50,342 tagged Claude Code, measured the same way as everything else here.
Browse within: agentic-ai 319antigravity 270agentic-skills 191ai-workflows 185coding-agents 164agentic-framework 109agentic-workflow 109swarm 109Autonomous Agents 106claude-code-skills 101ci 97LLM 96actions 96agent-infrastructure 96
Skill Claude Code
Orchestrates multi-phase research pipeline: scoping, evidence collection, claim extraction, graph relationship enrichment, section brief synthesis, report composition, and publishing.
wrsmith108/claude-skill-version-sync
Skill Claude CodeCodex
Detect and synchronize Node.js version specifications across project files.
Skill Claude CodeCodex
Write, read, debug, and compile wenyan-lang (文言) code — a programming language using Classical Chinese grammar that compiles to JavaScript, Python, or Ruby. Use this skill whenever the user asks about wenyan-lang, Classical Chinese programming, writing .wy files, debugging wenyan code, translating between wenyan and…
Skill Claude CodeCodex
Production scope gatekeeper v3 — catches secretly-MVP plans before they reach the audit pipeline. Use this skill when the user says 'fazxes', 'check scope', 'is this complete', or right after a plan is written and before it goes to /audit-plan. Hunts for buried scope reductions ('trade-offs accepted', 'for v1'…
Skill Claude CodeCodex
An automatic documentation tool that analyses dependencies, creates an outline, and writes Markdown pages with source labels.
Skill Claude CodeCodex needs its repo
Import an Obsidian vault into ChromaDB for semantic search. Parses markdown files, extracts frontmatter, headings, tags, and content sections. Chunks intelligently by heading hierarchy. Use when indexing a knowledge base, importing notes for semantic recall, or syncing an Obsidian vault to a vector database.
Skill Claude Code
AI-powered growth marketing creative engine. Generates multi-variant ad creatives from a product positioning document + channel selection, runs structured A/B experiments, monitors for creative fatigue / CAC shifts / payback drift, allocates spend via Thompson Sampling, and feeds learnings into a persistent knowledge…
Skill Claude CodeCodex
Analyze Claude Code session transcripts for repeating behavioral patterns and create GitHub Issues with suggestions.
Skill Claude CodeCodex needs its repo
Headless handoff guide for running other AI models from inside an agent session (any Agent Skills runtime - Claude Code, Codex, Grok Build, Cursor, OpenClaw, Hermes). Covers GPT (codex exec), GLM (opencode run or zcode --prompt), Grok (grok -p), Gemini (Antigravity agy -p), and Claude (claude -p or a subagent) …
Skill Claude CodeCodex
Coordinate and record an exact-approved delivery against pre-defined acceptance criteria, preserve private evidence, and prepare an evidence-labelled field report. Use after a payable test reaches delivery or an observed result.
mturac/recsys-pipeline-architect
Skill Claude CodeCodex
Designs composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework popularized by X's open-sourced For You algorithm. Use this skill when the user wants to build any system that picks "the top K items for a user/context" — content feeds…
Skill Claude Code needs its repo
A routing guide and builder for Prismstack, a collection of interactive skills for work in a specific field. It helps choose the right skill and load its instructions.
Skill Claude CodeCodex
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
brandrylabs/claude-jsonl-compressor
Skill Codex
Compress one Claude Code JSONL session with strict active-branch isolation, model-authored semantic summaries by default, recent raw context for rewind, validated compact-style output, transactional backup/replacement for one live .claude/projects file, and an independent byte-preserving Read.pages compatibility…
oukeming64-tech/candidate-screen
Skill Claude CodeCodex
A first-pass hiring review that reads applications and recommends passing, holding, or rejecting each candidate, with evidence for every recommendation. The final hiring decision remains with a human.
Skill Claude CodeCodex
A tool for finding, comparing, checking, and installing existing agent skills from different sources. It groups copies of the same skill and checks them for suspicious content before installation.
Skill Codex
A command-line tool for controlled file and directory operations, including reading, searching, editing, moving, deleting, binary handling, and JSON batch plans.
Skill Claude CodeCodex
A process for recording lessons from completed development work in reusable project notes and platform-specific guidance files.
Skill Claude CodeCodex
An executable, spec-driven framework for building production-ready AI-native applications. Based on 2026 best practices.
takeaseatventure/devops-skills
Skill Claude CodeCodex
Diagnose and validate cron expressions before they ship. Catches the five silent death-traps: impossible dates that never fire, OR-semantics that fire too often, midnight spikes, uneven step drift, and leap-year February 29.
Skill Claude CodeCodex
Use when working an enterprise B2B deal. Builds relationships with 4-6 stakeholders, maps the buying committee, surfaces blockers early.
Skill Codex
A review process for checking whether an operator’s reported sales are accurate before calculating revenue-sharing payments or performance obligations. It compares the report with records the operator does not control, such as utility use, access logs, delivery-platform payments, and inventory deliveries.
Skill Claude CodeCodex
Prevents prompt-cache thrash and runaway token burn in long or image-heavy agent sessions. Load BEFORE reading images/screenshots (visual QA, render checks, UI verification, diagram review) in a conversation that already has substantial history, when running long agentic loops with periodic wake-ups, or when the user…
Skill Claude CodeCodex
Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
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: