capiko-ai
AGENTS.md2 starsChanged 20 days agoMITView on GitHub
When working on this repository, load the relevant skill(s) BEFORE writing any code. Copilot reads this file as custom instructions, so these conventions apply automatically when developing capiko in this repo. Naming: capiko-* skills are repo-specific; unprefixed skills are portable. How to use: check the trigger column, then read the matching SKILL.md before starting the work. For the architecture and where code belongs, read the codebase guide: docs/codebase/ (mental-model.md, repository-map.md, architecture.md). These skills are for developing capiko. The skills capiko…
We split this AGENTS.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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 3
When working on this repository, load the relevant skill(s) BEFORE writing any code.
≈ “Common” is an estimate: at least 1 in 5 of the 36,368 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
capiko-ai — Agent Skills Index
When working on this repository, load the relevant skill(s) BEFORE writing any code. Copilot reads this file as custom instructions, so these conventions apply automatically when developing capiko in this repo.
Naming: capiko-* skills are repo-specific; unprefixed skills are portable.
| Trigger | Skill | Path |
| Any change to this repo (workflow, conventions, architecture) | capiko-dev | skills/capiko-dev/SKILL.md |
| Writing or reviewing Go / Bubbletea tests, golden files | go-testing | skills/go-testing/SKILL.md |
| Splitting work into commits | work-unit-commits | skills/work-unit-commits/SKILL.md |
| Opening a PR | branch-pr | skills/branch-pr/SKILL.md |
| A change is growing too large for one PR | chained-pr | skills/chained-pr/SKILL.md |
| Filing a bug report or feature request | issue-creation | skills/issue-creation/SKILL.md |
| Writing PR reviews / replies / feedback | comment-writer | skills/comment-writer/SKILL.md |
| Writing a README, guide, RFC, or doc | cognitive-doc-design | skills/cognitive-doc-design/SKILL.md |
How to use: check the trigger column, then read the matching SKILL.md before
starting the work.
For the architecture and where code belongs, read the codebase guide:
docs/codebase/ (mental-model.md, repository-map.md, architecture.md).
These skills are for developing capiko. The skills capiko ships to users live
in internal/catalog/skills/ (embedded in the binary).
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 28,693 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository9 other files it gives its agents.
- llms.txtllms.txt
- branch-prSkill
- capiko-devSkill
- chained-prSkill
- cognitive-doc-designSkill
- comment-writerSkill
- go-testingSkill
- issue-creationSkill
- work-unit-commitsSkill
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.

