agentleFS
gclmgclm/super-stack/skills/core/repo-bootstrap/SKILL.md

repo-bootstrap

Skill0 starsChanged 7 months agoMITView on GitHub

Inspect a repository and decide whether to initialize the generated-project scaffold before task-level harness work begins.

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 1 is distinctive, and 7 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.

  • 7

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use when entering a repository that may not yet have the standard docs-plus-harness layout, or when the user wants to adopt super-stack's …

    line 8
  2. Distinctive:

    avoid mixing project bootstrap with task bootstrap

    line 25
  3. Very specific:

    Use references/bootstrap-decision-rules.md to classify the repository state.

    line 31
  4. Very specific:

    If the repository is ready, do not rerun bootstrap.

    line 32
  5. Very specific:

    If the repository is missing and the user wants the standard layout, run bash …

    line 33
  6. Very specific:

    If the repository is partial, only fill missing scaffold files when the conflict risk is low and the user intent is explicit.

    line 34
  7. Very specific:

    If the repository has no docs/ or harness/ scaffold yet, treat bootstrap as a clean init.

    line 35
  8. Very specific:

    If the user also has a concrete task after bootstrap, either hand off to task-harness or create the first task pack with bash …

    line 36

≈ “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

Repo Bootstrap

Use when entering a repository that may not yet have the standard docs-plus-harness layout, or when the user wants to adopt super-stack's generated-project scaffold safely.

Read First

  • root AGENTS.md
  • nearby entry docs such as README*, docs/, and top-level manifests
  • harness/state.md if it exists
  • harness/history.md if it exists
  • references/bootstrap-decision-rules.md
  • ~/.super-stack/runtime/scripts/workflow/init-generated-project.sh
  • ~/.super-stack/runtime/scripts/workflow/init-harness-task.sh only if the user also wants the first task pack

Goals

  • inspect the repository before writing bootstrap files
  • classify the repository as missing, partial, or ready
  • initialize the standard docs-plus-harness scaffold only when it is truly missing or clearly safe to fill
  • avoid mixing project bootstrap with task bootstrap
  • hand the repository off to task-harness, plan, or migration work with a clear readiness status

Process

  1. Inspect whether the target repo already has its docs entrypoint, harness state file, and related layout.
  2. Use references/bootstrap-decision-rules.md to classify the repository state.
  3. If the repository is ready, do not rerun bootstrap; report readiness and move to task-harness or the requested stage.
  4. If the repository is missing and the user wants the standard layout, run bash ~/.super-stack/runtime/scripts/workflow/init-generated-project.sh --root <repo-root>.
  5. If the repository is partial, only fill missing scaffold files when the conflict risk is low and the user intent is explicit; otherwise step back to plan or migration design instead of forcing the layout.
  6. If the repository has no docs/ or harness/ scaffold yet, treat bootstrap as a clean init.
  7. If the user also has a concrete task after bootstrap, either hand off to task-harness or create the first task pack with bash ~/.super-stack/runtime/scripts/workflow/init-harness-task.sh --task-id <task-id>.

Output

Tell the user:

  • the repository readiness state
  • whether bootstrap was executed, skipped, or deferred
  • what files or directories were created when bootstrap ran
  • whether the next step is task-harness, plan, or migration work

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.

Reviews can't be read right now.

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.