agentleFS
bostonaholicbostonaholic/team/skills/team-design/SKILL.md

team-design

Skill11 starsChanged 4 months agoMITView on GitHub

Use for drafting technical designs with independent review.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 4 are distinctive, and 8 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.

  • 8

    Very specific

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

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

    Before this operation, read artifact schema.

    line 8
  2. Very specific:

    Before each consuming step, read its linked shared rules.

    line 9
  3. Distinctive:

    If a required read fails, stop that step and report its resolved path.

    line 10
  4. Distinctive:

    Before each dispatch or retry, read host dispatch and supply its resolved installed paths.

    line 12
  5. Distinctive:

    Before finalizing prose you author, read the writing standards.

    line 18
  6. Distinctive:

    No mid-run prompt fires.

    line 20
  7. Very specific:

    Printed a path: use it as $ARGUMENTS; announce it when no explicit arg was given.

    line 32
  8. Very specific:

    Printed nothing: do not hard-error. Fire AskUserQuestion with a Setup header and labeled options:

    line 34
  9. Very specific:

    Use the directory resolved in ## Input.

    line 42
  10. Very specific:

    If $ARGUMENTS/6-design.md already exists, skip to step 3 — never re-draft an existing design (durable state rules).

    line 43
  11. Very specific:

    Design review gate: Run "<team-skill-dir>/scripts/design-review-status.sh" "$ARGUMENTS".

    line 49
  12. Very specific:

    When it returns DONE, a fresh round runs.

    line 76

≈ “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

Before this operation, read artifact schema. Before each consuming step, read its linked shared rules. Resolve links from this installed SKILL.md directory. If a required read fails, stop that step and report its resolved path. Never use checkout fallback or recursive loading.

Before each dispatch or retry, read host dispatch and supply its resolved installed paths.

Before review dispatch, supply the installed plugin root, the resolved skills/team/references/design-reviewer.md path, the absolute installed skills/team/ directory as the base of that brief's links, and the resolved paths of the manuals its ## Review brief links, all in skills/team/references/: code-reviewer.md, code-standards.md, design-template.md, decisions.md, findings.md, writing.md, and cross-model-review.md when the prompt carries ## External review input. Require reads before work.

Team Design

Before finalizing prose you author, read the writing standards. Relay completed review reports unchanged.

No mid-run prompt fires.

Input

$ARGUMENTS is the artifact directory docs/plans/<id>/; if empty, the discovery command resolves it. Resolve <team-skill-dir> to the absolute directory containing skills/team/SKILL.md. From the repository root, run:

"<team-skill-dir>/discover-topic.sh" "${ARGUMENTS:-}" "5-research.md"
  • Printed a path: use it as $ARGUMENTS; announce it when no explicit arg was given.
  • Printed nothing: do not hard-error. Fire AskUserQuestion with a Setup header and labeled options:
    • Run the producer — run /team-research docs/plans/<id>/ to produce 5-research.md.
    • Give a path — the user supplies the docs/plans/<id>/ directory.

Execution

  1. Use the directory resolved in ## Input.
  2. If $ARGUMENTS/6-design.md already exists, skip to step 3 — never re-draft an existing design (durable state rules). Otherwise dispatch design-author; it writes $ARGUMENTS/6-design.md with frontmatter revision: 0. Go to step 3 only when it returns DONE, or, inline, when the body's ## Return reaches DONE. Route any other return per host dispatch.
  3. Design review gate. Run "<team-skill-dir>/scripts/design-review-status.sh" "$ARGUMENTS". Exit 0 (passed): skip to step 4 — never re-review a passed design. Exit 1 (pending): its second field <n> is this round's number. Exit 2: stop and report its stderr.

    Each round:

    a. Cross-model pass. Read the cross-model review and run its ## Design-review pass (gate: TEAM_DISABLE_CROSS_MODEL). Any skip continues with the reviewer alone; the pass never blocks the gate. b. Review. Read the ## Review brief from the design reviewer brief, substitute the artifact directory, attach the paths named at the top of this file, and give it to a read-only Explore subagent in a fresh context window. c. Record. Write the reviewer's report verbatim to a scratch file outside $ARGUMENTS with the Write tool, then run node "<team-skill-dir>/scripts/record-design-review.mjs" --dir "$ARGUMENTS" --report <report-file>. Its JSON line names the round and verdict. Exit 3 is an unparseable verdict (below); any other non-zero exit halts loudly with its stderr. d. Act on the verdict:

    • APPROVE or COMMENT — the review passes. Advance.
    • REQUEST CHANGES — re-dispatch design-author with the reviewer's findings verbatim; it re-drafts and increments revision: <n+1>. When it returns DONE, a fresh round runs. No round cap; the loop ends on the verdict.
    • Unparseable verdict or reviewer crash — retry the review once with the error; on second failure, halt loudly. Fail closed — never advance on a missing verdict (verified results rules).
  4. Stop once $ARGUMENTS/6-design.md exists and design-review-status.sh exits 0.

Report design path and tell the user: "Next: run /team-structure docs/plans/<id>/"

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.