KushpawanKushpawan/kmp-mobile-skills/AGENTS.md

kmp-mobile-skills

AGENTS.md15 starsChanged 22 days agoApache-2.0View on GitHub

This file is for agents editing this repo (writing or fixing skills). It is not loaded by people who install the skills. - The rules for every skill are in docs/skill-authoring-guide.md. Read it before creating or editing anything under skills/. - One skill per folder: skills/<name>/SKILL.md, where name in the frontmatter equals the folder name. Use only the six portable frontmatter keys. - Every skill needs evals/<name>-trigger/prompt.md; run python3 scripts/scaffold_trigger_eval.py <name> after writing the prompt. - Never hand-edit the skill…

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 31,700 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 repository34 other files it gives its agents.
- android-to-kmp-migrationSkill
- compose-design-system-componentSkill
- compose-multiplatform-localizationSkill
- compose-multiplatform-navigationSkill
- compose-multiplatform-screenSkill
- figma-to-mobile-uiSkill
- kmp-api-endpointSkill
- kmp-build-checkSkill
- kmp-build-failure-triageSkill
- kmp-ci-github-actionsSkill
- kmp-code-reviewSkill
- kmp-crash-triageSkill
- kmp-data-layerSkill
- kmp-dev-machine-cleanupSkill
- kmp-expect-actualSkill
- kmp-feature-moduleSkill
- kmp-flaky-test-triageSkill
- kmp-gradle-version-catalogSkill
- kmp-koin-diSkill
- kmp-module-healthSkill
- kmp-room-databaseSkill
- kmp-secure-storageSkill
- kmp-swiftui-interopSkill
- kmp-test-coverage-backfillSkill
- kmp-testing-patternsSkill
- kmp-xcframework-distributionSkill
- mobile-accessibility-test-idsSkill
- mobile-bug-fixSkill
- mobile-feature-implementSkill
- mobile-feature-planSkill
- mobile-performance-fixSkill
- mobile-platform-paritySkill
- mobile-releaseSkill
- mobile-security-reviewSkill

The file

We split this AGENTS.md into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Read it before creating or editing anything under skills/.
line 7
Very specific:
Every skill needs evals/<name>-trigger/prompt.md.
line 10
Very specific:
Never hand-edit the skill lists in .codex-plugin/plugin.json / .cursor-plugin/plugin.json or the README catalog.
line 12
Distinctive:
Before you say a change is done, run and report:
line 14
Distinctive:
Do not vendor third-party skills without following section 8 of the authoring guide.
line 24

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 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.

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

Files

AGENTS.md

Instructions for AI agents working on this repository

This file is for agents editing this repo (writing or fixing skills). It is not loaded by people who install the skills.

The rules for every skill are in docs/skill-authoring-guide.md. Read it before creating or editing anything under skills/.
One skill per folder: skills/<name>/SKILL.md, where name in the frontmatter equals the folder name. Use only the six portable frontmatter keys.
Every skill needs evals/<name>-trigger/prompt.md; run python3 scripts/scaffold_trigger_eval.py <name> after writing the prompt.
Never hand-edit the skill lists in .codex-plugin/plugin.json / .cursor-plugin/plugin.json or the README catalog. Run python3 scripts/sync_manifests.py.

Before you say a change is done, run and report:

python3 scripts/validate_skills.py --strict
python3 scripts/sync_manifests.py --check
python3 scripts/run_tests.py

Examples use com.example.app and neutral domains. Never add company, product or person names, internal hostnames, local paths, tokens or keys.
Do not vendor third-party skills without following section 8 of the authoring guide.

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