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.

release

11281

gpauloski/python-template

Skill Claude Code

Cut a new release by tagging a version and publishing via GitHub, which triggers the PyPI Trusted Publishing and docs-deploy workflows. Use when asked to "make a release", "cut a version", or "publish".

not rated 19 4d ago A SkillSpector: pass 47 tokens original MIT

consulting-analysis

11282

hunterLee666/deerflow2.0-project

Skill Claude CodeCodex

Use this skill when the user requests to generate, create, or write professional research reports including but not limited to market analysis, consumer insights, brand analysis, financial analysis, industry research, competitive intelligence, investment due diligence, or any consulting-grade analytical report. This…

not rated 19 7mo ago A 110 tokens

pin-guard

11283

walidboulanouar/pin-guard

Skill Claude CodeCodex

Enforce exact, pinned package versions across a JavaScript/TypeScript repo and its agent tooling. Scans package.json dependencies, npm scripts, MCP server configs (.mcp.json, Claude/Cursor settings), and CI workflows for unpinned specs (^, , , latest, missing versions on npx). Pins everything to exact versions…

not rated 19 5mo ago A 156 tokens original MIT

review-plan

11284

shravan-swagwalapm/shipstack

Skill Claude CodeCodex

Engineering review of implementation plan — ASCII diagrams, test matrix, past-mistakes injection, prerequisite chaining.

not rated 19 7mo ago A 24 tokens original MIT

sf-code-analyzer

11285

rsoesemann/ROBERT.md

Skill Claude Code

Run Salesforce Code Analyzer on Apex, Trigger, Flow, or metadata files. Use after writing or modifying .cls, .trigger, .xml, or flow files. Also use when asked to scan, lint, or check code quality.

not rated 19 3d ago A 52 tokens

belt

11286

jfrog/agent-belt

Skill Claude CodeCodex needs its repo

Operate the belt CLI to evaluate headless coding agents (Claude Code, Cursor, Codex, Gemini, and others) end to end. Use when the user asks to write or run eval scenarios, compare agents, score outputs with rules or LLM judges, register a new agent adapter, interpret reports or benchmark cards, or set up evals in CI.…

not rated 19 1mo ago A SkillSpector: pass 116 tokens original Apache-2.0

dayu-harness

11287

kinoward/dayu-harness-skill

Skill Codex

A one-time deployment tool that adds a project governance system built around AGENTS.md, project instructions, documentation, hooks, continuous integration, and maintenance scripts.

not rated 19 5mo ago A 69 tokens original MIT

brother-skill

11288

henryjohnbrand/brother-skill

Skill Claude CodeCodex

Distill the bros in your life — real brothers, internet brothers, group chat legends, and content creators who feel like friends. Captures how they talk, what makes them funny, their catchphrases, their chaos energy. Feed it clips, screenshots, and stories. It learns to talk like them, think like them, and roast you…

not rated 19 +1 7mo ago A 87 tokens original MIT

agentpack-operator

11289

liqiongyu/agentpack

Skill Claude CodeCodex

Operate agentpack safely in Claude Code. Use /ap- commands for execution; prefer --json.

not rated 19 +1 8mo ago A 25 tokens original MIT

guidance

11290

eric-cielo/moflo

Skill Claude Code

Add, edit, or audit guidance docs. Default writes guidance for Claude (.claude/guidance/, Markdown, moflo universal rules). -h writes for human readers (docs/, lighter ruleset). --html emits HTML with a minimal default stylesheet instead of Markdown. -a audits the .claude/guidance/ directory.

not rated 19 yesterday A SkillSpector: warn 70 tokens original MIT

stop-slop

11291

rpfilomeno/opencode-docker

Skill Claude CodeCodex

Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.

