template-skill
20665Skill Claude Code
Replace with description of the skill and when Claude should use it.
not rated 1 8mo ago A 17 tokens
copy · 100% MIT
check
20666Skill Claude Code
Reviews code diffs after implementation, auto-fixes safe issues, and runs specialist security and architecture reviewers on large diffs. Also triages issues and PRs when the user mentions them. Not for exploring ideas or debugging.
not rated 1 3mo ago A 47 tokens
original MIT
reverse-skills
20667Skill Claude Code
Reverse-engineer Android APKs, especially Flutter/Dart AOT apps. Guides static analysis (blutter, object-pool deserialization, capstone disasm), ARM64 libapp.so binary patching, Frida dynamic instrumentation, signature/integrity-bypass, packer (360 jiagu) handling, and test-environment choice. Use when the user wants…
not rated 1 3mo ago A 174 tokens
original MIT
Skill Claude CodeCodex
Use when applying 2d animation best practices.
not rated 1
changed 14d ago A 18 tokens
mcp-builder
20669Skill Claude CodeCodex
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
not rated 1 7mo ago A 61 tokens
baozi-prediction-markets
20670Skill Claude CodeCodex
Trade, create, and manage Solana prediction markets on Baozi.bet — autonomous betting, market creation, affiliate earnings, and portfolio tracking.
not rated 1 5mo ago A 35 tokens
one-person-pharma
20671BioTender-max/one-person-pharma
Skill Claude CodeCodex
Build a complete AI-powered protein design pipeline with cloud GPU compute (Modal) and automated wet-lab validation (Adaptyv Bio). Enables dry-wet closed-loop iteration for antibody/binder discovery at a fraction of traditional CRO costs ($1.7K for 3 rounds). Use this skill when: (1) Designing a protein/antibody…
not rated 1 5mo ago C 128 tokens
content-summarizer
20672CaptainDarkHeart/claude-skills-starter-kit
Skill Claude CodeCodex
Read this when the user asks to summarize something, wants the key points, or uploads a document to condense. Use it for long-form content such as articles, documents and reports. It produces a concise summary.
not rated 1
changed 3d ago A 48 tokens
original MIT
chrome-hook-browser
20673Skill Claude CodeCodex
Launch Chromium/Chrome via Playwright MCP (chrome-hook) with network hooks, multi-slot dual browsers (account A + B without logout), cookie/storage persistence, authenticated API requests, and Plan A real-browser CDP attach for strict bot protection. Use when the user wants browser automation without Browser MCP…
not rated 1 2mo ago A 108 tokens
phylax-skill-audit
20674Skill Claude CodeCodex
Pre-install security audit for agent skills on Base. Scans SKILL.md + manifest for prompt-injection and secret-exfiltration, audits referenced contracts (unlimited approvals, upgradeable owner, honeypot), and validates x402 endpoints. Returns a deterministic risk verdict (ALLOW/WARN/DENY) with evidence. Read-only…
not rated 1 2mo ago A 82 tokens
original MIT
cli-builder
20675Skill Claude CodeCodex
Build a generic-installable CLI tool with its companion SKILL.md so any agent (Vellum, Claude, GPT, etc.) can pick it up and use it. Use when the task is "ship a CLI for service X" or "wrap API Y in a tool agents can call." Out of scope for one-off internal scripts that don't need agent discovery, and for skills that…
not rated 1 3mo ago A 95 tokens
original MIT
youtube_upload
20676marco77x/openclaw-youtube-pipeline
Skill Claude CodeCodex
Carica video su YouTube con thumbnail. Usa questa skill per pubblicare video.
not rated 1 6mo ago A 20 tokens
original MIT
Skill Claude CodeCodex
Run one bounded ESRA review after a major architecture or skill change, repeated failure, or an explicit full-cycle request. Select only the meta-skills justified by observable evidence; skip routine successful work. Triggered by "orchestrate evolution", "run full ESRA cycle", "improve self-development cycle", "hermes…
not rated 1
changed 26d ago A 85 tokens
original Apache-2.0 archived
Skill Claude CodeCodex
A paragraph-by-paragraph review process for Japanese documents that identifies claims, supporting reasons, connections, and opposing views. It is designed to clarify reasoning, not to guess what the writer intended.
not rated 1 2d ago A 137 tokens
context-degradation
20679sheng3233836/vibe-coding-standards
Skill Claude CodeCodex
This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. Provides patterns for recognizing…
not rated 1 6mo ago A 66 tokens
Skill Claude CodeCodex
A tool that turns a code change into a self-contained HTML report for a person to review. It explains the change’s purpose, effects, risks, compatibility, and supporting checks instead of only showing added and removed lines.
not rated 1 2mo ago A 107 tokens
original Apache-2.0
html2deck
20681Skill Claude Code
Turn an HTML page (benchmark walkthrough, README, or written explainer) into 16:9 presentation slides by MEASURING rendered height, projecting a visual-first face (strip excess prose to speaker notes), and splitting overflowing sections at safe child boundaries — never shrinking text below a readability floor. Emits…
not rated 1 2mo ago A 79 tokens
original MIT
avoid-ai-writing
20682Skill Claude Code
Audit and rewrite prose to remove AI writing patterns, with detect-only and edit-in-place modes. Use when asked to remove AI-isms or make writing sound less machine-written.
not rated 1
changed 2d ago A 39 tokens
Skill Claude CodeCodex
Master context engineering principles for building production-grade AI agent systems with effective context management, multi-agent architectures, and memory systems.
not rated 1 2mo ago A 31 tokens
brainstorm
20684Skill Claude CodeCodex
Facilitate a structured brainstorm — from a fuzzy idea or open decision to a committed, remembered outcome. Use when the user wants to think something through, weigh options, explore an idea, make a non-trivial decision, or asks to "brainstorm", "think this through", "help me decide", "kick this around". Also use to…
not rated 1 3d ago A 98 tokens
original MIT
commit-discipline
20685ayush-singh-0601/commit-discipline-mcp
Skill Claude CodeCodex
Plan implementation work into small test-gated Git commits and record each stage through commit-discipline-mcp.
not rated 1 3d ago A 25 tokens
original MIT
deepseek-vision-skill
20686Skill Claude CodeCodex
A vision skill that sends images and screenshots to a visual analysis service. It adds image understanding to a model that otherwise works only with text.
not rated 1 2mo ago A 39 tokens
coaligne-workflow
20687dataelement/dsh-plugin-coaligne
Skill Claude CodeCodex
CoAligne workflow skill. Use when a user wants an Agent to use shared CoAligne project context: inspect synced files, read Agent sessions, understand teammate activity, send files or sessions to teammates, download cloud files, resolve CoAligne file/session links, or troubleshoot CoAligne Desktop sync.
not rated 1 1mo ago A 66 tokens
diepi-quant-research
20688elonmaskhair-prog/dsh-plugin-diepi
Skill Claude CodeCodex
Turn a natural-language daily A-share stock or ETF idea into a typed diePi StrategySpec, obtain missing Tushare data through an already-installed official Skill, validate marketdatav1 inputs, run an auditable backtest, and interpret only verified results.
not rated 1 2d ago A 59 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: