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

architect-propose

Skill3 starsChanged 2 months agoApache-2.0View on GitHub

Propose and create a new Architect track for an initialized project, including its spec, plan, metadata, and registry entry. Use when the user asks to add, plan, or propose a new feature, bug fix, chore, refactor, docs, or test track.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 4 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    Create one proposal track from approved specification and plan artifacts.

    line 8
  2. Distinctive:

    Do not create a track before both spec and plan approvals.

    line 13
  3. Very specific:

    Keep writes and links under safe architect/ paths.

    line 14
  4. Distinctive:

    Do not let unrelated track status block an independent proposal.

    line 15
  5. Distinctive:

    Commit only when explicitly requested in the current conversation.

    line 16
  6. Very specific:

    Read references/propose-track-protocol.md and core project context.

    line 20
  7. Very specific:

    Ask for Task or Sub-task status granularity, default to Sub-task, then draft, present, revise, and approve plan.md from the project …

    line 23
  8. Distinctive:

    Create artifacts, register the track, and report next steps without starting implementation.

    line 25

≈ “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 Propose

Create one proposal track from approved specification and plan artifacts. Follow references/propose-track-protocol.md as the source of truth.

Hard Boundaries

  • Require initialized core Architect context.
  • Do not create a track before both spec and plan approvals.
  • Keep writes and links under safe architect/ paths.
  • Do not let unrelated track status block an independent proposal; only collisions may block creation.
  • Commit only when explicitly requested in the current conversation.

Run

  1. Read references/propose-track-protocol.md and core project context.
  2. Establish description and inferred track type.
  3. Draft, present, revise, and approve spec.md.
  4. Ask for Task or Sub-task status granularity, default to Sub-task, then draft, present, revise, and approve plan.md from the project workflow.
  5. Recover management paths when needed, generate a safe ID, and run collision checks.
  6. Create artifacts, register the track, and report next steps without starting implementation.

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