Recently added

볼륨 큰 AI 협업 작업의 폭발 반경을 줄이는 워크플로우 — 상태 단일화, 결정론 판정, 분모 고정

Project-agnostic agentic SDLC framework: entities are the single source of truth, every index is generated, and the deterministic operations are script calls with fixed token cost.

Lightweight loop harness with strict evidence gates.

German freelancer tax filing for Claude Code. Fetch transactions from your bank, classify with AI, calculate EÜR, file via ELSTER.

Reusable AI dev workflow for Claude Code: orchestrated agents, session lifecycle, deep reviews, and project-aware slash commands.

A portable v1 suite. Includes 1 skill and 2 MCP servers.

display-name-skill is an open-source Claude Code plugin indexed from GitHub. Review its manifest and source before installing.

Nested Codex runtime plugin. Includes 1 skill.

Codex bundled demo plugin with an MCP server

Not listed in the marketplace

Second demo skill. Includes 1 skill.

First demo skill. Includes 1 skill.

CC command and agent compat fixture. Includes 1 skill.

bad-skill-suite is an open-source Claude Code plugin indexed from GitHub. Review its manifest and source before installing.

bad-mcp is an open-source Agent Plugins plugin indexed from GitHub with 1 skill and 1 MCP server. Review its manifest and source before installing.

A focused toolkit for clarifying goals and delivering verifiable software artifacts.

Semantic long-term memory and context engine for coding agents. Recall prior knowledge with the find/search/read MCP tools and persist durable facts with remember/write, backed by an OpenViking server.

Turn one Codex task into a durable repository root with visible, bounded orchestration and recovery.

Orchestrate parallel Codex agents with reusable DAG workflows, strict outputs, detached runs, adaptive research, and persistent loops

Ten language servers for Claude Code (bash, PHP incl. .phtml, Java, Kotlin, Nix, Python, Rust, TypeScript, Vue, YAML). Needs its binaries installed separately: nix profile add github:Tschallacka/lsp-flake#lsps — then run /lsp-doctor to check.

ボイスメモをローカル WhisperX で文字起こし＋Claude 校閲し、その内容を口述の指示・思考として会話を始める /voice-memo スキル

GitHub and GitLab automation skills: PR workflows, CI fixes, comment resolution, and contribution planning.

Writing quality and change-safety toolkit: cut AI tells (unslop), remove code slop (deslop), and prove blast radius before shipping.

Core orchestration skills, dev companion, output handshake, PR fallback, and code-reviewer agent. The baseline install for any project.

Full stable skill catalog coverage for consumers who want everything (

18 AI agent personas: 11 holistic (planner, architect, designer, implementer, reviewer, qa-engineer, security-engineer, platform-engineer, researcher, data-engineer) + orchestrator (assistant, client-workflow-bootstrap) + 5 specialists (code-reviewer, agentic-security-reviewer, security-reviewer, e2e-runner, tdd-guide, build-error-resolver) — 7 specialists archived to references in #865 (typescript/database/performance/refactor → reviewer/references/*; docs/reference-lookup → researcher/references/LOOKUP_GUIDE.md; tech-assistant → platform-engineer/references/WORKSTATION_OPS.md) — see docs/AGENT_TAXONOMY.md §8.

Release checklist skill plus the MCP servers it needs

Design, write, repair, review, discover, and audit Python black-box pytest contract suites.

Create and maintain durable project context in the repository itself so any coding agent can quickly understand a project.

IMG.LY CreativeEditor SDK builder agent and documentation for Web

IMG.LY CreativeEditor SDK skills for Swift on iOS, macOS, and Mac Catalyst

IMG.LY CreativeEditor SDK skills for Kotlin and Jetpack Compose on Android

Evidence-first AI agent skills for reliable data analysis, machine learning, and reproducible model validation.

Portable skills, agents, and templates that add Spec-Driven Development and TDD workflows to any Claude Code project.

Claude skills that make an agent verify before asserting, refute its own work, re-read changed state, protect what it doesn't understand, keep things simple, and escalate what it cannot control.

Agent Discovery + Trust: search, verify, and trust tools before calling them — plus webpage understanding and deployment verification.

Search official AI and cloud documentation, verify public web deployments, and discover trusted MCP tools.

An Agent Plugin for persistent AI memory over MCP: notes and knowledge as Open Knowledge Format (OKF) Markdown, cataloged with library and information science. Contains the librocat MCP server and Agent Skills.

An Agent Plugin for persistent AI memory over MCP: notes and knowledge as Open Knowledge Format (OKF) Markdown, cataloged with library and information science. Contains the librocat MCP server and Agent Skills.

An Agent Plugin for persistent AI memory over MCP: notes and knowledge as Open Knowledge Format (OKF) Markdown, cataloged with library and information science. Contains the librocat MCP server and Agent Skills.

Extract any website's design language and ship it. Fourteen slash commands — /extract, /site, /grade, /battle, /remix, /pack, /theme-swap, /brand, /pair, /studio, /verify, /fidelity, /gallery, /dna — wrap the designlang CLI to pull DTCG tokens, Tailwind/shadcn/Figma vars, motion + voice, synthesize a whole-site canonical design system with a consistency grade, generate shareable graded report cards, head-to-head battle pages, six-vocabulary remixes, downloadable design-system bundles, OKLCH-correct theme recolouring, full editorial brand-guidelines books, design crossovers between two sites, a live token-editor studio, a rebuild-and-pixel-diff fidelity check, a measured clone-vs-original fidelity score (visual + motion) with a ranked correction plan via /fidelity, a shareable static gallery of scored clones via /gallery, and — via /dna — a measured design space that places any site among real design systems by nearest neighbours, per-axis percentiles, and the features that make it look the way it does.

Google Cloud Well-Architected Framework guidance across all six pillars.

Cloud Run guidance for coding agents: services, jobs, and worker pools.

Google Kubernetes Engine guidance for coding agents: clusters, networking, scaling, security, observability, cost, and AI inference.

Core Google Cloud guidance for coding agents: onboarding, authentication, and gcloud CLI safety.

Gemini Enterprise Agent Platform guidance for coding agents: deploy, tune, evaluate, and operate agents and models.

Gemini API guidance for coding agents: generation, the Interactions API, and the Live API.

Explain any topic like I'm 5: a dead-simple HTML picture explainer with big visuals and few words. Use /eli5 <topic>.

Engineer an agent's forgetting, not just its remembering. Four deterministic stdlib scripts implement the four lenses of agent memory: a cost profiler that splits construction from query spend and reports cost per correct answer (construction energy exceeds total query energy across 300 queries in the Stanford characterization); an architecture picker that scores the four paradigm families — long-context, flat RAG, structure-augmented RAG, agentic — disqualifies on hard constraints, names the cost the winning choice makes you pay, and refuses to pick when the top two tie; a density auditor that classifies every record in a real memory directory or JSONL export as FACT / SKILL / LOG / PROSE, finds near-duplicates, and flags stale and time-relative wording; and a forgetting-policy linter that fails any design with no forgetting rule or that auto-merges contradictions. Ships cs-memory-engineer agent, /cs:memory-engineering and /cs:forgetting-audit commands, 4 references citing 7 sources each, and a seven-question forcing worksheet.

Converts books, documentation folders, and source collections (PDF, EPUB, DOCX, HTML, Markdown, RST, AsciiDoc, RTF, MOBI/AZW) into structured agent skills: a master SKILL.md with core frameworks and a topic index, on-demand chapter files, a glossary, a patterns file, and a decision cheatsheet. Ships 4 stdlib-only tools (multi-format extractor with invisible-Unicode sanitization, four-family generated-skill validator, pre/post-flight token budget estimator, and a plugin emitter that wraps a compiled skill as an installable claude-skills package), 5 references citing 7-8 sources each (including the full step-by-step conversion workflow), a cs-book-to-skill agent, and /cs:book-to-skill + /cs:book-to-plugin commands. Use when the user wants to study a document with an agent, apply an author's frameworks while working, turn internal docs or standards into a reusable knowledge base, or package a compiled book skill as a plugin.