Factory · install guide
Factory (Droid) skills. Where they live and how to install them.
Where Factory (Droid) loads skills
- In a project
.factory/skills/.agents/skills/- For all projects
~/.factory/skills/~/.agents/skills/- Docs
- docs.factory.ai
- Website
- factory.ai
- Droid searches skill folders recursively; the first directory containing SKILL.md is the skill. Project skills beat personal skills, which beat built-in ones.
- Folder-specific skills in <repo>/<area>/.factory/skills/ apply once Droid inspects that area.
- /skills opens a manager with Effective, User, Project, Plugins, Built-in and Import tabs; Space toggles a skill (stored as disabledSkills in settings.json).
- Frontmatter: name and description required; optional allowed-tools (metadata only, not a sandbox), enabled, user-invocable, disable-model-invocation, license, compatibility, version, metadata.
- A valid, enabled, user-invocable skill appears as /skill-name; disable-model-invocation: true keeps Droid from running it automatically.
How to install a skill
npx skills add {owner}/{repo} --skill {skill} -a droidFactory's docs describe no install command for repo skills. Project install goes to .agents/skills/; add -g for ~/.factory/skills/.
npx skills add anthropics/skills --skill mcp-builder -a droidExample with MCP Server Builder.
gh skill install {owner}/{repo} {skill} --agent droidProject scope by default; add --scope user for a personal install.
gh skill install anthropics/skills mcp-builder --agent droidExample with MCP Server Builder.
git clone --depth 1 https://github.com/{owner}/{repo}.git skills-src && mkdir -p .factory/skills && cp -r skills-src/{path} .factory/skills/{skill} && rm -rf skills-srcUse ~/.factory/skills/ instead of .factory/skills for a personal install. Start a new Droid session if the skill is not visible.
git clone --depth 1 https://github.com/anthropics/skills.git skills-src && mkdir -p .factory/skills && cp -r skills-src/skills/mcp-builder .factory/skills/mcp-builder && rm -rf skills-srcExample with MCP Server Builder.
Guide
How to install agent skills in Factory Droid
What skills are in Factory
Factory's documentation describes skills as reusable SKILL.md workflows that Droid, Factory's agent, can discover, invoke and share across projects. A skill is a directory with a SKILL.md entry point, optional supporting files and frontmatter that tells Droid when the workflow applies. Factory suggests skills for procedures that are too specific for the always-on AGENTS.md file, too structured for a one-off prompt, and useful enough to reuse.
Droid reads each skill's name and description first, compares them with your request, and loads the full body only when a skill applies. Supporting files are not loaded automatically, so the skill's instructions should say when to read or run them.
Where Droid looks for skills
| Scope | Location |
|---|---|
| Project | <repo>/.factory/skills/<skill-name>/SKILL.md |
| Folder-specific | <repo>/<project-area>/.factory/skills/<skill-name>/SKILL.md |
| Personal | ~/.factory/skills/<skill-name>/SKILL.md |
| Compatibility | <repo>/.agents/skills/ and <repo>/.agent/skills/ |
| Personal compatibility | ~/.agents/skills/ and ~/.agent/skills/ |
There are also plugin, built-in, mission and automation scopes. Droid searches skill folders recursively and treats the first directory containing SKILL.md as a skill. Outside mission and automation sessions, project skills win over personal skills, which win over built-in skills. If two skills in the same source share a name, that is invalid configuration, so rename or remove one.
Install a skill
Factory's documentation describes creating skills in these folders rather than a command for fetching them from GitHub, so the routes below use other tools or a manual copy. The examples use frontend-design from anthropics/skills, located at skills/frontend-design.
Option 1: the skills CLI
npx skills add anthropics/skills --skill frontend-design -a droid
This installs into .agents/skills/ in the project, which Droid reads as a compatibility folder. Add -g for ~/.factory/skills/.
Option 2: GitHub CLI
gh skill install anthropics/skills frontend-design --agent droid
gh skill install anthropics/skills frontend-design --agent droid --scope user
Needs GitHub CLI 2.90.0 or later, where gh skill is a public preview.
Option 3: copy the folder
git clone --depth 1 https://github.com/anthropics/skills.git skills-src
mkdir -p .factory/skills
cp -r skills-src/skills/frontend-design .factory/skills/frontend-design
rm -rf skills-src
Use ~/.factory/skills/ for a personal skill. Start a new Droid session if the skill is not visible straight away.
Check that it loaded
Run /skills. The manager has Effective, User, Project, Plugins, Built-in and Import tabs. The Effective tab groups every discovered skill by status: Enabled, Disabled, Overridden (a higher-priority skill with the same name is active) or Invalid (the name, frontmatter or prompt has a problem). A valid, enabled skill that is user-invocable also appears as a slash command, so you can run /frontend-design or mention it in the middle of a prompt.
Manage, update and remove
- Turn a skill off: select it in
/skillsand press Space. The choice is written todisabledSkillsin~/.factory/settings.json(User tab) or the project's.factory/settings.json(Project tab). Or setenabled: falsein the skill's frontmatter. - Remove: delete the skill folder, or run
npx skills remove frontend-design. - Update: copy a newer version of the folder over the old one, or use
npx skills updateorgh skill updatefor skills those tools installed. - Run
/diagnosticsafter fixing a name collision to confirm it is resolved.
Troubleshooting
- The skill is not a slash command: check the file is named
SKILL.md, thatnameanddescriptionare present, and thatenabledis notfalse. A skill withuser-invocable: falseis hidden from slash invocation by design. - Droid does not invoke it automatically: check that
disable-model-invocation: trueis not set, and tighten the description so it says exactly when to use the skill. - A skill deeper in the repository does not appear: Droid may discover it only after inspecting that part of the project.
- A tool is unavailable inside the skill:
allowed-toolsis metadata for review and display and does not grant tools or sandbox the skill, so the session must already have the tool. - The wrong skill is chosen: give the names and descriptions more specific wording.
Safety
Factory notes that allowed-tools is not a runtime sandbox and should not be treated as a security boundary. To enforce tool access, it points to a custom droid with a tool policy. Review SKILL.md and any scripts before installing a skill from outside your team, and do not store secrets, customer data or private host names in a skill folder, since skills are often shared through repositories.
Top skills to try in Factory (Droid)
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation. | anthropics/ | 180k | 62 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 2 | Handles everyday PDF jobs in Python and on the command line: extract text and tables, merge, split, rotate, watermark, fill forms, encrypt and OCR. | anthropics/ | 180k | 48 repos | ~2k | Automated safety check: Pass | Proprietary | 2 days ago |
| 3 | Builds multi-component claude.ai HTML artifacts as a small React, TypeScript and Tailwind project, then bundles it into one shareable HTML file. | anthropics/ | 180k | 40 repos | ~769 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 4 | Builds animated HTML slide decks that run in the browser with no dependencies, or converts PowerPoint files to the web, starting from visual style previews. | zarazhangrui/ | 30k | 16 repos | ~7k | Automated safety check: Pass | MIT | 3 mo ago |
| 5 | Design and build AI agents for any domain. An agent skill from shareAI-lab/learn-claude-code. | shareAI-lab/ | 78k | 6 repos | ~1.2k | Automated safety check: Pass | MIT | 9 days ago |
| 6 | Lets Claude Code ask questions of your Google NotebookLM notebooks through browser automation and return answers grounded in your uploaded sources. | PleasePrompto/ | 7.8k | 13 repos | ~2.4k | Automated safety check: Notes | MIT | 27 days ago |
| 7 | Scans React code for lint, accessibility, bundle size and architecture issues, reports a health score and checks that changes do not lower it. | makeplane/ | 60k | 12 repos | ~657 | Automated safety check: Pass | AGPL-3.0 | yesterday |
| 8 | Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree. | obra/ | 296k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | today |
| 9 | Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart. | anthropics/ | 37k | 11 repos | ~4.1k | Automated safety check: Notes | Apache-2.0 | today |
| 10 | Produces math and technical explainer videos with Manim Community Edition: concept animations, equation derivations, algorithm walkthroughs and data stories. | browser-use/ | 28k | 6 repos | ~3k | Automated safety check: Pass | MIT | 4 days ago |
| 11 | Guides a conversation that takes a vague idea through divergent and convergent thinking and ends in a markdown one-pager covering scope and assumptions. | addyosmani/ | 102k | 6 repos | ~2k | Automated safety check: Pass | MIT | 3 days ago |
| 12 | Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking… | vercel-labs/ | 44k | 24 repos | ~864 | Automated safety check: Pass | Apache-2.0 | today |
| 13 | Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications. | rolling-scopes/ | 10k | 24 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | 3 days ago |
| 14 | A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions | farm-fe/ | 5.6k | 34 repos | ~1.4k | Automated safety check: Pass | MIT | 15 days ago |
| 15 | Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review. | obra/ | 296k | 2 repos | ~5.1k | Automated safety check: Pass | MIT | today |
| 16 | Explores a web app with the agent-browser CLI to find bugs and UX problems, then writes a report with screenshots, repro videos and step-by-step reproduction for each issue. | vercel-labs/ | 44k | 8 repos | ~2.7k | Automated safety check: Pass | Apache-2.0 | today |
| 17 | Creates original generative art in two steps: a written algorithmic philosophy, then a p5.js sketch with seeded randomness and an interactive viewer for exploring parameters. | anthropics/ | 180k | 37 repos | ~4.9k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 18 | Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. | spacering-net/ | 3.8k | 15 repos | ~3.6k | Automated safety check: Pass | MIT | today |
| 19 | 19.Matplotlib Low-level plotting library for full customization. An agent skill from zLanqing/codex-claude-academic-skills. | zLanqing/ | 4.6k | 17 repos | ~2.9k | Automated safety check: Pass | MIT | 4 mo ago |
| 20 | A skill your agent uses whenever the user mentions Horizon by name in a Laravel context. | coollabsio/ | 63k | 4 repos | ~898 | Automated safety check: Pass | MIT | today |
| 21 | Gives the agent Postgres rules to consult before writing or changing tables, queries, indexes, RLS policies or migrations, and when diagnosing slow queries. | supabase/ | 2.7k | 24 repos | ~808 | Automated safety check: Pass | MIT | 5 days ago |
| 22 | Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way. | openinterpreter/ | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | today |
| 23 | Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design. | anthropics/ | 37k | 8 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | today |
| 24 | Create new skills, modify and improve existing skills, and measure skill performance. | Azure/ | 794 | 89 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 | yesterday |
Questions, answered from the data.
Where does Factory (Droid) look for skills?
Factory (Droid) loads skill folders (each with a SKILL.md file) inside a project from .factory/skills/ and .agents/skills/ and for every project from ~/.factory/skills/ and ~/.agents/skills/.
How do I install a skill in Factory (Droid)?
skills CLI: npx skills add {owner}/{repo} --skill {skill} -a droid. GitHub CLI: gh skill install {owner}/{repo} {skill} --agent droid. Manual copy: git clone --depth 1 https://github.com/{owner}/{repo}.git skills-src && mkdir -p .factory/skills && cp -r skills-src/{path} .factory/skills/{skill} && rm -rf skills-src. Replace the placeholders with the skill's GitHub owner, repository and name; every skill page here shows the filled-in command.
What are the best skills for Factory (Droid)?
Agent skills are portable SKILL.md folders, so the catalogue's top skills work in Factory (Droid) too. The highest-ranked right now are MCP Server Builder (anthropics/skills), PDF Processing (anthropics/skills) and Web Artifacts Builder (anthropics/skills).
Sources
- https://docs.factory.ai/cli/configuration/skills
- https://github.com/vercel-labs/skills
- https://cli.github.com/manual/gh_skill_install
Checked October 7, 2026