not rated 19 5mo ago A 26 tokens copy · 92% MIT

autogap

11292

micpet7514088/autogap

Skill Claude CodeCodex

High-value project analyst + impl strategist. Any project type (code, docs, research, strategy, workflow, creative, ops, non-tech, hybrid). Inspect deep, infer top-value objective from signals, find top 3 gaps, propose 3 macro-steps user picks (none/one/two/all). After pick, plan + implement autonomously. Triggers…

not rated 19 +1 6mo ago C 134 tokens original MIT

plan-implementation

11293

dnlbox/ai-protocol

Skill Claude CodeCodex

Create the minimum execution contract needed to implement accepted product intent.

not rated 19 3mo ago A 16 tokens original MIT

devPnal/design-system-is-all-you-need

Skill Claude CodeCodex

This skill provides a curated set of cross-platform design guideline prompts for building consistent, high-quality UIs. Each guideline defines common rules, component-specific guides, and an auto-derived token system — all driven by minimal user inputs.

not rated 19 8mo ago A 53 tokens original MIT

convex-create-component

11296

Cheggin/minecraft-use

Skill Codex

Designs and builds Convex components with isolated tables, clear boundaries, and app-facing wrappers. Use this skill when creating a new Convex component, extracting reusable backend logic into a component, building a third-party integration that owns its own tables, packaging Convex functionality for reuse, or when…

not rated 19 6mo ago A 95 tokens GPL-3.0

rust-best-practices

11297

JSK9999/ai-nexus

Skill Claude CodeCodex

Comprehensive Rust best practices covering ownership, error handling, async patterns, testing, and project structure.

not rated 19 8mo ago A 25 tokens original Apache-2.0

browser-automation

11298

archubbuck/workspace-architect

Skill Claude CodeCodex

Local Python-based browser automation toolkit using Playwright. Provides command-line tools for navigating, interacting with, and testing web applications without using MCP protocols. Supports clicking, typing, hovering, screenshots, content extraction, and JavaScript execution.

not rated 19 yesterday B 50 tokens original ISC

perplexity-web-research

11299

xpepper/perplexity-agent-skill

Skill Claude Code

Leverage Perplexity CLI for web research, deep reasoning, and independent validation. Use when you need current/external knowledge, want a second opinion before decisions, or want to delegate complex analytical thinking to specialized reasoning models. Complements (not replaces) standard web tools. Can be invoked…

not rated 19 9mo ago A 73 tokens original MIT

whmcs-dev-skills

11300

Waqasahmedwaseer/whmcs-dev-skills

Skill Claude CodeCodex

Senior WHMCS Developer & Architect skill for AI coding agents. Builds, debugs, and maintains WHMCS Addon Modules, Provisioning (Server) Modules, Domain Registrar Modules, Payment Gateway Modules, and Action Hooks. Enforces WHMCS 8.x / 9.x best practices, modern PHP 8.1+ standards, Laravel Capsule ORM, Smarty v4…

not rated 19 9mo ago A 127 tokens GPL-2.0

compliance-remediation

11301

tahirraufkeeyu/software-development-agent-stack--sdas

Skill Claude CodeCodex

Use when compliance-check has produced control gaps (SOC2, ISO 27001, HIPAA, PCI) and you need to close them. Classifies each gap as Design / Operating / Evidence, drafts or configures the missing policy / control / evidence artifact, maps the closure to the control ID, and assembles the auditor-ready evidence locker.

not rated 19 6mo ago A 75 tokens original MIT

frontend-nextjs

11302

arvoreeducacao/rhm

Skill Claude CodeCodex

NextJS frontend development patterns. Use when developing frontend code with NextJS, React, Tailwind, and TypeScript.

not rated 19 11d ago A SkillSpector: pass 28 tokens original MIT

unityctl-workflows

11304

Jason-hub-star/unityctl

Skill Codex

Drive, inspect, debug, and verify Unity projects through the unityctl CLI or MCP server. Use when an agent needs to modify scenes, GameObjects, components, assets, scripts, project settings, Play Mode, tests, builds, screenshots, or verification workflows in a Unity project, especially when changes need structured…

not rated 19 2mo ago A SkillSpector: pass 79 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: