests or process pending work.

not rated 93 8mo ago A 12 tokens

hertzflow

5996

HertzFlow/hertzflow-skills

Skill Claude CodeCodex

An on-chain trading-research guide for examining token activity across Binance Alpha and several Ethereum-compatible blockchain networks. It covers trader or insider distribution, confirmed selling, wallet categories, unusual activity waves, and monitoring exports.

not rated 93 +1 4mo ago A Socket: warnSnyk: warnSkillSpector: warn 306 tokens original MIT

agent-orchestra

5997

3338902669-ops/agent-orchestra

Skill Claude CodeCodex

Use when three or more AI agents are available and a task needs coordinated execution, or when work must be handed to another agent, session or tool. It ships the coordination rules as ENFORCED invariants rather than advice: one writer per resource (a conflicting claim is refused and names the holder), a verifier that…

not rated 93 changed 17d ago A 291 tokens original Apache-2.0

python-testing

5998

Jamkris/everything-gemini-code

Skill Claude CodeCodex

Python testing strategies using pytest, TDD methodology, fixtures, mocking, parametrization, and coverage requirements.

not rated 93 5mo ago A 24 tokens original MIT

ml-paper-writing

5999

raphaelmansuy/edgecrab

Skill Claude CodeCodex

Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.

not rated 93 3mo ago A 65 tokens

build-mcp-app

6000

nota-america/forgecat-agent-profiles

Skill Claude Code

This skill should be used when the user wants to build an "MCP app", add "interactive UI" or "widgets" to an MCP server, "render components in chat", build "MCP UI resources", make a tool that shows a "form", "picker", "dashboard" or "confirmation dialog" inline in the conversation, or mentions "apps SDK" in the…

not rated 93 1mo ago A SkillSpector: pass 111 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: