agentleFS
TheAstroByteTheAstroByte/astrobyte-agent-skills/skills/astrobyte-project-startup/SKILL.md

astrobyte-project-startup

Skill1 starsChanged 14 days agoMITView on GitHub

Establish or revise a project's stack and operating assumptions before substantial implementation. Use for greenfield setup, repository bootstrap, prototype kickoff, architecture startup, or when project stack choices are materially unresolved.

The file

We split this skill 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
  1. Very specific:

    Read repository instructions and .astrobyte/config.json when present.

    line 10
  2. Very specific:

    Read stack-policy.md and consult project-defaults.json.

    line 20
  3. Distinctive:

    Ask one question at a time unless the operator requests a batch.

    line 26
  4. Very specific:

    After confirmation, create or update .astrobyte/config.json using project-config.example.json as the shape.

    line 33
  5. Distinctive:

    Keep the project file portable and safe to commit: exclude secrets, credentials, absolute machine paths, and transient local endpoint …

    line 34

≈ “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

Astrobyte project startup

Inspect

  1. Read repository instructions and .astrobyte/config.json when present.
  2. Resolve preferences with this skill's scripts/runtime_config.py --project <project-root>. Read the packaged working agreement and apply returned working_agreement_layers in order, including local stack choices. Apply higher-priority machine, project, repository, and task evidence as specified in configuration.md. Missing optional config uses the packaged baseline; malformed or explicitly requested missing config needs resolution.
  3. Inspect manifests, lockfiles, imports, services, containers, CI, deployment files, data formats, and runnable entry points.
  4. Classify each relevant choice as detected, confirmed, defaultable, conflicting, or unresolved.
  5. Preserve a coherent existing stack. Treat conflicting evidence as unresolved rather than choosing by file count.

Inspection is complete when observable facts are separated from decisions that require the operator.

Interview

Read stack-policy.md and consult project-defaults.json. When a recommendation depends on a changing tool capability, verify it against current primary documentation, starting from sources.md. Ask only questions whose answers materially affect architecture, dependencies, external data transfer, deployment, cost, or verification.

  1. Establish project archetype, maturity, expected users, and success evidence.
  2. Resolve deployment target, data sensitivity, authentication exposure, and external-provider permissions.
  3. Resolve only the stack boundaries still marked conflicting or unresolved.
  4. For each question, show the detected evidence, recommend one choice with a short reason, and name the meaningful alternative.
  5. Ask one question at a time unless the operator requests a batch. Accept “use the default” without extending the interview.

The interview is complete when implementation can start without an implicit material stack decision.

Record

  1. Summarize the selected stack, inherited choices, exceptions, and unresolved decisions.
  2. After confirmation, create or update .astrobyte/config.json using project-config.example.json as the shape. Record only relevant fields.
  3. Keep the project file portable and safe to commit: exclude secrets, credentials, absolute machine paths, and transient local endpoint values.
  4. Point implementation plans to the project file. Reopen the interview only when scope or constraints invalidate a recorded choice.

Startup is complete when the operator has confirmed the material choices and .astrobyte/config.json matches that decision. Stack selection does not itself authorize scaffolding, dependency installation, deployment, or external actions.

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.