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.

obra/clank

Skill Claude Code

Hide implementation details behind interfaces - work at domain level (what), not implementation level (how).

not rated 43 +1 1y ago A 24 tokens

computer-use

8306

Plocr/Reasonix-computer-use

Skill Claude Code

A set of rules for controlling Windows desktop applications through screen observation and simulated mouse and keyboard actions. It also describes how to find and launch installed applications and verify the results.

not rated 43 3mo ago A 23 tokens original MIT

chapter-progress-bar

8307

serenawangCU/chapter-progress-bar

Skill Claude CodeCodex

A tool for creating transparent chapter-progress overlays for videos from subtitle files or supplied timestamps. It supports several listed visual styles, including layouts for horizontal and vertical video.

not rated 43 changed 1mo ago A 105 tokens

spec-to-readable-html

8308

KeMezz/spec-to-readable-html

Skill Claude Code

Transform Markdown or text specifications into human-readable HTML documents with summaries, reordered structure, visual explanations, diagrams, charts, and traceability to the source. Use when asked to convert a spec, requirements document, API spec, product spec, design doc, or technical document into readable HTML…

not rated 43 5mo ago A 91 tokens original MIT

budget-tracking

8309

Katagiri-Hoshino-Lab/VibeCodeHPC

Skill Claude Code

Compute budget management with phase-based termination criteria. Use when checking budget, determining project phase, or making stop decisions.

not rated 43 27d ago A 27 tokens original MIT

qi-cli

8310

itsmostafa/qi

Skill Claude CodeCodex

Guide for using qi, a local knowledge search CLI for macOS and Linux. Use this skill when the user wants to index documents into a searchable knowledge base, search or retrieve from one, configure qi's collections or embedding providers (Ollama, OpenAI-compatible), choose between its search modes (lexical BM25 or…

not rated 43 changed 14d ago A SkillSpector: warn 92 tokens original MIT

mcp_demo

8311

sinanuozdemir/advanced-ai-intensive

Skill Claude CodeCodex

You have a shell. You can write Python files and run them. Use that to answer the user's question by searching a pre-built corpus.

not rated 43 +1 3mo ago A 0 tokens

agent-media

8312

yuvalsuede/agent-media-skill

Skill Claude CodeCodex

AI UGC video production from the terminal using the agent-media CLI.

not rated 43 6mo ago A 19 tokens original Apache-2.0

design-system

8313

albertzhangz10/design-system-skill

Skill Claude CodeCodex

Generate a complete design system (design.md, design-guidelines.md, design-components.md) from any reference materials — images, PDFs, links, or descriptions.

not rated 43 7mo ago A 35 tokens original MIT

claude-command-router

8314

sepehrbayat/SEPCC

Skill Claude Code

Choose when to use Claude Code built-in commands before adding FCC-specific workflow.

not rated 43 2mo ago A 20 tokens original MIT

dergipark

8315

saidsurucu/dergipark-skill

Skill Claude CodeCodex

Use when the user wants to search Turkish academic journals on DergiPark (keyword or advanced field search by title/author/abstract/DOI/ORCID/year/etc.), read a DergiPark article PDF as text, or extract an article's references — drives the user's own Chrome (no CAPTCHA solving needed) by injecting JavaScript.

not rated 43 3mo ago A 75 tokens original MIT

BayramAnnakov/synthetic-market-research

Skill Claude Code

Fast, cheap market research using LLM-generated synthetic survey responses with Semantic Similarity Rating (SSR). Runs purchase intent, concept tests, and pricing research in minutes instead of weeks, at $0 per respondent. Based on PyMC Labs' validated methodology (90% correlation with real humans across 57 surveys).…

not rated 45 8mo ago A 103 tokens original MIT

isomux-soft-handoff

8317

nmamano/isomux

Skill Claude CodeCodex

Hand off your current task to a peer agent. You write a thorough brief, message it to them directly, then stay around as a reference for follow-up questions. Optionally takes the peer's name as an argument.

not rated 43 +1 changed 12d ago A SkillSpector: warn 51 tokens original

handoff

8318

ToolMonsters/handoff-skill

Skill Claude CodeCodex

Generate a complete handoff document of the current conversation so another LLM (ChatGPT, a fresh Claude, Gemini...) can pick up exactly where this one left off. Use when the user types "handoff", says the session is almost full, mentions hitting the context/usage limit, or wants to continue this conversation in…

not rated 43 3mo ago A 71 tokens original MIT

wiki

8319

natsu1211/deepwiki-skill

Skill Claude CodeCodex

Generating comprehensive wiki-style documentation for any codebase. This skill can be used when 1. Generating documentation for a new project, 2. Update existing documentation after code changes, 3. Create or refine a wiki TOC for a codebase, 4. Obtain a comprehensive overview of an unfamiliar project.

not rated 43 +1 4mo ago A 66 tokens original MIT

jurisd-research

8320

russellbrenner/jurisd

Skill Claude CodeCodex

Expert Australian/NZ legal research and AGLC4 citation using the jurisd MCP server. Use when finding cases or legislation (AustLII), looking up a provision offline, formatting or resolving citations, building a pinpoint, tracing who-cites-what, or producing an AGLC4 bibliography. Triggers on case law, legislation…

not rated 44 +2 6d ago A SkillSpector: warn 133 tokens original Apache-2.0

ielts-writing

8321

Evianyeung1204/ielts-assitant

Skill Claude CodeCodex

A complete coach for IELTS Writing, the writing part of an English-language proficiency exam, covering Task 1 data descriptions and Task 2 essays.

not rated 43 4mo ago A 81 tokens original MIT

manage-skills

8322

umutbozdag/agent-skills-manager

Skill Claude CodeCodex

Discover, list, create, edit, toggle, copy, move, and delete AI agent skills across 11 tools (Cursor, Claude, Agents, Windsurf, Copilot, Codex, Cline, Aider, Continue, Roo Code, Augment).

not rated 43 7mo ago D 57 tokens original MIT

通达信TQ

8323

adambbhe/TDX-finance-mcp-plugin-v3

Skill Claude CodeCodex

A connection between Python strategy files and TdxQuant, TongdaXin's platform for securities data analysis and quantitative investment research. It uses the platform's tqcenter.py module to interact with the TongdaXin client.

not rated 43 16d ago A 56 tokens original MIT

clean-c-drive

8324

iziqing/-disk-cleaner

Skill Claude CodeCodex

A Windows guide for safely freeing space on the C: drive, the computer's main system disk.

not rated 43 +2 3mo ago A 81 tokens original MIT

business-plan

8325

inbharatai/claude-skills

Skill Claude CodeCodex

Write comprehensive business plans — executive summary, market analysis, financial projections, and competitive positioning.

not rated 43 8mo ago A 21 tokens original MIT

hearth-feel

8326

echoo19/hearth

Skill Claude Code

Make a Hearth game feel good, not just run — the juice stack (hit-stop, screen shake, flash, particle bursts, layered sound), tween easing, camera effects, anticipation/recovery animation idioms, game-UX conventions (menus, pause, onboarding, difficulty, save etiquette), effect-asserting playtests, and the quality bar…

not rated 43 +5 1mo ago A SkillSpector: pass 97 tokens original MIT

kpi-dashboard

8327

vivy-yi/finance-skills

Skill Claude Code

A financial KPI dashboard workflow for tracking a company's key performance indicators. KPIs are measurable signs of business health, such as profit margins, cash strength, operating efficiency, and growth.

not rated 43 4mo ago A 107 tokens original MIT

wit

8328

deltadbu/WIT-skill

Skill Claude CodeCodex

Apply WIT (Writing Is Thinking) as a human–LLM collaborative scientific reasoning skill for scientific question formulation, finding-driven research planning, next-experiment selection, Results or Discussion review, claim–evidence and reviewer stress tests, manuscript logic audits, deadline closure, and researcher…

not rated 43 +1 changed 2mo ago A 93 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: