agentleFS
Sign inStart free
martinhgmartinhg/capiko-ai/skills/capiko-dev/SKILL.md

capiko-dev

Skill2 starsChanged 20 days agoMITView on GitHub

capiko-ai codebase conventions and architecture. Trigger: any change to this repository.

We split this skill 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
  1. Distinctive:

    Branch first: Create a branch from main BEFORE the first edit.

    line 8

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Workflow

  • Branch first. Create a branch from main BEFORE the first edit. Never commit straight to main. Then commit, push, open a PR, wait for CI, squash- merge, delete the branch, and sync main.
  • Conventional commits. Never add Co-Authored-By or any AI attribution.
  • Quality gate before opening a PR: gofmt -l . clean, go vet ./... clean, go test -race ./... green.
  • Tools: prefer bat/rg/fd/eza over cat/grep/find/ls.

TUI golden tests

  • Screen rendering is covered by golden files in internal/tui/testdata/*.golden.
  • Regenerate with go test ./internal/tui -update, then always inspect the diff before committing — confirm only the intended lines changed.
  • Tests force the ASCII color profile (see view_test.go TestMain) so goldens are deterministic across terminals and CI.

Architecture patterns

  • Screens implement screen (Update(tea.Msg) (screen, tea.Cmd) + View()). They return to the menu by emitting backMsg, and transition to another screen by returning the next screen from Update (e.g. detection → persona → SDD → selector). Test a screen by driving Update with tea.Msg directly.
  • Instruction blocks (persona, SDD orchestrator) are marker-bound sections written into ~/.copilot/copilot-instructions.md via internal/instructions. Render-when-changed, back up the file (backup.CreateFiles) before writing, then record in internal/state.
  • Skills install verbatim into ~/.copilot/skills/<name>/SKILL.md; scoped instructions into ~/.copilot/instructions/*.instructions.md.
  • State lives in ~/.capiko/state.json; every mutation is snapshotted to ~/.capiko/backups/ first (snapshot-before-mutate).
  • For testability, wrap exec / network / home-dir behind package-level function vars (seams), as internal/release, internal/sysinfo, internal/copilot do.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free