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.

longtext-translate

7201

zlhhhh8901/longtext-translate

Skill Claude CodeCodex

A workflow for translating, checking, or polishing text of any length. It first converts local PDFs and EPUBs into Markdown, a plain-text document format, before translating them.

not rated 58 +1 4mo ago A 86 tokens

repogps-basecamp

7202

masterofthechaos/ProxyPilot-public

Skill Claude CodeCodex

Establish and maintain a tiered, reversible repository governance foundation and scoped session Waypoints.

not rated 58 +1 changed 1mo ago A 24 tokens AGPL-3.0

smartstudy

7203

HumphreySun98/Smart-Study-Agent

Skill Claude CodeCodex

Turn any lecture material (text, PDF, web page) into an adaptive study session — extract topics, quiz the user, track mastery with FSRS spaced repetition, and let the RL policy decide what to study next. Use when the user wants to study, revise, prepare for an exam, or asks "quiz me" on some material.

not rated 58 2mo ago A SkillSpector: pass 72 tokens original MIT

fix-ticket

7204

EricTechPro/startup-claude-skills

Skill Claude CodeCodex

Automate the full Jira bug-fix pipeline end-to-end. Use when the user says 'fix ticket', 'fix PROJ-123', 'fix this bug', 'resolve PROJ-XXX', 'fix and ship this ticket', or passes a Jira ticket ID for autonomous bug resolution. Reads the Jira ticket, implements the fix, reviews it, commits, moves the ticket to QA…

not rated 58 +1 5mo ago A 115 tokens original MIT

design-contract

7205

Carlos-Dominguez-faber/criterio

Skill Claude CodeCodex needs its repo

Crea el contrato de diseño de un proyecto antes de escribir el primer componente. Corre una entrevista de 8 preguntas, elige un preset visual, y escribe brand.json, voice.json, motion.json y COMPONENTRULES.md (y compila brand.css). Úsala cuando el usuario diga "quiero que se vea bien", "hazme una landing bonita"…

not rated 58 +1 3mo ago A SkillSpector: pass 143 tokens original MIT

vajra-code-review

7206

zamana-inc/vajra

Skill Claude CodeCodex

Use for Vajra code review stages to perform a blocking review of the implementation, writing findings or approval.

not rated 58 3mo ago A SkillSpector: pass 26 tokens original MIT

create-parents

7207

xiaoheizi8/parents-skills

Skill Claude Code

A tool for turning information about a parent into an AI skill, including chat history, photos, and voice memos. It can create a memory and personality profile and update it over time, in English or Chinese.

not rated 58 7mo ago C 70 tokens original MIT

toss-tech-design

7208

Ilbie/Toss-Design-Skill

Skill Claude CodeCodex

Use when applying Toss Tech Design principles from a 129-article toss.tech design summary to complex product flows, research ops, internal tools, UX writing, accessibility, or brand work with high cognitive load, repeated manual work, trust issues, or inclusion gaps.

not rated 58 4mo ago A 57 tokens original MIT

irenerachel/skill-interview-builder

Skill Claude CodeCodex

A step-by-step interview workflow for creating a complete coding-agent skill package. It gathers the skill's purpose, triggers, environment, references, output rules, and supporting files before producing the package.

not rated 58 7mo ago A 166 tokens original MIT

byok-relay

7210

avikalpg/byok-relay

Skill Claude CodeCodex

OpenAI-compatible LLM gateway for any client-side application (browser, mobile, React Native, Flutter, VS Code extensions, browser extensions, Electron, smart TV, and more). Routes requests to OpenAI, Anthropic, Gemini, Groq, Mistral, and 200+ models, handling CORS, key encryption, and streaming without a dedicated…

not rated 58 changed 1mo ago A SkillSpector: warn 131 tokens original Apache-2.0

odie

7211

dcramer/agents

Skill Claude CodeCodex

Use when transcript, commit, Sentry, GitHub, CI, review, or Garfield history suggests recurring failure patterns that might become hard deterministic checks. Analyze the evidence, reject judgment-based ideas, and output only mechanically enforceable lint, schema, CI, workflow, or deterministic test rules. Do not use…

not rated 58 +1 24d ago A SkillSpector: pass 78 tokens original Apache-2.0

symbiont

7212

ThirdKeyAI/Symbiont

Skill Claude CodeCodex

AI-native agent runtime with typestate-enforced ORGA reasoning loop, Cedar policy authorization, CommunicationPolicyGate for inter-agent governance, ToolClad declarative tool contracts, knowledge bridge, zero-trust security, multi-tier sandboxing including a daemon-free Landlock tier, governed workflow improvements…

not rated 58 +1 changed 1mo ago A 107 tokens original Apache-2.0

burner-phone

7213

SouthpawIN/burner-phone

Skill Claude CodeCodex

Universal Android device control with vision feedback. Supports Termux phones, ADB-only devices, and emulators. Use for phone automation, AI companionship, or mobile app testing.

not rated 58 +1 4mo ago B 39 tokens original MIT

fix-ci

7214

CliMA/CloudMicrophysics.jl

Skill Claude Code

Fix CI failures and performance regressions for a Julia package PR by iterating - triage the latest CI results, fix one root cause, verify locally, push. Use when a PR's GitHub Actions or Buildkite CI is failing, or when CI jobs run slower than they do on the main branch. Verifies CPU and GPU compilation locally…

not rated 58 +1 changed 6d ago A 95 tokens copy · 100% Apache-2.0

my-skill

7215

TokenRollAI/acplugin

Skill Claude Code

A sample skill for testing conversion.

not rated 58 2mo ago A 10 tokens

pine-develop

7216

greenpeas007/tradingview-mcp-jackson

Skill Claude CodeCodex

Full Pine Script development loop — write code, compile, fix errors, iterate. Use when building a new indicator or strategy in TradingView.

not rated 58 4mo ago A 32 tokens

recallium-guidance

7218

recallium-ai/recallium

Skill Claude CodeCodex

Use when you have access to Recallium MCP tools. Provides guidance on memory storage, search, and knowledge management. CRITICAL - invoke the MCP tool recallium at session start, store memories after EVERY substantive interaction, and honor global rules.

not rated 58 29d ago A 57 tokens

hersona

7219

shiro-0x/hersona

Skill Claude CodeCodex

A skill for building reusable agent personas from separate traits, such as personality, speaking style, role, appearance, and hobbies. Several traits can be combined and applied to the current session.

not rated 58 +1 1mo ago A SkillSpector: warn 261 tokens original MIT

debug-tunnel-network

7220

LongNgn204/local-coding-agent

Skill Claude CodeCodex

Diagnose Local Coding Agent tunnel, DNS, TCP, TLS, proxy, organization, and office-network blocking issues.

not rated 58 1mo ago A 28 tokens AGPL-3.0

blog-to-linkedin-post

7221

JeffLi1993/content-repurposing-skills

Skill Claude CodeCodex

Convert a long-form blog article into LinkedIn-ready professional posts with a clear point of view, source-grounded golden quote, last-30-day trend adaptation, current LinkedIn rule checks, and a primary visual concept or generated image. Use when the user asks for blog to LinkedIn, LinkedIn post, LinkedIn…

not rated 58 +1 3mo ago A 95 tokens

real-browser-control

7222

ofershap/real-browser-mcp

Skill Claude CodeCodex

Connect an AI coding agent to the user's REAL Chrome via Real Browser MCP (local MCP server + Chrome extension over localhost WebSocket). Use for live UI verification, already-open tabs, existing cookies/SSO/2FA, staging admin panels, and any task where headless Playwright or a cloud agentic browser would miss the…

not rated 58 7d ago A SkillSpector: warn 158 tokens original MIT

tmux-via-mcp

7223

bnomei/tmux-mcp

Skill Claude CodeCodex

Use the tmux MCP tools to create sessions, shape layouts, run tracked commands, and automate interactive terminals when a real TTY or parallel panes are required.

not rated 58 +1 4mo ago A 39 tokens original MIT

30x-seo-local

7224

norahe0304-art/30x-seo

Skill Claude Code

Local SEO audit and optimization for Google Business Profile, Google Maps, and Gemini Ask Maps. Covers GBP completeness, NAP consistency, review strategy, local schema, competitor benchmarking, GeoGrid visibility, multi-location, AI Local Pack readiness, and GBP suspension prevention. Use when user says "local SEO"…

not rated 58 8mo ago A 110 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: