Shelves Architecture & codebase
Setup & scaffolding
5,913 rows from 1,733 repositories
Getting a project to the point where work can start.
What Setup & scaffolding skills agree on
1,967 skill files read, by 1,553 of the 3,091 authors on this shelf whose files we hold, 2026-09-06
The middle one of the 171 measured here is ~1.6k tokens long, counted with cl100k_base
Counted by distinct author, so one author publishing three of these counts once. Where a claim sits in fewer files than authors, that is said: a claim held by forty authors across three files is one file people copied, not forty people who agreed. Near-identical wordings are grouped and the other wordings are shown, so the grouping is yours to check.
What they tell the agent to do
- Write the configuration file36 of 1553also worded as Write configuration file; Create the configuration file
- Create the directory structure35 of 1553 in 33 filesalso worded as Create the directory structure; Create the folder structure
- Verify the setup31 of 1553 in 28 filesalso worded as Verify the installation; Verify installation
- Run the setup script30 of 1553 in 29 filesalso worded as Run cluster setup script; Run the installer script
- Pre-determine the required sample size29 of 1553 in 12 filesalso worded as Pre-determine sample size; Pre-determine the sample size
- Check if the configuration already exists29 of 1553also worded as Check if configuration file exists; Read existing config if it exists
- Document every test26 of 1553 in 10 filesalso worded as Document every test with hypothesis and results; Document every test completely
- Start with a hypothesis26 of 1553 in 11 filesalso worded as Start with a clear hypothesis; Start with a specific hypothesis
- Ask one question at a time22 of 1553also worded as Ask one focused question at a time; Ask questions one at a time
- Test a single variable per test21 of 1553 in 9 filesalso worded as Test a single variable per experiment; Test a single variable
- Read product marketing context before asking questions19 of 1553 in 8 filesalso worded as Read product marketing context first; Check for product marketing context first
- Do not peek and stop early18 of 1553 in 7 filesalso worded as Do not peek at results and stop early; Do not stop tests early
- Validate configuration before deploying17 of 1553 in 14 filesalso worded as Validate configuration; Validate configuration before applying changes
- Generate CLAUDE.md17 of 1553also worded as Generate CLAUDE md; Generate or update CLAUDE.md
- Define primary, secondary, and guardrail metrics16 of 1553 in 5 filesalso worded as Define primary secondary and guardrail metrics; Define primary and secondary metrics
What they tell it not to do
- Do not overwrite existing files102 of 1553also worded as Never overwrite existing files; Never overwrite existing files without asking
- Do not make changes to variants mid-test33 of 1553 in 14 filesalso worded as Do not make changes to variants; Avoid changing things mid-test
- Do not peek at results and stop early28 of 1553 in 11 filesalso worded as Do not peek at results and stop early; Don't peek and stop early
- Never commit secrets20 of 1553also worded as Do not commit secrets; Never commit secrets to git
- Never commit .env files20 of 1553 in 14 filesalso worded as Do not commit .env files; Do not commit .env to git
- Never invent a plausible entry to fill a field18 of 1553 in 17 filesalso worded as Do not invent a plausible entry to fill a field; Do not invent a plausible entry
- Do not add traffic from new sources18 of 1553 in 9 filesalso worded as Do not add new traffic sources; Do not add traffic from new sources mid-test
- Do not ignore errors14 of 1553 in 5 filesalso worded as Do not ignore errors; Don't ignore errors
- Never create AGENTS.md when CLAUDE.md already exists14 of 1553also worded as Do not overwrite existing CLAUDE.md files.; Never create AGENTS.md when CLAUDE.md exists
- Do not use absolute paths13 of 1553 in 7 filesalso worded as Do not use hardcoded absolute paths; Do not use absolute paths in manifest component paths
What they expect to be installed
- git318 of 1553
- bash176 of 1553
- python3144 of 1553
- npm144 of 1553 in 143 files
- node134 of 1553
- curl120 of 1553
- gh110 of 1553
- npx107 of 1553
- grep94 of 1553
- AskUserQuestion84 of 1553
What they ask it to produce
- CLAUDE.md177 of 1553also worded as ~/.claude/CLAUDE.md; CLAUDE.local.md
- AGENTS.md81 of 1553also worded as AGENTS.md files; AGENT.md
- .gitignore52 of 1553also worded as gitignore; .dockerignore
- config.json51 of 1553also worded as config json; tsconfig.json
- README.md46 of 1553also worded as README; docs/README.md
- .claude/settings.json39 of 1553also worded as .claude/settings.local.json; ~/.claude/settings.json
- config.yaml35 of 1553also worded as config.yml; drconfig.yaml
- settings.json30 of 1553also worded as settings.local.json; settings local json
When Setup & scaffolding authors say to reach for one
The situations these authors wrote into their own files, counted out of the same 1,553 authors, with the skills that name each one
- Starting a new project31 of 1553 in 29 files
- Survey
- Init
- New project
- Harness init
- Init project
- Code scaffolder
- and 28 more on this shelf
- Setup27 of 1553 in 26 files
- Setup
- Harness setup
- Dev init
- Dotnet init
- Extracting design system
- Eval check
- and 20 more on this shelf
- Scaffold27 of 1553 in 24 files
- Dev init
- Scaffold
- Dr init
- Scaffold project
- Agentic skeleton dir structure
- Oci project
- and 22 more on this shelf
- User says setup24 of 1553
- Ads start
- Project conventions
- Setup
- Cloud setup
- Specsmith init
- Workspace setup
- and 16 more on this shelf
- A/B test23 of 1553 in 9 files
- Ab test setup
- and 31 more on this shelf
- Test this change mentioned21 of 1553 in 9 files
- Ab test setup
- and 29 more on this shelf
- Split test mentioned20 of 1553 in 8 files
- Ab test setup
- and 28 more on this shelf
- Experiment mentioned20 of 1553 in 8 files
- Ab test setup
- and 28 more on this shelf
How Setup & scaffolding skills are built
5,431 skill directories by 1,614 authors, read from their repositories’ own file trees 2026-08-05
The middle bundle among those shipping files is 4 files, 12.8 KB beside SKILL.md
Counted by distinct author, same as above, so one author publishing forty template copies counts once. SKILL.md itself is not counted as a file, so a single-file skill is one where that file is the whole skill.
The shape
- SKILL.md is the whole skill622 of 1,614 authors, 2,447 of 5,431 skills
- files ship beside it992 of 1,614 authors, 2,984 of 5,431 skills
- executable scripts ship inside395 of 1,614 authors, 1,084 of 5,431 skills
The folders they converge on
- references/586 of 1,614 authors, 1,488 of 5,431 skills
- scripts/286 of 1,614 authors, 916 of 5,431 skills
- agents/169 of 1,614 authors, 283 of 5,431 skills
- assets/148 of 1,614 authors, 481 of 5,431 skills
- templates/111 of 1,614 authors, 174 of 5,431 skills
- evals/84 of 1,614 authors, 201 of 5,431 skills
microsoft/azure-skills/.github/plugins/azure-skills/skills/airunway-aks-setup Skill
1,405★ repoOfficial agent plugin providing skills and MCP server configurations for Azure scenarios.
AI-Builder-Club/skills/skills/crabbox-setup Skill
no license1,191★ repoCodebase harness + loop engineer
bevibing/tutor-skills/skills/tutor-setup Skill
1,108★ repoA Claude Code skill that turns PDFs, docs, and codebases into Obsidian study vaults
alibaba/skill-up/skills/skill-upper Skill
659★ repoAn evaluation and evolution tool for Agent Skills.
SponsioLabs/Sponsio/plugins/sponsio-claude-code/skills/configure Skill
445★ repoDeterministic safety solutions for probabilistic AI agents
shinpr/mcp-local-rag/io.github.shinpr/mcp-local-rag MCP server
360★ repoEasy-to-setup local RAG server with minimal configuration
aerovato/container/skills/container Skill
332★ repoSafely run OpenCode, Codex, Claude Code with full permissions.
lifedever/claude-rules/.claude/skills/init-rules Skill
189★ repoCoding standards for AI coding assistants. Auto-detect tech stack, generate project rules. Works with Claude Code, Cursor, Antigravity, GitHub Copilot.
AElfProject/aelf-skills Skill
no license184★Unified aelf skills hub for discovery, routing, bootstrap, and health checks across OpenClaw, Codex, Cursor, and Claude Code.
XBuilderLAB/cheat-on-skill/skills/skill-init Skill
174★ repo帮你在 AI 时代找到一份高薪 × 你学得动 × 不会被 AI 吃掉的工作，并给出个性化学习陪跑计划。能力匹配 + 可学性闸门 + BOSS 直聘真实招聘数据 + 反诈。
goSprinto/compliance-skills/gdpr-compliance-checker Skill
130★ reposendaifun/skills/skills/arcium Skill
127★ repoa public marketplace of all solana-related skills for agents to learn from!
jinzhezenggroup/computational-chemistry-agent-skills/.github/skills/create-skill Skill
125★ repoAgent skills to run computational-chemistry tasks, used in OpenClaw
RayFernando1337/rayfernando-skills/plugins/bootstrap-ios/skills/bootstrap-ios Skill
124★ repoRay Fernando's collection of Skill files for AI coding agents. First up: running-bug-review-board, a real-user QA workflow with a Bug Review Board (BRB) feedback loop.
incogbyte/android-reverse-engineering-claude-skill/plugins/android-reverse-engineering/skills/android-reverse-engineering Skill
106★ repoClaude Code skill that automates Android application reverse engineering
gogf/skills/skills/goframe-v2 Skill
no license78★ repoGoFrame Agent Skills empowering AI to deeply understand GoFrame conventions and best practices, generating high-quality, production-ready code.
michtio/craftcms-claude-skills/skills/craft-cloud Skill
77★ repoProduction-ready Claude Code skills, agents, and project templates for Craft CMS 5 development
001TMF/harness-forge/skills/meta-harness Skill
76★ repoTurn Claude Code into its own Meta-Harness — a skill that evolves the scaffolding around a fixed model (memory, retrieval, context, prompts) via a native propose→score→Pareto loop. Native reimplementation of Meta-Harness (Lee et al. 2026).
ronnythedev/dotnet-clean-architecture-skills/cli/dist/skills/01-dotnet-clean-architecture Skill
no license69★ repo27 AI-ready skills for generating production-grade .NET code — Clean Architecture, CQRS, DDD. Works with Claude Code, GitHub Copilot, and Cursor.
vanillaflava/llm-wiki-skills/wiki-config Skill
59★ repoTurn your markdown vault into a compounding knowledge wiki (Karpathy inspired). Six agent skills - knowledge grows with every conversation. Works with Obsidian, Logseq, etc. or just folders on your local drive. Compiled memory for your LLM sessions. Crossplatform. GUI install on Claude Desktop, no terminal, no code.
lensesio/agentic-engineering-for-apache-kafka/skills/kafka-connector-review Skill
56★ repoAI agent skills for building, operating and troubleshooting Apache Kafka applications. Topic audit, consumer lag, schema review, security, connectors and DLQ
tdimino/claude-code-minoan/skills/core-development/agents-md-manager Skill
41★ repoA curated ~/.claude/ configuration for professional development workflows — 90+ skills, 46 hooks, and CLI tools
siddik-web/wp-block-theme-converter Skill
41★A Claude skill for converting any HTML/CSS/JavaScript project into a production-ready WordPress Block Theme (Full Site Editing).
Agronomic experiment design starter
ma-compbio-lab/SkillFoundry/skills/agriculture-food-and-plant-science/agronomic-experiment-design-starter Skill
36★ repoA framework for discovering, compiling, and validating reusable skills for scientific agents.
pumblus/okf-harness/packages/agent-pack/templates/okf-harness-bootstrap Skill
32★ repoAgent-first local harness for OKF-compatible LLM Wikis.
ankraft/ACME-oneM2M-CSE/skills/acme-cse Skill
30★ repoAn open source CSE Middleware for Education.
zebbern/skills/claude-code-project Skill
no license29★ repoHigh-quality Agent Skills made to perform reliably in real workflows
michellemayes/meta-doctor/plugins/meta-doctor/skills/add-doctor-runbook Skill
29★ repoMost monitoring tells you something broke. A doctor opens the pull request that fixes it.
ptsilivis/autonomousguy/skills/autosar/autosar-bsw Skill
26★ repoAutonomousGuy — AI skill prompts for embedded automotive engineers (AUTOSAR, MISRA, ISO 26262, ECU)
SebGalina/betaflight-claude-skill Skill
no license24★Claude skill for Betaflight: FPV drone configuration, PID tuning, log analysis, and troubleshooting.
anliberant/obsidian-ai-setup Skill
no license24★Bootstrap a fully personalized Obsidian vault with AI. Interactive onboarding, document ingestion, and automatic knowledge base generation for Claude Code and compatible AI agents.
ai4curation/curation-skills/ai4curation-configuration Skill
no license24★ repoClaude skills for a variety of curation and knowledge-based tasks. We currently have 3 skills included, but intend to grow this.
ShulkwiSEC/bb-huge/skills/bb-huge Skill
21★ repobb-huge 🤗 , Personal bug bounty findings hub and bug bounty orchestration for multiple agents
galyarderlabs/galyarder-framework/integrations/antigravity/ab-test-setup Skill
20★ repoThe framework that powers your Agentic Company
rudderlabs/rudder-agent-skills/plugins/rudder-cli/skills/rudder-cli-setup Skill
18★ repoClaude Code plugin marketplace & agent skills for RudderStack — instrument events, design tracking plans & data graphs, write transformations, build Profiles, and drive the CLI, MCP server, and Terraform provider from Claude Code, Cursor, and 40+ AI agents.
livlign/claude-skills/plugins/dotnet-coverage-kit/skills/coverage-init Skill
18★ repoA Claude Code plugin marketplace for open-source maintainers — README heroes, README audits, and .NET test-coverage backfills.
powersync-ja/agent-skills/skills/powersync Skill
18★ repoOfficial agent skills for PowerSync
ombulabs/claude-code_rails-load-defaults-skill/rails-load-defaults Skill
17★ repoA Claude Code Skill to help upgrade the Rails defaults
claudius-ars/embedded-agent-skills/embedded-agent-skills/gpio-config Skill
16★ repolistfold/botfile/examples/botfile_example/botfile/skills/bootstrap-botfile Skill
16★ repoThis is a mirror, active development happens on codeberg: https://codeberg.org/botfile/botfile
stablyai/agent-skills/skills/github-actions-setup Skill
no license16★ repoAI agent skills for the Stably Playwright SDK.
jackchuka/skills/claude-permissions-audit Skill
15★ repoA lazy engineer's toolkit — why do it yourself when a Skill can?
jame581/LogseqBrain/skills/brain-doctor Skill
15★ repoPersistent memory for Claude using a dedicated Logseq graph. Save and load project context, decisions, and progress across sessions and devices.
ajmeese7/hermes-multi-user-skill/hermes-multi-user Skill
no license14★ repoEnable multiple Hermes Agent personalities, cementing OpenClaw feature parity.
SoulKyu/openwiki-cc/.agents/skills/openwiki Skill
no license14★ repoAuto-generate and maintain a documentation wiki for any repo — native Claude Code plugin (/openwiki:wiki) & OpenAI Codex skill. A faithful port of OpenWiki: grounds every doc in your source & git history, updates only what changed.
aborroy/aiup-alfresco/.cursor/skills/aca-extension Skill
13★ repoA Claude Code plugin that packages Alfresco extension development as slash commands, skills, and agents
unlayer/unlayer-skills/unlayer-config Skill
13★ repoAI skills for integrating the Unlayer drag-and-drop editor. Install with: npx skills add unlayer/unlayer-skills
adisinghstudent/ara.so/skills/openclaw-config Skill
no license13★ repoOpenClaw operations skill for AI agents — 1.5K installs on skills.sh
mirkobozzetto/arsenal/plugins/code-roadmap/skills/code-roadmap Skill
12★ repoMirko Bozzetto's curated skills for AI coding agents (Claude Code, Codex, Cursor, ...)
elb-pr/claudikins-automatic-context-manager/skills/acm-config Skill
12★ repoClaudikins Automatic Context Manager - seamless context handoff for Claude Code
eugenepyvovarov/mcpbundler-agent-skills-marketplace/ab-test-setup Skill
12★ repoagent skills marketplace for mcp bundler(can be used with other ai tools with support of agent skills markeplaces). some skills are mine, also borrowed skills(credited to authors)
labeveryday/claude-put-in-work/.claude/skills/autonomous-build Skill
11★ repoThis is a repo used to make claude put in work autonomously.
NovaCode37/claude-security-skills/skills/cors-auditor Skill
11★ repoProduction-ready Claude Code skills for cybersecurity — secret scanning, SAST, prompt-injection testing, HTTP/JWT/dependency auditing. Zero dependencies.
dashaworks/report-skills Skill
11★Claude Code & Codex skills for AI reports, decks and client sharing: publish agent-made research as live tracked web reports, recurring client reports, view-tracked proposals and slide decks via the ReportRoom MCP. Beautiful by default, analytics back to the agent.
qiaomiaojoe/ai-academic-workflow/skills/academic-project-init Skill
no license10★ repoAI学术工作流 · 乔淼PhD「AI学术训练营」skills 库：选题 / 文献搜索 / 文献分析 / 研究设计 / 数据分析 / 全文初稿，30 个 skills 拆到步骤颗粒度，单个可独立运行、可自由组合（Claude Code / Codex）
monthu56/landforge/.claude/skills/init-landing-system Skill
10★ repoStatic landing-page generation system built on Claude Code skills — SEO, A/B testing, analytics, deploy and change-audit built in.
0x-Professor/Agent-Skills-Hub/skills/agentic-mcp-server-builder Skill
10★ repoPublic skill pack for AI coding/automation/penetration-testing agents.
exasol-labs/exasol-agent-skills/plugins/exasol/skills/exasol-ai-setup Skill
10★ repoExasol skills for AI agents. Optimized for Claude Code and OpenAI Codex 🤖
Power automate action configuration
Wals-pro/claude-power-automate/skills/power-automate-action-configuration Skill
10★ repoA Claude Code suite for Microsoft Power Automate development — Agent Skills + a local CLI (Dataverse/Power Platform APIs, Azure CLI auth, no stored secrets). Beta.
s3onghyun/otelcol-doctor Skill
8★A Claude Code skill that writes, fixes, and validates OpenTelemetry Collector configs — processor order, core-vs-contrib, pull-vs-push exporters, the works.