harness-engineering
claudeReadiness analysis and enforcement scaffolding for AI coding agent projects.
2 skills
Every plugin for Claude Code we can find on GitHub, read straight from each repo's .claude-plugin manifests. Install one with claude plugin marketplace add owner/repo and claude plugin install name@marketplace — each page has the exact lines. Looking for Codex? See Codex plugins.
Readiness analysis and enforcement scaffolding for AI coding agent projects.
2 skills
止まった場面を責めずに振り返り、見えていなかった前提と次の一歩を見つける対話型スキル。
1 skill
OpenTelemetry Collector component configuration: config keys, defaults, validation rules, signal support, stability, and gotchas. Progressive disclosure via components/<name>/README.md plus on-demand detail files.
1 skill
Building custom OpenTelemetry Collector distributions with OCB: builder manifest authoring, core/contrib/provider version alignment, local component development, CI/Docker/multi-arch builds, and troubleshooting.
1 skill
OpenTelemetry declarative YAML configuration for SDK setup (otelconf, OTEL_CONFIG_FILE, file_format). Points at upstream schema, env-var substitution, and configuration precedence.
1 skill
Apple-authored SwiftUI and platform guidance extracted from Xcode.
1 skill
Migrates consumer projects between major versions of Montage (Wanted Design System for Web)
1 skill
Standalone self-documentation: classified indexes, progressive disclosure and staged Git checks.
1 skill
Mission Control for Claude Code — auto-starts web dashboard, provides 85+ MCP tools and 12 skills including /session-recap, /daily-cost, /standup, /coaching, /insights, /live, /usage, and /team-status.
PM agents, slash commands, and Claude-only playbooks for the lane conveyor.
62 skills · 4 commands · 24 agents · 1 MCP server · hooks
워크플로우 19개 + docs 스위트 4개 + 기술 스킬 10개 + E2E/Stitch 5개 + 이미지 1개 + 에이전트 12개 + 커맨드 3개 + hooks 보장 시스템 올인원
43 skills · 4 commands · 12 agents · hooks
Ponytail·의도→설계→계획 흐름·auto memory 확장·리드/워커 메모리박스·검증 투표 리뷰를 묶은 Claude Code·Codex·Copilot CLI 공용 개발 하네스. 런타임 의존성 0.
29 skills · 1 command · 3 agents · hooks
14 Karpathy-inspired working methods + 1 methodology router, distilled from his 2023-2026 public X posts and Gists into executable agent skills: agentic-engineering, vibe-to-agentic, autoresearch, llm-simulator, llm-wiki, minimalism, supply-chain-hygiene, understanding-first, idea-files, output-evolution, education-first, system-prompt-learning, practice-environments, meta-reflection. Every skill cites its original source. Unofficial, not endorsed by Andrej Karpathy.
15 skills
Design principles, legendary designers, and historical movements applied to UI work, with agents and workflows for brand identity, design audits, style guides, and premium landing pages.
5 skills · 4 commands · 3 agents
Enforce measurement-driven optimization and reproduce-first debugging. Activates automatically on performance and bug-related queries.
11 skills
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
5 skills · 1 command · 4 agents
LLM application development, prompt engineering, and AI assistant optimization
5 skills · 3 commands · 2 agents
6 skill hygiene tools: health report, auto-fix + prune, value (honest token split + usage), security scan (prompt injection + malicious patterns), discover (search + precheck), swipe (interactive triage).
6 skills
Autonomous software-building workflow with structured review
6 skills
Local-first observability and cost control for Claude Code agents: a zero-token statusline showing context re-read %, savings/optimize reports, and a health check.
5 commands
Ruby version manager detection, authoritative resource map, and test framework reference
3 skills · hooks
Skills for using Build123D - a Python CAD library for creating parametric 3D models with code
2 skills
Create and drive Vibe Seller tasks from your agent over the hosted /api/mcp endpoint.
1 skill · 1 MCP server
Render GLB 3D models to PNG images for visual verification
1 skill
Optimize and post-process GLB/glTF 3D models
1 skill
Hands a Claude Code session off to a fresh one before the context fills: a Haiku-written brief, /clear, and a seed that points the new session at the brief.
Everything for writing and publishing research: paper writing, journal formats, literature review, citations, ideation and figures.
200 skills
Machine learning experiments, training, evaluation and reproducible papers.
200 skills
AI agents, language models, retrieval, evaluation and research papers.
200 skills
Multi-agent orchestration subset: search competing plans and ship one selected repo change through the Suede Thought Graph DAG (suede-graph-flo-xr), coordinate build lanes with quality gates and a signed handoff (suede-agent-teams), route cross-surface work end to end (suede-workflow-skills), and turn AI features into eval specs and acceptance gates (suede-ai-eval).
67 skills