Explore skills
Showing 71101–71130 of 71536 skills
Tests whether a repository's README actually works by cloning the repo into a throwaway directory (optionally a clean Docker machine) and following the setup instructions exactly like a brand-new user would, running every command for real and timing it. Produces a step-by-step pass/fail report with "time to first run", a list of concrete README improvements with evidence ("add X because…", "remove Y because…"), checks translated READMEs for drift, then walks the user through each fix one at a time and can open a pull request. Use this whenever the user asks to check, test, verify, audit or improve a README, getting-started guide, installation docs or onboarding instructions; whenever they say things like "does my README still work", "would a new contributor get stuck", "my install docs are probably outdated", "someone opened an issue saying setup fails" or "clean up the README"; and before a release or open-sourcing a project. Trigger even if the word README is not used but the request is about whether setup/installation instructions are accurate.
vSkyfall/fresh-clone
Stars: 1Claude CodeCodexGenerate production-ready Claude Code hooks with interactive Q&A, automated installation, and enhanced validation. Supports 10 templates across 7 event types for comprehensive workflow automation.
alirezarezvani/claude-code-skill-factory
Stars: 904Claude CodeCodexPython scripting with uv and PEP 723 inline dependencies. Use when creating standalone Python scripts with automatic dependency management.
ComeOnOliver/skillshub
Stars: 67Claude CodeCodexThis skill should be used when deploying or debugging a self-hosted OpenClaw (formerly Clawdbot/Moltbot) agent gateway — a Node.js personal-assistant service bridging Telegram/WhatsApp/Discord to an LLM with tool/skill access. Covers install, secure baseline config (loopback bind, token auth, exec approval gating), the two non-obvious config traps that silently break things (model selection vs. API key, exec security vs. ask), Telegram channel lockdown, configuring the web_search tool/Brave provider, voice-note transcription (tools.media.audio/Groq), memory indexing and its embedding-provider auth (openclaw memory index/status), evaluating ClawHub skills/plugins by real usage data, and building trustworthy custom skills instead of pulling from the unvetted ClawHub marketplace. Trigger phrases include "openclaw config", "openclaw gateway", "tools.exec.security", "openclaw model not found", "ProviderAuthError No API key found for provider openai", "exec denied security=deny", "openclaw dashboard", "openclaw pairing", "ClawHub skill", "openclaw skills install local", "openclaw web search", "tools.web.search.provider", "web_search provider is not available", "openclaw plugins install clawhub", "plugins.allow is empty", "tools.media.audio", "voice memo transcription", "openclaw skills search --json", "ClawHub popular skills", "EXTERNALLY-MANAGED pip openclaw", "AgentMail openclaw", "clawdbot paths in skill", "openclaw memory index", "memorySearch.provider", "memory index failed no api key", "credit_balance_exhausted", "insufficient_quota embeddings", "memory index --force", "scoped sudo for openclaw agent", "dispatch script security boundary", "openclaw agent --message-file", "openclaw agent --session-key timeout", "brief openclaw on new capabilities", "openclaw treats primer as prompt injection", "openclaw session jsonl toolCall", "arm olu with new tools", "expand openclaw agent privilege incrementally", "skill_workshop", "openclaw agent rejects everything as injected",
jackson2w/claude-code-skills
Stars: 1Claude CodeCodexThis skill should be used when a Prometheus + Grafana stack has metrics being scraped but no real alerting configured, when adding a new Grafana alert rule via provisioning-as-code (not the UI), when checking whether Prometheus alert rules actually exist versus assuming a monitoring stack alerts on its own, when detecting individual systemd service failures across a fleet without building a custom OnFailure-to-webhook mechanism, or when a Grafana alert rule needs testing end-to-end before trusting it. Also use it when a disk/filesystem alert rule is green over something that is actually filling up, when a mounted volume has no `node_filesystem_*` series at all, or when a scrape target goes DOWN after a host changes address. Trigger phrases include "prometheus has no alert rules", "grafana provisioning alert rules", "node_systemd_unit_state", "grafana rules.yaml", "alert on systemd unit failure", "grafana noDataState", "test grafana alert rule firing", "prometheus /api/v1/rules empty", "node_exporter systemd collector", "node_exporter not showing /mnt", "no metrics for mounted volume", "mount-points-exclude", "collector.filesystem.mount-points-exclude", "datastore has no disk metrics", "alert green but disk full", "filesystem collector skipping mount", "disk space rule never fires", "scrape target DOWN after IP change", "pin scrape target to hostname not IP".
jackson2w/claude-code-skills
Stars: 1Claude CodeCodexThis skill should be used when adding DNS-over-TLS (DoT) as a Pi-hole upstream resolver, when evaluating cloudflared for DoT/DoH proxying, when a "no fallback DNS" or "DNS failures should surface" constraint needs to coexist with wanting resilience against a recursive resolver (e.g. Unbound) going down, when pihole-FTL --config dns.upstreams rejects an unquoted value as invalid JSON, or when designing an alerted (not silent) failover watcher for infrastructure that must not silently mask its own failures. Trigger phrases include "cloudflared proxy-dns", "cloudflared DoT deprecated", "pihole DNS over TLS", "stubby DoT", "pihole-FTL --config dns.upstreams", "dns.upstreams invalid JSON", "Unbound fallback resolver", "no fallback DNS constraint", "alerted failover watcher", "silent fallback DNS", "pihole upstream failover", "Quad9", "Unbound forward-zone DoT", "forward-tls-upstream", "switch Unbound from recursive to forwarding", "tls-cert-bundle certificate verify failed", "unbound reload vs restart", "serve-expired hides an upstream outage", "FTLCONF_dns_upstreams read-only", "docker Pi-hole upstream".
