Claude Code skills for Coding
1,036,333 coding skills for Claude Code, Codex, Cursor and other AI coding agents, ranked by trust score. Open a skill to see its security scan and source before you install it, or filter the full registry.
npx vskill@latest install <owner>/<repo>/<skill>
Top 50 Coding skills by trust score
anthropics/claude-cookbooks
Coding · 33,839 stars- anthropics/skills/mcp-builderCertified
anthropics/skills
Coding · 176,809 stars - anthropics/skills/skill-creatorCertified
anthropics/skills
Coding · 176,809 stars - anton-abyzov/anymodel/anymodelCertified
anton-abyzov/anymodel
Coding · 41 stars anton-abyzov/greet-app-demo
Coding- anton-abyzov/greet-elena/greet-elenaCertified
anton-abyzov/greet-elena
Coding - anton-abyzov/hi-anton/hi-antonCertified
anton-abyzov/hi-anton
Coding - anton-abyzov/specweave-umb/hi-antonCertified
anton-abyzov/specweave-umb
Coding - anton-abyzov/specweave/0671Certified
anton-abyzov/specweave
Coding - anton-abyzov/specweave/glossaryCertified
anton-abyzov/specweave
Coding - anton-abyzov/specweave/handoffCertified
anton-abyzov/specweave
Coding · 147 stars - anton-abyzov/specweave/jevCertified
Use Jev or optional OpenAI Decisions for bounded routing, shell-command risk, text screening and failure triage. Use for "jev", "system one", or "classify this".
Coding · 169 stars - anton-abyzov/specweave/reviewCertified
Adversarial review of an increment before it ships, by a fresh context or another model family; every finding cites path:line and is re-verified. Use for "review", "qa", "critique …
Coding · 165 stars - anton-abyzov/specweave/sw-autoCertified
Run a SpecWeave increment unattended until every task is done, then verify and close - the Unattended section of sw-do. Use for "auto mode", "run until done".
Coding · 164 stars - anton-abyzov/specweave/sw-doCertified
Work a SpecWeave increment task by task - claim, implement inside its Files, test, commit, done with evidence - alone, unattended or in lanes, then close. Use for "implement", "con…
Coding · 166 stars - anton-abyzov/specweave/sw-doneCertified
Close a SpecWeave increment - every task done or skipped, specweave verify green, a fresh-context review, then specweave complete. Use for "close it", "we are done", "finish up".
Coding · 166 stars - anton-abyzov/specweave/sw-glossaryCertified
anton-abyzov/specweave
Coding - anton-abyzov/specweave/sw-grill-meCertified
anton-abyzov/specweave
Coding - anton-abyzov/specweave/sw-handoffCertified
Hand work to another tool, account or machine and pick it up there, in two words. Use when the user says "hand off", "hand off all", "out of tokens", "switching accounts" or "pick …
Coding · 166 stars - anton-abyzov/specweave/sw-incrementCertified
Plan work as a SpecWeave increment - one spec.md with Problem, Scope, numbered ACs, Approach and Tasks - before writing code. Use for "plan a feature", "new increment", "let's buil…
Coding · 166 stars - anton-abyzov/specweave/sw-jevCertified
Use Jev or optional OpenAI Decisions for bounded routing, shell-command risk, text screening and failure triage. Use for "jev", "system one", or "classify this".
Coding · 164 stars - anton-abyzov/specweave/sw-projectCertified
Keep a project's goal, decisions, work items, artifacts and briefs portable across AI tools and accounts. Use for project coordination, "project brief", "what is this project about…
Coding · 164 stars - anton-abyzov/specweave/sw-reviewCertified
Adversarial review of an increment before it ships, by a fresh context or another model family; every finding cites path:line and is re-verified. Use for "review", "qa", "critique …
Coding · 166 stars End-to-end corporate and personal tax preparation: data gathering from Xero/bank statements/Gmail/Obsidian/Google Drive, P&L generation, IRS compliance analysis, tax calculation, d…
Coding · 1 stars- anton-abyzov/vskill/agents-md-authorCertified
Bootstrap or update project AI-agent instruction files (AGENTS.md for Codex, CLAUDE.md for Claude Code, or both) from the current project's structure. Triggers on: write AGENTS.md,…
Coding · 2 installs · 47 stars - anton-abyzov/vskill/anton-gridCertified
anton-abyzov/vskill
Coding · 35 stars - anton-abyzov/vskill/appstoreCertified
iOS/macOS app deployment and App Store Connect automation using the `asc` CLI — a lightweight alternative to fastlane. Activates when deploying iOS apps, distributing TestFlight bu…
Coding · 85 installs · 36 stars - anton-abyzov/vskill/blotatoCertified
anton-abyzov/vskill
Coding · 2 installs · 35 stars - anton-abyzov/vskill/existing-skillCertified
anton-abyzov/vskill
Coding · 28 stars - anton-abyzov/vskill/greet-antonCertified
anton-abyzov/vskill
Coding · 46 stars - anton-abyzov/vskill/greet-elenaCertified
This skill should be used whenever the user asks Claude to perform any action, task, or operation — including \"create X\", \"fix Y\", \"run Z\", \"build\", \"edit\", \"search\", \…
Coding · 40 stars - anton-abyzov/vskill/gwsCertified
anton-abyzov/vskill
Coding · 39 stars - anton-abyzov/vskill/handoffCertified
anton-abyzov/vskill
Coding · 45 stars - anton-abyzov/vskill/hello-worldCertified
anton-abyzov/vskill
Coding · 40 stars - anton-abyzov/vskill/hi-atlantisCertified
anton-abyzov/vskill
Coding · 44 stars anton-abyzov/vskill
Coding · 46 starsAfter Effects-style motion graphics for short product promos (15-45 s, vertical or landscape), built as code with HyperFrames + GSAP. Covers a story-first brief, motion grammar (en…
Coding · 48 stars- anton-abyzov/vskill/project-wakeCertified
Manual sweep of a SpecWithCode project after an update, restart or outage: list every thread, continue only work the restart cut off and the app did not continue, never touch work …
Coding · 48 stars - anton-abyzov/vskill/reaCertified
Find out exactly how a feature is implemented in a shipped tool or app you don't have the source for (desktop apps, Electron apps like Claude desktop, native CLIs like Codex, websi…
Coding · 47 stars - anton-abyzov/vskill/scoutCertified
anton-abyzov/vskill
Coding · 6 installs · 36 stars - anton-abyzov/vskill/slack-messagingCertified
anton-abyzov/vskill
Coding · 39 stars - anton-abyzov/vskill/survey-passingCertified
anton-abyzov/vskill
Coding · 39 stars anton-abyzov/vskill
Coding · 37 installs · 46 stars- anton-abyzov/vskill/tax-filingCertified
anton-abyzov/vskill
Coding · 36 stars anton-abyzov/vskill
Coding · 46 stars- cloudflare/skills/agents-sdkCertified
Build, debug, or review Cloudflare Agents SDK applications using the agents package.
Coding · 2,915 stars - cloudflare/skills/wranglerCertified
Run or troubleshoot Wrangler CLI commands in projects that have a wrangler.jsonc, wrangler.json, or wrangler.toml file, including local development, Previews, deployment, and resou…
Coding · 2,888 stars - google/adk-go/grocery-pricesCertified
google/adk-go
Coding · 8,291 stars - google/adk-go/weatherCertified
google/adk-go
Coding · 7,970 stars - google/adk-java/a-bCertified
conflicting skill 1
Coding · 1,740 stars
Common questions
What is a Claude Code skill?
A folder with a SKILL.md file that teaches an agent how to do one job well. Claude Code loads it only when the task needs it. The same format works in Codex, Cursor, GitHub Copilot, Gemini CLI and other agents.
How do I install one?
Run npx vskill@latest install owner/repo/skill. The vskill CLI detects which agents you have and puts the skill where each one looks for it.
Are these skills safe to install?
Every listing shows its security scan results, trust tier and source before you install it. Read them, and see the verification methodology for what the scan checks.
How do I keep AI coding work on track across tools?
Skills teach an agent how to do a job. SpecWeave keeps the spec, task progress and a handoff in git, so you can switch between Claude Code, Codex and other tools mid-task.