templates
Skill1 starsChanged 4 months agoMITView on GitHub
A skill is a reusable method your agent can run instead of you explaining it again. When you find yourself describing the same process twice, write it down here and save it in your methods folder. One skill, one method. A skill that tries to do five things is really five skills. Small skills are easier to trust, reuse, and combine. Add every skill to your toolkit index, keyed by intent, so you and your agent can find it by…
22 other projects use a version of this.
Adopted by
Most recently taken up by
- runa-tic/palimpsesttheir own version, first seen Nov 8, 2026
- vijaysuperpositionist/skillstheir own version, first seen Nov 1, 2026
- razzant/ouroborostheir own version, first seen Oct 25, 2026
- sid-lakhani/agents-configtheir own version, first seen Oct 20, 2026
- The-Utopia-Studio/skillstheir own version, first seen Oct 13, 2026
- butterbase-ai/butterbase-plugintheir own version, first seen Oct 8, 2026
Other versions22 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 22
- razzant/ouroboros★ 1.6ksame name
- butterbase-ai/butterbase-plugin★ 535same name
- butterbase-ai/butterbase-skills★ 535same name
- xenitV1/Antigravity-Workflows★ 130same name
- VoDaiLocz/kilo-kit-mcp★ 28same name
- coder/skills★ 14same name
- The-Utopia-Studio/skills★ 6same name
- SKB3002/agenthub★ 4same name
- wachterjohannes/symfony-skills★ 4same name
- WESTsyre21/setup-backend-stack★ 4same name
12 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 repositoryOne other file it gives its agents.
- agent-os/CLAUDE.mdCLAUDE.md
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 17 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 34
Add every skill to your toolkit index, keyed by intent, so you and your agent can find it by what it does.
“Common” is measured: kept by at least 6 in 10 of the 17 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 template
A skill is a reusable method your agent can run instead of you explaining it again. When you find yourself describing the same process twice, write it down here and save it in your methods folder.
---
name: <short-name>
description: <when to use this: the trigger, in the words you would actually think>
---
# <Skill name>
## When to use
<The situation this applies to. Be specific, so the agent picks it at the right moment and not the wrong one.>
## Steps
1. <First step.>
2. <Next step.>
3. <And so on. Keep each step a single clear action.>
## Rules
- <Anything that must always be true. Constraints, standards, things not to do.>
## Output
<What "done" looks like. The shape of the result.>Keep skills small
One skill, one method. A skill that tries to do five things is really five skills. Small skills are easier to trust, reuse, and combine.
Reference it from the index
Add every skill to your toolkit index, keyed by intent, so you and your agent can find it by what it does.
Lite version of the NexForge Agent Starter Kit. MIT licensed.
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.