agentleFS
Sign inStart free
xialangji-debugxialangji-debug/codex-skills-agentmd-obsidian/skills/asr3601-project-onboard/SKILL.md

asr3601-project-onboard

Skill3 starsChanged 2 months agoMITView on GitHub

Prepare recorded ASR360x branch configuration after a checkout, recover missing generated context, or register confirmed build parameters. Use for 切换后初始化, 调取版本配置, 生成项目 AGENTS, or a missing build profile. Ordinary source questions and direct build/release requests use their owners without an extra onboarding pass.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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
  1. Very specific:

    After an authorized branch switch, run the generator with --prepare once.

    line 12
  2. Very specific:

    Use live identity and unique confirmed mappings.

    line 18
  3. Very specific:

    Default context consists of AGENTS.md, .codex-project/asr3602-build-profile.json, and .codex-project/variant.md.

    line 19

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

ASR360x Project Configuration

Live Git and yl.h own current identity. The registered branch profile owns build parameters. The existing private project map owns external mappings. variant.md is a generated view.

Prepare Configuration

After an authorized branch switch, run the generator with --prepare once. Build and release controllers restore their profiles internally; do not repeat initialization outside the owner.

Records live under the Git common directory's codex/build-profiles/. Worktrees share branch records but keep their own current profile. Version dates and ordinary commits do not require registering build parameters again. Hardware or build-input changes require verified updated settings.

Generation Contract

  1. Use live identity and unique confirmed mappings. Missing or ambiguous build records remain NEEDS_CONFIGURATION; ordinary source work can continue.
  2. Default context consists of AGENTS.md, .codex-project/asr3602-build-profile.json, and .codex-project/variant.md. Write only changed generated files.
  3. Preserve local.md, project-owned AGENTS content, specialized documents, resources, and validation material. --force does not erase project-owned instructions.
  4. Protocol classification is only a search hint. Device selection and remote writes retain their owner's checks.
  5. For first registration or a confirmed update, use branch profile operations. Reuse user-supplied parameters and exact-target evidence before asking for missing facts. Do not qualify a build from folder tokens or a copied support label.

Repository and variant hashes are privacy-safe identifiers. Target IDs retain branch/version case and match the canonical memory writer and Zentao reconciliation; do not rewrite historical memory targets during onboarding.

Commands

The generator uses Python; private project-map parsing uses PyYAML.

python "$env:USERPROFILE\.codex\skills\asr3601-project-onboard\scripts\project_onboard.py" --repo . --check
python "$env:USERPROFILE\.codex\skills\asr3601-project-onboard\scripts\project_onboard.py" --repo . --dry-run
python -X utf8 "$env:USERPROFILE\.codex\skills\asr3601-project-onboard\scripts\project_onboard.py" --repo . --prepare

--check is read-only; --dry-run previews. --write remains an alias for preparation and view generation. Add --json for structured context. A record does not replace current Git state or actual device verification. Never store private customer mappings or service data in reusable templates.

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