skill-template
Skill0 starsChanged 8 days agoApache-2.0View on GitHub
Scaffold-only starting template for a new portable Solo Empire AI skill package; copy it into skills/<name>/ and fill in the placeholders. Use only when you need the blank SKILL.md structure. Not for auditing, de-duplicating, updating, retiring, or validating skills — use govern-ai-skills.
12 other projects use a version of this.
Adopted by
Most recently taken up by
- gaia-research/gaia-skill-treetheir own version, first seen Nov 7, 2026
- claude-world/director-mode-litetheir own version, first seen Nov 1, 2026
- Baba01hacker666/dummyskillstheir own version, first seen Oct 13, 2026
- cadeKukk/claude-skillstheir own version, first seen Oct 13, 2026
- KiloAgent/skillstheir own version, first seen Oct 13, 2026
- Gopyr/gopyr-skills-hubtheir own version, first seen Oct 11, 2026
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- muratcankoylan/Agent-Skills-for-Context-Engineering★ 18ksame name
- anbeime/skill★ 7.9ksame name
- claude-world/director-mode-lite★ 80same name
- VoDaiLocz/kilo-kit-mcp★ 28same name
- gaia-research/gaia-skill-tree★ 22same name
- maybeanns/context-management-for-antigravity★ 4same name
- carlosedm10/skills★ 1same name
- KiloAgent/skills★ 1same name
- Baba01hacker666/dummyskills★ 0same name
- cadeKukk/claude-skills★ 0same name
2 more not listed
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.
In this repository27 other files it gives its agents.
- ai-agentsSkill
- ai-agent-workflowsSkill
- ai-native-estimationSkill
- ai-product-deliverySkill
- book-dev-engineering-loopSkill
- business-analysisSkill
- client-discovery-and-proposalsSkill
- content-distributionSkill
- data-engineeringSkill
- flow-videoSkill
- game-engineeringSkill
- govern-ai-skillsSkill
- graphic-designSkill
- lead-research-and-crmSkill
- main-only-developmentSkill
- product-managementSkill
- product-ownerSkill
- project-managementSkill
- qa-testingSkill
- security-and-privacySkill
- solo-empire-operatorSkill
- solution-architectureSkill
- subagent-orchestrationSkill
- system-docpackSkill
- unused-file-cleanupSkill
- ux-reviewSkill
- xr-engineeringSkill
The file
Files
[Skill name]
Overview
[State what this skill enables and the kind of task it handles. Keep this section short; the frontmatter description is the trigger contract.]
Workflow
- Read the relevant repository guidance and current source of truth.
- [First task-specific step]
- [Next task-specific step]
- Verify the result with the narrowest relevant check.
Decision rules
- [Condition] → [Action]
- [Condition] → [Action]
Resources
references/<file>.md— [Read when ...]scripts/<file>— [Run when ...]assets/<file>— [Use when ...]
[Delete unused resource entries and this instruction before publishing the skill. Do not add a README, changelog, or installation guide inside a skill.]
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.