Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 870 files from 1 769 authors, of which 62 217 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Set up, harden, audit, or explain a Linux VPS as a Codex App SSH host for Krypton-style agent workflows. Use when the user wants to move Codex or Claude Code work from a local Mac to a VPS, connect Codex App to an SSH host, configure Ubuntu 24.04/devbox tools, clone a repo remotely, run Codex/Claude/tmux/cmux on the VPS, forward ports for localhost testing, or create repeatable founder/builder setup instructions with proof checks.
Find any local business by category and location on Google Maps. Get names, phone numbers, emails, websites, ratings, and hours. Search restaurants, dentists, plumbers, or any service.
Generate qualified B2B leads from Google Maps. Define your ICP, extract matching businesses, score and qualify leads, export ready-to-outreach lists.
Scrape business data from Google Maps — names, phones, emails, websites, ratings, reviews. Extract leads by keyword and location with no coding required.
Write hyper-personalized cold emails to local businesses using their Google Maps data (CSV). Generates AIDA sequences with personalization from ratings, reviews, website, and industry context.
Extract verified business email addresses from Google Maps listings. Find contact emails for any industry and location — ready for cold outreach campaigns.
Analyze Google Maps review data from CSV exports. Sentiment analysis, trend detection, competitor review comparison, and reputation insights — no API key needed.
Analyze local competitors from a Google Maps CSV export. Compare ratings, reviews, digital presence, and positioning. Find market gaps and opportunities without any API calls.
Export Google Maps business data to CSV, JSON, or CRM format (HubSpot, Pipedrive, Salesforce). Bulk export with custom field mapping and filtering.
Generates paste-ready Power Apps Canvas App YAML. Invoke when the user wants to replicate a UI mockup, improve an existing Canvas app screen, or build a new screen from a text description. Also invoke when the user asks to "improve", "redesign", or "generate YAML" for a Canvas app screen.
Rust Code review checklist and decision framework for Rust PRs, derived from rust-best-practices.
Generate or edit raster images through the user's ChatGPT subscription and save or preview workspace PNGs. Use for text-to-image, local-reference generation, edits, follow-up revisions, variants, multi-image batches, or subscription-backed setup in Codex, Claude Code, and compatible local agents. Preserve direct prompts verbatim; develop distinct per-output prompts when the user delegates multiple concepts. Attach actual reference files. Prefer host-native image_gen; otherwise use Codex CLI with ChatGPT sign-in. Never use the Images API, OPENAI_API_KEY, or API-key login.
15维度招标文件解读
智能排版
合规性检查
正文生成(四模式)
Use when refactoring a user-level or project-level CLAUDE.md for progressive disclosure
Use when refactoring a user-level or project-level AGENTS.md for progressive disclosure
Use when the user asks for a blindspot pass or to find their unknown unknowns, or signals unfamiliarity with a domain, tool, or codebase area ("never used X", "first time doing Y", "no idea where to start", "don't know what I don't know") before working there. Turns unknown unknowns into known unknowns so the user can prompt well
Use when the user asks about best practices, gotchas, common pitfalls, or recommended patterns for tools, libraries, config formats, API patterns, or project setup, or when setting up, configuring, choosing, or refining these where outdated guidance causes debugging pain. Also use when the user says "search online", "how should I", or "what's the best way to
Use when making any git commit. Always pass a brief description of what changed as the argument.
(project) Use when refreshing install tasks in playbooks/roles/ against upstream docs — bumping a pinned version, adopting a newly recommended install method, repointing a doc link that moved, or realigning the community.general pin with the brew-installed ansible
(project) Use when editing any file under skills/hal-skills/ or plugins/hal-voice/ to bump the plugin version before committing
Use when the user wants technical or developer writing (docs, issues, READMEs, comments, UI text) drafted or rewritten to be clear and simple for a global audience
Use when creating or editing a skill that uses Bash commands, external tools, or skill invocations and the allowed-tools frontmatter may be incomplete
Find academic papers across up to 7 sources (OpenAlex / Semantic Scholar / CrossRef / PubMed / arXiv for English, plus native-Chinese retrieval via NSSD 国家哲社文献中心 + yiigle 中华医学期刊) with adjustable depth — Quick scan (5 min) to Audit prep (3 hr). Use when the user wants to find papers, run a literature search, gather references, scope a research topic, search Chinese-language / 中文原生 literature (中文文献/中文核心/CSSCI/C刊/国内研究/国内文献/中华××期刊/心理学报/经济研究), or filter results by journal tier (中科院分区/一区/几区, Q1, JCR/SJR quartile, 影响因子/impact factor, 期刊分区, 顶刊/top journal, '按分区筛'). Triggers on search verbs ('find papers', 'literature search', 'papers about X'), review types ('scoping review', 'systematic review', 'SR prep', 'literature review', 'lit review', 'help me write a lit review'), Chinese ('找文献', '找论文', '论文搜索', '学术检索', '文献检索', '文献综述', '综述前期', '求文献', '中文文献', '中文核心', 'CSSCI', 'C刊', '国内研究', '找中文的'). Outputs Shadcn HTML report + BibTeX/RIS/CSV + PRISMA-S log. Do NOT use for: concept explanations ('what is X' / 'X 是什么', e.g. '影响因子怎么算'), writing ('帮我写' / 'help me write a paragraph'), single-paper interpretation or PDF download with metadata (use paper-downloader-portable), or when the user already has a literature set (use literature-set-review).
>- Generate complete urban masterplans with spatial structure, land use distribution, street network, block layout, density strategy, phasing plan, and implementation framework. Use when the user asks to design a masterplan, create an urban layout, develop a neighborhood plan, design a district, plan a new community, lay out a development, structure an urban area, or create a site plan at the urban scale. Also use when the user provides a site and asks for a development proposal, a design concept, or a spatial framework. Handles greenfield, brownfield, and infill development scenarios.
>- Apply climate-specific urban design strategies for hot-arid, tropical, temperate, and cold climates. Covers building orientation, street alignment, shading strategies, wind management, vegetation selection, urban heat island mitigation, stormwater management, and thermal comfort in outdoor spaces. Use when the user specifies a climate zone, asks about climate-responsive design, needs orientation advice, asks about heat island mitigation, discusses thermal comfort, or designs for extreme weather conditions. Also use for microclimate analysis, wind corridor design, or solar access optimization.
>- Generate professional urban design briefs, design reports, and project documentation. Produces structured documents with vision statements, design principles, spatial requirements, performance targets, and implementation guidelines. Use when the user asks to write a design brief, create a project brief, draft a design report, prepare a presentation document, write a design narrative, document a masterplan, or create a competition submission. Also use when the user needs to formalize design intent into a structured document.
>- Evaluate urban designs against comprehensive criteria drawn from all major global standards, certification systems, and theoretical frameworks. Generates detailed scorecards and improvement recommendations. Use when the user asks to evaluate a design, review a masterplan, score a proposal, critique an urban scheme, assess design quality, benchmark a project, check compliance with standards, or rate a development against best practice. Covers Jan Gehl 12 Quality Criteria, Ian Bentley 7 Responsive Environments qualities, PPS 4 Placemaking qualities, LEED-ND prerequisites, BREEAM Communities categories, Healthy Streets indicators, CPTED principles, Universal Design compliance, and biophilic design patterns.
>- Comprehensive mobility and transport planning for urban design including trip generation, mode split targets, street network connectivity, transit planning, cycling network design, pedestrian accessibility, freight and servicing strategy, parking demand management, and traffic impact assessment. Use when the user asks about transport planning, trip generation, mode split, traffic impact, transit catchment, cycling network, pedestrian access, freight servicing, mobility hubs, first-last mile, level of service, vehicle-km traveled, or any movement and accessibility question beyond individual street cross-section design. Also use for transport demand management (TDM), multimodal integration, or mobility frameworks for masterplan transport chapters.
>- Develop land use programs and optimize the mix of uses for urban districts, neighborhoods, and individual buildings. Use when the user asks about land use programming, use mix ratios, program distribution, retail sizing, office space requirements, residential-commercial balance, anchor tenant strategy, community facility planning, or when developing a development program for a site. Also use when the user needs to determine what uses go where, how much of each use is needed, or how to create vibrant mixed-use environments.
>- Design urban blocks and optimize density using typological analysis, FAR calculations, and building configuration strategies. Use when the user asks about block dimensions, block layout, density calculations, FAR optimization, building footprint coverage, height-density relationships, block typologies, perimeter block design, courtyard blocks, tower-podium configurations, or massing studies. Also use when the user needs to understand how many units fit on a site, calculate gross vs net density, or optimize a block plan for daylight and privacy.
>- Estimate construction costs, infrastructure costs, soft costs, and total development costs for urban design projects. Covers building construction cost per m2 by typology, infrastructure cost per linear meter and per dwelling, site preparation, landscaping, professional fees, and financial feasibility analysis. Use when the user asks about project cost, construction cost, infrastructure budget, development feasibility, cost per unit, cost per m2, capital expenditure, opex, cost benchmarking, value engineering, phasing costs, or any question about how much an urban design project or its components will cost. Also use for preliminary budget estimation, order-of- magnitude costing, cost comparison between design alternatives, or cost optimization of masterplans.
>- Conduct comprehensive multi-scale site analysis from regional to neighborhood to site scale. Generates structured analysis reports covering physical context, infrastructure, demographics, environmental conditions, regulatory framework, and design opportunities and constraints. Use when the user asks to analyze a site, understand site context, assess a location for development, conduct due diligence on a parcel, evaluate site conditions, create a site analysis report, or study the urban context of a project area. Covers topography, hydrology, vegetation, solar and wind analysis, noise mapping, infrastructure audit, zoning review, circulation analysis, visual assessment, SWOT analysis, and stakeholder mapping.
>- Score urban designs against LEED-ND, BREEAM Communities, WELL Community Standard, Green Star Communities, CASBEE Urban Development, and Estidama Pearl Community Rating System. Generates detailed scoring reports with credit-by-credit analysis, achievability assessment, and optimization recommendations. Use when the user asks to score a design for sustainability, assess LEED-ND credits, evaluate BREEAM compliance, check WELL community criteria, calculate a sustainability rating, or optimize a design for green certification.
>- Design parks, plazas, waterfronts, pocket parks, civic spaces, playgrounds, and urban gardens using Jan Gehl quality criteria, PPS placemaking methodology, and global best practices. Use when the user asks to design a park, create a plaza, plan a waterfront, design a civic space, lay out a playground, plan a community garden, create an outdoor gathering space, design a public realm strategy, or improve an existing public space. Also use when discussing public space programming, activation strategies, or landscape design at the urban scale.
>- Research and analyze urban design precedents systematically. Generates structured case study reports with quantitative metrics, design principles, lessons learned, and transferability assessment. Use when the user asks for precedents, case studies, reference projects, comparable developments, benchmarks from other cities, examples of similar projects, or best practice examples. Also use when the user names a specific urban project and wants it analyzed as a precedent.
>- Design complete streets with proper cross-sections, lane allocation, pedestrian and cycling infrastructure, intersection design, and streetscape elements using NACTO and global standards. Use when the user asks to design a street, create a cross-section, determine road width, design an intersection, plan a bike lane, design a sidewalk, create a boulevard, design a shared street, plan traffic calming, or specify streetscape elements. Also use for street hierarchy classification, right-of-way allocation, or any question about street dimensions and standards.
>- Design transit-oriented developments using ITDP TOD Standard, global best practices, and density-distance gradient principles. Use when the user asks to design around a transit station, create a TOD plan, optimize development near transit, plan a transit district, design a station area, or develop around a metro stop, BRT station, tram stop, or rail station. Also use when discussing walk catchments around transit, density gradients from stations, or first-last mile connectivity.
>- Python computational tools for urban design metric calculations including density, FAR, walkability scoring, parking requirements, green space analysis, and block optimization. Use when the user asks to calculate density, compute FAR, score walkability, determine parking requirements, analyze green space provision, optimize block dimensions, run urban metrics, or perform any quantitative urban design calculation. Also use when precise numbers are needed for any urban design metric rather than rules of thumb.
>- Comprehensive urban design knowledge base containing theories, principles, quantitative standards, and rules of thumb from 40+ theorists and global frameworks. Provides foundational knowledge for all urban design tasks including masterplanning, site analysis, street design, public space design, density calculations, and sustainability assessment. Automatically activates whenever the conversation involves urban design, city planning, urban morphology, placemaking, walkability, transit-oriented development, mixed-use development, zoning, building typologies, streetscapes, public realm, neighborhood design, district planning, or any AEC topic at the urban scale. Covers Kevin Lynch, Jane Jacobs, Christopher Alexander, Jan Gehl, Gordon Cullen, Camillo Sitte, Andres Duany, Leon Krier, Ian Bentley, New Urbanism, Smart Growth, Complete Streets, 15-Minute City, Space Syntax, CPTED, and all major sustainability certifications.
>- Analyze zoning regulations and generate form-based codes, including Euclidean zoning analysis, performance zoning parameters, transect-based coding, building envelope controls, and development standard specification. Use when the user asks about zoning, building codes, development standards, setbacks, height limits, FAR regulations, use permissions, overlay zones, special districts, or form-based codes. Also use when the user needs to create a zoning framework for a masterplan, understand what can be built on a site, or translate a design into regulatory language.
>- Urban regeneration, brownfield redevelopment, heritage-led renewal, and neighborhood revitalization strategies. Covers site remediation assessment, adaptive reuse frameworks, catalyst project design, gentrification risk management, community engagement methodology, incremental urbanism, and phased delivery of regeneration programs. Use when the user asks about brownfield development, urban renewal, regeneration strategy, adaptive reuse, heritage-led regeneration, gentrification, community-led development, vacant land strategy, post-industrial redevelopment, waterfront regeneration, neighborhood decline, blight remediation, infill development, meanwhile use, temporary urbanism, or revitalizing an existing urban area. Also use for regeneration feasibility, stakeholder engagement in regeneration projects, or comparing regeneration approaches.
Run Claude Code (Anthropic) from this host via the `claude` CLI (Agent SDK) in headless mode (`-p`) for codebase analysis, refactors, test fixing, and structured output. Use when the user asks to use Claude Code, run `claude -p`, use Plan Mode, auto-approve tools with --allowedTools, generate JSON output, or integrate Claude Code into Clawdbot workflows/cron.
Reverse-engineer architecture from an existing codebase to create ADRs documenting discovered decisions. Use when bootstrapping architecture documentation for brownfield projects.
Analyze architecture for consistency between ADRs and AD, completeness, and quality issues. Use when validating generated or refined architecture artifacts, before feature development, during architecture review, or periodically to detect drift.
Interactive PRD exploration and system-level ADR creation for greenfield projects. Use when transforming a PRD or high-level system description into Architecture Decision Records.
Analyze evaluation results and close the loop. Specification failures create local CDRs to fix agent rules; generalization failures go to evaluator backlog.
Refine, cluster, and accept draft criteria into the published goldset. Isolates 20% holdout split and publishes goldset.md + goldset.json.
Refine and validate system-level ADRs through targeted clarification questions. Use when ADRs need review, gaps need filling, or ADR status must be approved before architecture generation.
Generate a full Architecture Description (AD.md) from accepted ADRs using multi-agent DAG orchestration. Use when accepted ADRs exist and you need to produce or update unified architecture documentation.
Generate executable graders and configs from goldset. Generates Python graders / metrics and auto-runs unit tests to verify grader correctness.
Initialize evals/{system}/ directory structure for evaluation system following EDD principles (Standalone). Choose PromptFoo or DeepEval based on tech stack, generate security baseline.
Extract eval criteria from product specs and production failure traces (bottom-up error analysis). Writes proposed criteria to .adlc/drafts/evals/.
Review, accept, reject, or defer Context Directive Records (CDRs) discovered by levelup-init or proposed by levelup-specify. Interactive one-CDR-at-a-time workflow.
Reverse-engineer Context Directive Records (CDRs) from an existing codebase for contribution to team-ai-directives. Use when bootstrapping team knowledge from brownfield projects.
Compile accepted Context Directive Records (CDRs) into team-ai-directives artifacts and create a draft PR. Builds context modules, evals goldensets, and/or skills based on CDR context types.
Extract Context Directive Records (CDRs) from the current session after completing work. Identifies reusable patterns (rules, personas, examples, evals) and captures directive compliance cases for team-ai-directives.
Run evaluations and validate evaluator quality (SLA compliance, TPR/TNR, statistical accuracy). Executes PromptFoo or pytest DeepEval.
Claude Skills — questions
Answers built from the skills we actually parsed.