agentleFS
Sign inStart free
hlhr202hlhr202/swe-skills/skills/architect-setup/SKILL.md

architect-setup

Skill3 starsChanged 2 months agoApache-2.0View on GitHub

Initialize or resume Architect project setup by creating only the core architect/ context. Use when the user asks to set up Architect, scaffold Architect context, or recover an interrupted setup before discussion or proposal work.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create only product, product-guideline, tech-stack, code-style, workflow, and index context.

    line 12
  2. Very specific:

    Keep writes under architect/.

    line 13
  3. Distinctive:

    Use reviewable edits, preferably patches.

    line 14
  4. Distinctive:

    Commit only when the user explicitly requests it in the current conversation.

    line 15
  5. Very specific:

    Stop when core context is ready.

    line 23

≈ “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

Architect Setup

Initialize or resume the durable Architect core context, then hand off to discussion. Follow references/setup-protocol.md as the source of truth.

Hard Boundaries

  • Create only product, product-guideline, tech-stack, code-style, workflow, and index context. Never create or repair tracks.
  • Keep writes under architect/; reject absolute paths and ...
  • Use reviewable edits, preferably patches; never use shell redirection for writes.
  • Commit only when the user explicitly requests it in the current conversation.

Run

  1. Read references/setup-protocol.md.
  2. Audit core artifacts and resume at the earliest incomplete state.
  3. Detect Greenfield or Brownfield context and follow the required approval gates.
  4. Complete and approve each missing core artifact in order.
  5. Stop when core context is ready; summarize changes and recommend /architect-discuss.

Bundled references/workflow.md is the default workflow. Enumerate references/code_styleguides/*.md at runtime so newly bundled guides remain available.

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