Skills for overnight agent runs
Setting a goal and leaving the agent to work overnight only pays off if the skill gives it a procedure, a way to keep state, and a check before it claims success. These are the reviewed skills that do.
Before you leave an agent alone
- Set an iteration or time limit and a clear stop condition.
- Run it in a sandbox, container or separate git worktree; skills with shell scripts run with your permissions.
- Read the skill's files first. Our security reviews help, but they are not a guarantee.
| Skill | Verdict | Installs |
|---|---|---|
 skill-creator skill in anthropics/skills Anthropic's skill for writing new skills and improving them with test prompts, graders, a review viewer and trigger-description optimization. | Recommended | 418K |
 Cloudflare security-audit cloudflare/security-audit-skill A single multi-agent skill from Cloudflare that audits a codebase in six phases and writes validated, independently verified findings. | Recommended | 64K |
 agent-browser vercel-labs/agent-browser A native browser-automation CLI for agents, plus 11 skills that teach the snapshot-and-ref workflow for navigating, filling forms, scraping and testing. | Recommended | 1.3M |
 google-agents-cli-eval skill in google/agents-cli Teaches an agent to evaluate ADK agents: dataset schema, built-in and custom metrics, LLM-as-judge scoring and an eval-fix loop. | Recommended | 519K |
 Planning with Files OthmanAdi/planning-with-files Keeps task_plan.md, findings.md and progress.md on disk and re-injects them via hooks, so a plan survives /clear, compaction and crashes. | Recommended | — |
 Compound Engineering EveryInc/compound-engineering-plugin Every's plugin of 36 skills for a brainstorm, plan, build, review and capture-the-learning loop, with an optional hands-off /lfg pipeline. | Recommended | — |
 SkillSpector NVIDIA/SkillSpector NVIDIA's open-source security scanner for agent skills, with 71 detection patterns, optional LLM review and a skill-inspector skill. | Recommended | — |
 drawio-skill Agents365-ai/drawio-skill Skill that turns natural language, Terraform, SQL, OpenAPI and other sources into editable draw.io diagrams, with incremental sync, drift detection and CI tests. | Recommended | — |
 claude-blog AgriciDaniel/claude-blog A Claude Code skill suite for writing, auditing and refreshing blog posts, with a five-gate delivery contract, 30 /blog commands, 5 agents and a bundled Obsidian brain. | Recommended | — |
 delegate-skills amElnagdy/delegate-skills Twenty skills that hand a coding task to another agent CLI (Codex, Cursor, Aider, Claude and many more) in the background, then leave the diff review and commit to you. | Recommended | — |
 ToolUniverse mims-harvard/ToolUniverse Harvard MIMS lab's Python SDK, MCP server and 556 skills that give agents access to thousands of scientific databases and tools for biomedical research. | Recommended | — |
 Superpowers obra/superpowers A 15-skill development methodology that makes coding agents clarify the goal, write a plan, work through it with subagents and verify before calling it done. | Recommended | 3.7M |
 Stitch Skills (Google Labs) google-labs-code/stitch-skills Google Labs' 16 skills for the Stitch design tool: generate screens, extract design systems, and convert Stitch designs to React, React Native and more. | Recommended | 65K |
 Journalism agent skills (jamditis) jamditis/claude-skills-journalism Plugin packages of skills for journalists and researchers (verification, FOIA, AP style) plus dev, newsroom-ops and security toolkits for Claude Code and Codex. | Recommended | — |
 Matt Pocock's Skills mattpocock/skills Small, composable engineering skills: grill-me interviews, shared glossary, TDD, triage, prototyping, code review, handoff and a flow router. | Recommended | 31M |
 Nx AI Agent Skills nrwl/nx-ai-agents-config Official skills, subagents and commands from the Nx team for working in Nx monorepos, including Nx Cloud CI monitoring and self-healing fixes. | Recommended | 80K |
 notebooklm-py teng-lin/notebooklm-py Unofficial Python API, CLI and agent skill for Google's NotebookLM (now Gemini Notebook), built on undocumented endpoints. | With caveats | — |
 Obsidian Second Brain eugeniughelbur/obsidian-second-brain Persistent, self-rewriting memory in your Obsidian vault: 48 commands, a shared cross-agent logbook (Crew), scheduled maintenance and a research toolkit. | With caveats | — |
 onetake feitangyuan/onetake A skill for making short product launch and feature-demo films as one continuous camera move, rendered from HTML and checked by a continuity script. | With caveats | — |
 Paperclip paperclipai/paperclip A self-hosted app for orchestrating teams of AI agents with org charts, budgets and approvals; its skills are mostly maintainer workflows. | With caveats | — |
 NanoClaw nanocoai/nanoclaw A small self-hosted assistant that runs Claude agents in Docker containers and connects to chat apps, extended by about 35 Claude Code setup skills. | With caveats | — |
 ARIS (Auto-Research-In-Sleep) wanshuiyin/Auto-claude-code-research-in-sleep A large markdown skill set for autonomous ML research: idea discovery, experiment runs and cross-model review loops where a second model critiques the first. | With caveats | — |
 AI Research Skills (Orchestra) Orchestra-Research/AI-Research-SKILLs 98 skills for AI research and ML engineering, plus an autoresearch orchestrator that runs a two-loop experiment and synthesis cycle. | With caveats | — |
 Claude Octopus nyldn/claude-octopus An escalation layer that runs tasks past up to twelve external AI providers (Codex, Copilot, Ollama, Grok, more) with a consensus gate, plus 63 skills. | With caveats | — |
 Babysitter a5c-ai/babysitter An npm-installed orchestration runtime that makes coding agents follow workflows defined in JS code, with quality gates, approval breakpoints and a run journal. | With caveats | — |
 Deep Research Skill 199-biotechnologies/claude-deep-research-skill A single research skill with an 8-phase pipeline, parallel search, source scoring, claim and citation checks, and report output in Markdown, HTML and PDF. | With caveats | — |
| git-guardrails-claude-code skill in mattpocock/skills Installs a Claude Code PreToolUse hook that blocks git push, reset --hard, clean -f, branch -D and similar commands before the agent can run them. | With caveats | 514K |
 OmO (oh-my-openagent) code-yeongyu/oh-my-openagent An agent harness and CLI (omo) with multi-model orchestration; its .agents/skills folder holds mostly maintainer workflows for the project itself. | With caveats | — |
 Skill Seekers yusufkaraaslan/Skill_Seekers Python tool and MCP server that converts documentation sites, repos, PDFs and other sources into agent skills and RAG-ready knowledge, with 22 export targets. | With caveats | — |
 Harness revfactory/harness A Claude Code meta-skill that designs a project-specific agent team, writes the agent definitions and skills for it, and has an evolve skill to refine them from feedback. | With caveats | — |
 Google Maps Scraper gosom/google-maps-scraper Agent skill that runs the open-source gosom Google Maps scraper locally in Docker to collect business leads, reviews, emails and contact details. | With caveats | — |
 pstack-claude michael-denyer/pstack-claude A port of Lauren Tan's pstack workflow skills to Claude Code, Codex, Copilot and others, with a poteto-mode router and 67 skills. | With caveats | — |
 UX/UI Agent Skills (XIAS) plugin87/ux-ui-agent-skills Design-system doctrine, DTCG tokens and 27 skills for coding agents, plus about 50 scripted gates that check what the agent built, including accessibility. | With caveats | — |
 ScienceClaw beita6969/ScienceClaw A research agent system built on the OpenClaw gateway whose Skills and typed Operators are updated only after a replay-verified execution; ships with 319 skills. | With caveats | — |
 Firecrawl CLI firecrawl/cli Firecrawl's command-line client and 13 agent skills for web search, scraping, crawling, interacting with pages and parsing files through the paid Firecrawl API. | With caveats | 660K |
 herdr herdrdev/herdr A Rust terminal multiplexer for coding agents, with a skill that lets one agent split panes, start other agents and wait on them. | With caveats | 75K |
| Claude for Legal anthropics/claude-for-legal Anthropic's suite of legal-workflow plugins: 151 skills across in-house practice areas, each driven by a cold-start interview and a practice profile. | With caveats | — |
 Agentix CEO skill agentix-cloud/skills One skill that turns your agent into a manager of remote Claude Code workers on the Agentix hosted platform, using your Anthropic and GitHub tokens. | With caveats | 75K |
 Pro Workflow rohitg00/pro-workflow A Claude Code plugin with 41 skills and many hooks that stores your corrections in SQLite and adds searchable research wikis, quality gates and cost tracking. | With caveats | — |