jackson2w/claude-code-skills
Stars: 1Claude CodeCodexExpert SurrealDB 3 architect and developer skill. SurrealQL mastery, multi-model data modeling (document, graph, vector, time-series, geospatial), schema design, security, deployment, performance tuning, SDK integration (JS, Python, Go, Rust), Surrealism WASM extensions, and full ecosystem (Surrealist, Surreal-Sync, SurrealFS). Universal skill for 30+ AI agents.
baneeishaque/ljt-520_openclaw-backup
Stars: 0Claude CodeCodexInitialize and configure OpenClaw agent workspace MD files (AGENTS.md, SOUL.md, IDENTITY.md, USER.md, TOOLS.md, BOOTSTRAP.md, HEARTBEAT.md). Use when: setting up a new agent, customizing agent personality/behavior, configuring agent workspace, or checking/fixing agent environment (Python/uv). Provides interactive interview workflow before generating files. Supports both container and external (host) OpenClaw instances.
shivamchopra7/claude-skill-directory
Stars: 0Claude CodeCodexManage and develop AI agents using kubani CLI. Use for checking agent health, versions, deployment status, running tests, evaluations, and managing Nexus proactive background missions.
shivamchopra7/claude-skill-directory
Stars: 0Claude CodeCodexUse when building a feature, refactoring, fixing a complex bug, changing architecture, or starting any non-trivial coding task. 12-stage verified dev workflow from research to deploy.
artemiimillier/bulletproof
Stars: 155Claude CodeCodexConfigure, extend, or contribute to Hermes Agent.
aboylabs/ai-agent-skills
Stars: 15Claude CodeCodexKnowledge comics (知识漫画): educational, biography, tutorial.
aboylabs/ai-agent-skills
Stars: 15Claude CodeCodexHimalaya CLI: IMAP/SMTP email from terminal.
aboylabs/ai-agent-skills
Stars: 15Claude CodeCodexGitHub auth setup: HTTPS tokens, SSH keys, gh CLI login.
aboylabs/ai-agent-skills
Stars: 15Claude CodeCodexReview PRs: diffs, inline comments via gh or REST.
aboylabs/ai-agent-skills
Stars: 15Claude CodeCodexCreate, triage, label, assign GitHub issues via gh or REST.
aboylabs/ai-agent-skills
Stars: 15Claude CodeCodexGitHub PR lifecycle: branch, commit, open, CI, merge.
aboylabs/ai-agent-skills
Stars: 15Claude CodeCodexClone/create/fork repos; manage remotes, releases.
aboylabs/ai-agent-skills
Stars: 15Claude CodeCodexAxolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).
aboylabs/ai-agent-skills
Stars: 15Claude CodeCodexSearch arXiv papers by keyword, author, category, or ID.
aboylabs/ai-agent-skills
Stars: 15Claude CodeCodexX/Twitter via xurl CLI: post, search, DM, media, v2 API.
aboylabs/ai-agent-skills
Stars: 15Claude CodeCodex"Debug and harden production LLM prompts — handle prompt injection, output format drift, instruction forgetting in long contexts, and cross-model portability issues. Use this skill when the user ships an LLM-powered feature to production and needs to diagnose why outputs are inconsistent, unsafe, or regressed after model updates — NOT for basic 'write a better prompt' questions.".
charlieviettq/awesome-agent-skill
Stars: 27Claude CodeCodexSpeed-optimized offensive checklist for rapid assessment: quick-win vulnerability patterns, fast recon shortcuts, automated scanner configurations, and triage shortcuts. Use for time-boxed assessments, CTF-speed engagements, or initial rapid surface mapping.
ajtazer/heckit
Stars: 2Claude CodeCodexHeroUI v3 React component library (Tailwind CSS v4 + React Aria). Use when building UIs with HeroUI — creating Buttons, Modals, Forms, Cards; installing @heroui/react; configuring dark/light themes with oklch variables; or fetching component docs. Keywords: HeroUI, Hero UI, heroui, @heroui/react, @heroui/styles.
NarixHine/uni-chem
Stars: 0Claude CodeCodexRun the shotgun handoff system in this project, so any agent can resume work another one stopped. Use for setting up the handoff files in a new project, taking over queue work from another agent or another session, saving progress before a new chat, archiving a finished round of work, reporting queue status, or updating shotgun. Triggers on "shotgun", "set up handoff", "continue the queue", "save before a new chat", "finish this round", "what is next in the plan", "take over this project".
adamalshoomary/shotgun
Stars: 2Claude CodeCodexEvery product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production.
Ronak1167/aura-vega-tv
Stars: 0Claude CodeCodexACTIVATE THIS SKILL FOR ANY SHELL COMMAND OR FILE READ. Check curl, wget, rm, sudo, apt, dpkg, chmod, dd, format, powershell, bash, sh. Check pipe patterns like | sh or | bash. Check shell wrappers like bash -c, xargs, find -exec. Check cloud CLI (aws, gcloud, kubectl, terraform). Check when user says sysadmin told me, Stack Overflow says, is this safe, can I run. Block reading of .env, .ssh, .aws, and credential files. This skill blocks dangerous commands and warns on risky ones. ALWAYS apply the safety protocol from this document before responding about any command.
frmoretto/hardstop
Stars: 32Claude CodeCodexApply cinematic film looks to images/video via the Hance CLI. Use when asked to grade, color, or "make it look like" film.
Orva-Studio/hance
Stars: 83Claude CodeCodexSecurity audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response, and infrastructure security for any project.
sergiovazquezdml/Base-de-datos-aluminio
Stars: 0Claude CodeCodexTesting and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks
sergiovazquezdml/Base-de-datos-aluminio
Stars: 0Claude CodeCodex