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.

creative-toolkit

14329

HUANGcvs/MeiGen-AI-Design-MCP

Skill Claude CodeCodex

Generate images from text with multi-provider routing — supports Nanobanana Pro, GPT Image, Seedream, and local ComfyUI workflows. Includes 1,300+ curated prompts and style-aware prompt enhancement. Use when users want to create images, design assets, enhance prompts, or manage AI art workflows.

not rated 8 2d ago B 66 tokens original MIT

agent-connector

14330

ken-jo/agent-connector

Skill Claude CodeCodex

Use when building, reviewing, installing, packaging, or diagnosing an agent-connector integration. Two audiences: MCP developers use agent-connector as a framework dependency inside their own branded MCP package/bin, while agent-host users use connector-free agent-connector usage for whole-conversation token totals.…

not rated 8 changed 22d ago A 0 tokens original Apache-2.0

virtualsms-io/mcp-server

Skill Claude CodeCodex

Real SIM-card SMS verification for AI agents via VirtualSMS MCP server. TRIGGERS: SMS verification, OTP code, phone number, virtual number, SIM card, two-factor authentication, account verification, WhatsApp verify, Telegram verify, real SIM, agent phone, MCP SMS, virtualsms. Use when an agent needs to receive an SMS…

not rated 8 2d ago A 106 tokens original MIT

LGDiMaggio/claude-stwinbox-diagnostics

Skill Claude CodeCodex

WHAT: Generates structured diagnostic reports for machine operators and maintenance technicians, summarizing vibration analysis results with severity levels, fault findings, and actionable maintenance recommendations in clear, non-technical language. WHEN: Use when the user asks to create a report, generate a…

not rated 8 5mo ago A 102 tokens original Apache-2.0

nothumansearch

14333

unitedideas/nothumansearch

Skill Claude CodeCodex

Search and score AI-ready websites via MCP. Find MCP servers, check site AI-readiness scores, and verify MCP endpoint compliance using the Not Human Search API at nothumansearch.ai.

not rated 8 1mo ago A 42 tokens original MIT

verification

14334

Aurite-ai/kahuna

Skill Claude Code

Verify agent code against organizational policies and best practices. Trigger this skill when the user says something like "verify my agent", "review agent code", "check compliance", "audit my agent", "check my agent against rules", or "validate agent implementation".

not rated 8 4mo ago A 53 tokens

developer-workflow

14335

derob98/ailmanac

Skill Claude CodeCodex

Use when the user is writing, reviewing, debugging, testing, or refactoring code, or wants help with commits and pull requests. Emphasizes reading existing code first, verifying changes, and never inventing APIs.

not rated 8 today A 48 tokens

mohamed2m2018/react-native-agentic-ai

Skill Claude CodeCodex

Generic AI-agent skill for installing and wiring the @mobileai/react-native SDK into Expo or React Native apps. Use when a coding assistant needs to add MobileAI, install the React Native AI support agent, configure AIAgent, enable screen mapping, set up voice/dictation/human escalation dependencies, troubleshoot…

not rated 8 3mo ago A 87 tokens

replen-onboard

14337

replenhq/replen

Skill Claude CodeCodex

One-time Replen setup — profiles your active repos so matches are relevant, not generic. Runs autonomously in the background. Invoke with /replen-onboard.

not rated 8 19d ago A SkillSpector: warn 38 tokens original Apache-2.0

design-lab

14338

zhenheco/design-lab

Skill Claude CodeCodex needs its repo

Ein persönliches Design-System mit einer Dateiablage pro Kunde, einer lokalen Weboberfläche und einer lokalen Verbindung, die passende gespeicherte Designinformationen für neue Arbeiten bereitstellt.

not rated 8 8d ago C 91 tokens original MIT

codex-claude-worker

14339

zhuzai-2007/claude-code-mcp-harness

Skill Codex

Translate natural-language user requests into bounded Claude Code worker tasks while Codex or ChatGPT remains the supervisor. Use when the user gives an ordinary prompt and wants Codex to clarify scope, choose a safe work boundary, generate a worker prompt, approve or defer worker execution, read run summaries and…

not rated 8 1mo ago A 86 tokens original MIT

ssh-deploy

14340

muchiny/bridge-mcp

Skill Claude Code

This skill should be used when the user asks to "deploy to production", "restart a service", "do a rolling update", "canary deploy", "helm upgrade", or "rollout to K8s". Manual-only for safety — requires explicit /ssh-deploy invocation.

not rated 8 5d ago A SkillSpector: pass 61 tokens original MIT

siyuan-skill

14341

PurpleLiu/siyuan-mcp

Skill Claude CodeCodex

OpenClaw workflows for SiYuan Note via the siyuan MCP server (mcporter).

not rated 8 7mo ago A 25 tokens original Apache-2.0

task-workflow

14342

beyondeye/aitasks

Skill Claude Code

Shared implementation workflow for task-based skills, with profile-check sites wrapped in Jinja conditionals.

not rated 8 changed yesterday A 23 tokens

apiclaw

14343

nordsym/apiclaw

Skill Claude CodeCodex

Set up APIClaw and land one live API execute. When a user says "set up https://apiclaw.cloud/SKILL.md", or you need a research API call without collecting provider keys, follow this file. Auth is Clerk via npx @nordsym/apiclaw auth login. Confirm with npx @nordsym/apiclaw auth whoami before any execute. Execution is…

not rated 8 changed 7d ago C 123 tokens original MIT

flavormancer

14344

echelonts/flavormancer

Skill Claude CodeCodex

Bench-chemistry flavor & aroma analysis from chemical structure. Use when working on food/beverage flavor formulation, ingredient substitution, or molecular taste/aroma questions: predict a molecule's taste (6 heads) and aroma (24 heads); analyze a whole formulation "before you pour" (blended note-profile…

not rated 8 1mo ago A 142 tokens original Apache-2.0

gemini-cli-hud

14345

yideng-xl/gemini-cli-hud

Skill Claude CodeCodex

Activates when user asks about HUD status, terminal display issues, or wants to check context usage and tool call statistics.

not rated 8 3mo ago A 29 tokens original MIT

ssq-predictor

14346

ma-pony/ssq-predictor

Skill Claude CodeCodex

A Chinese-language skill that claims to analyse historical results for China’s Double Color Ball lottery and suggest numbers using statistical and traditional methods. The description does not provide evidence that its predictions improve the odds of winning.

not rated 8 7mo ago A 98 tokens

quick-dev-setup

14348

polygraphso/litmus

Skill Claude CodeCodex

Use when setting up a new Node.js project to install tooling and pre-commit hooks.

not rated 8 2mo ago A 23 tokens original Apache-2.0

sn-implementation

14349

signnow/sn-mcp-server

Skill Claude Code

Coding standards and implementation patterns for SignNow MCP Server. Use when writing or modifying Python source code in this project — implementing features, fixing bugs, refactoring. Covers layer-specific coding rules, error handling patterns, typing standards, the bug fix protocol, and verification steps. Do NOT…

not rated 8 2mo ago A 77 tokens original MIT archived

redator-adversarial

14350

neimaciel/redator-adversarial

Skill Claude Code

Redação e revisão adversarial de peças processuais. Use quando precisar redigir peça (inicial, contestação, réplica, recurso) com estrutura padrão, ou testar peça pronta simulando o juiz (admissibilidade, clareza, requisitos formais) e a parte contrária (contra-argumentos, flancos), gerando relatório de fragilidades…

not rated 8 2mo ago A 87 tokens original MIT

setup-project

14352

SongshGeo/Python-Project-Template

Skill Claude Code needs its repo

Bootstrap a freshly cloned copy of this Python template into a working project — set the project name/description, install dependencies, wire pre-commit, install the recommended external skills, and initialize the memory bank. Use right after applying or cloning the template, or whenever pyproject.toml still shows the…

not rated 8 2mo ago A ✓ AI review 69 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: