skill-hub
Skill1 starsChanged 3 months agoMITView on GitHub
Skill Hub for Command Code — keep skills up to date and get stack-aware recommendations. Use when the user wants to list, update, or discover relevant skills for the current project (e.g. "/skillhub", "update my skills", "recommend skills for this project", "what skills should I install here?").
6 other projects use a version of this.
Adopted by
Most recently taken up by
- yinsanbian/AgentSkillHubtheir own version, first seen Oct 17, 2026
- kannaka-labs/Kannaktopustheir own version, first seen Oct 13, 2026
- FlyrenxingSkill/skill-hubtheir own version, first seen Aug 8, 2026
- finger88/my-claude-skillstheir own version, first seen Apr 7, 2026
- kevinaimonster/skill-hubtheir own version, first seen Mar 18, 2026
- PhenixStar/openclaw-skills-collectiontheir own version, first seen Feb 8, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- kevinaimonster/skill-hub★ 4same name
- finger88/my-claude-skills★ 3same name
- PhenixStar/openclaw-skills-collection★ 1same name
- yinsanbian/AgentSkillHub★ 1same name
- FlyrenxingSkill/skill-hub★ 0same name
- kannaka-labs/Kannaktopus★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 52
Use recommend_skills when the user asks "what should I install here?" — it returns install commands you can surface verbatim.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Skill Hub
Manage Command Code skills from a single interface. Works alongside the skill-hub-mod (slash commands + tools); this skill provides the detailed usage reference that loads into context when invoked.
Mod vs Skill
- Mod (
skill-hub-mod): registers/skillhub,/skills-update, toolsskill_autoupdate_check/recommend_skills, and session hooks. Always available after install. - Skill (this file): loaded on demand (
/skill-hub) to give the model full context when reasoning about skill management. No duplication — the skill documents what the mod exposes.
Install the mod once:
# Try without installing
cmdc --mod ./src/index.ts
# Project scope
cmdc mods add /path/to/skill-hub-mod
# Global (every workspace)
cmdc mods add -g /path/to/skill-hub-mod
# From GitHub (once public)
cmdc mods add PabloJustDevelops/skill-hub-mod
npx skills add PabloJustDevelops/skill-hub-mod --skill skill-hub -g -ySlash Commands
| Command | Description |
/skillhub | Help (lists subcommands) |
/skillhub list | List installed skills (skills list -g --json) |
/skillhub check | Quick status: installed count + detected stack + pending recommendations |
/skillhub update [name] | Update one or all skills (prompts with confirm) |
/skillhub recommend [--verbose] | Recommend skills for the current project (local heuristic, suggestions only) |
/skills-update [list|name|all] | Compatibility alias for /skillhub update / /skillhub list |
check and recommend share the same local stack detection (see below). update wraps npx --yes skills update -g -y.
Tools
| Tool | Schema | Notes |
skill_autoupdate_check | {updateAll?: boolean, skillName?: string} | No args = list installed; skillName = update one; updateAll = update all. readOnly: false |
recommend_skills | {verbose?: boolean} | Recommends for cwd via local detection, filtered against installed. readOnly: true |
Use recommend_skills when the user asks "what should I install here?" — it returns install commands you can surface verbatim.
Recommendation Heuristic
Purely local, no network. Factors:
package.jsondeps:astro,next,react,vue,svelte,tailwindcss,typescript,vitest/jest,playwright/cypress,pdflibs,openai/firecrawl,prisma/drizzle/postgres,seolibs,typedoc/docusaurus- Files:
tsconfig.json,astro.config.*,pyproject.toml,requirements.txt,Dockerfile,.github/,prisma/,tests/,__tests__/
Mapping (conservative):
| Tag | Skill | Source |
astro | astro-framework | delineas/astro-framework-agents |
next/react/vue/svelte/tailwind | vercel-labs/agent-skills | vercel-labs/agent-skills |
testing/e2e | playwright-testing | anthropics/skills |
pdf | pdf | anthropics/skills |
| frontend stack | accessibility | addyosmani/web-quality-skills |
seo | seo-audit | anthropics/skills |
database | orchestration | anthropics/skills |
ai | firecrawl | anthropics/skills |
docs | docx | anthropics/skills |
deployment | wrangler | anthropics/skills |
Recommendations filter out already-installed skill names and are suggestions only:
npx skills add <source> --skill <name> -g -y
https://skills.sh/<source>Flags
| Flag | Default | Description |
autoCheck | true | Reminder on session start (startup) |
autoUpdate | false | Auto-run skills update -g -y on start |
autoRecommend | false | Suggest recommended skills on start when relevant |
cmdc --mod-option autoRecommend=true
cmdc --mod-option autoUpdate=trueonSessionStart only fires on startup (not resume) and is try/catch-wrapped.
Notes
npx skillshas nocheckcommand — onlylist+update.npx --yesskips theskills@latestinstall prompt.cmdon Windows is the Windows shell; Command Code's binary on this machine iscmdc.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

