team-design
Decide the approach before any code is written. The design-author drafts the ~200-line design document, resolving its own open questions autonomously as recorded assumptions, then an adversarial design review gates advancement. Trigger on "design this", "let's align on the approa
Install
npx skills add https://github.com/bostonaholic/team/tree/main/skills/team-design
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install bostonaholic-team@llmmart
git clone https://github.com/bostonaholic/team.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole bostonaholic/team collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
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/references/ 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
AskUserQuestionwith aSetupheader and labeled options:- Run the producer — run
/team-research docs/plans/<id>/to produce5-research.md. - Give a path — the user supplies the
docs/plans/<id>/directory.
- Run the producer — run
Execution
Use the directory resolved in
## Input.If
$ARGUMENTS/6-design.mdalready exists, skip to step 3 — never re-draft an existing design (durable state rules). Otherwise dispatchdesign-author; it writes$ARGUMENTS/6-design.mdwith frontmatterrevision: 0. Go to step 3 only when it returnsDONE, or, inline, when the body's## ReturnreachesDONE. Route any other return per host dispatch.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:
- 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. - Review. Read the
## Review brieffrom the design reviewer brief, substitute the artifact directory, attach the paths named at the top of this file, and give it to a read-onlyExploresubagent in a fresh context window. - Record. Write the reviewer's report verbatim to a scratch file
outside
$ARGUMENTSwith the Write tool, then runnode "<team-skill-dir>/scripts/record-design-review.mjs" --dir "$ARGUMENTS" --report <report-file>. Its JSON line names theroundandverdict. Exit 3 is an unparseable verdict (below); any other non-zero exit halts loudly with its stderr. - Act on the verdict:
- APPROVE or COMMENT — the review passes. Advance.
- REQUEST CHANGES — re-dispatch
design-authorwith the reviewer's findings verbatim; it re-drafts and incrementsrevision: <n+1>. When it returnsDONE, 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).
- Cross-model pass. Read the
cross-model review and run
its
Stop once
$ARGUMENTS/6-design.mdexists anddesign-review-status.shexits 0.
Report design path and tell the user:
"Next: run /team-structure docs/plans/<id>/"
Files (team)
-
agents
-
openai.yaml 185 B
Loading…
-
-
SKILL.md 4.6 KB
--- name: team-design description: 'Use for drafting technical designs with independent review.' effort: medium argument-hint: "[docs/plans/<id>/]" --- Before this operation, read [artifact schema](../team/references/artifacts.md). Before each consuming step, read its linked shared rules. Resolve links from this installed `SKILL.md` directory. If a required read fails, stop that step and report its resolved path. Never use checkout fallback or recursive loading. Before each dispatch or retry, read [host dispatch](../team/references/15-host-dispatch.md) and supply its resolved installed paths. Before review dispatch, supply the installed plugin root, the resolved `skills/team/references/design-reviewer.md` path, the absolute installed `skills/team/references/` directory as the base of that brief's links, and the resolved paths of the manuals its `## Review brief` links, all in `skills/team/references/`: `code-reviewer.md`, `code-standards.md`, `design-template.md`, `decisions.md`, `findings.md`, `writing.md`, and `cross-model-review.md` when the prompt carries `## External review input`. Require reads before work. # Team Design Before finalizing prose you author, read the [writing standards](../team/references/writing.md). Relay completed review reports unchanged. No mid-run prompt fires. ## Input `$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: ```sh "<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 `$ARGUMENTS/6-design.md` already exists, skip to step 3 — never re-draft an existing design ([durable state rules](../team/principles/durable-state.md)). Otherwise dispatch [`design-author`](../../agents/design-author.md); it writes `$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" "$ARGUMENTS"`. Exit 0 (`passed`): skip to step 4 — never re-review a passed design. Exit 1 (`pending`): its second field `<n>` is this round's number. Exit 2: stop and report its stderr. Each round: a. **Cross-model pass.** Read the [cross-model review](../team/references/cross-model-review.md) and run its `## Design-review pass` (gate: `TEAM_DISABLE_CROSS_MODEL`). Any skip continues with the reviewer alone; the pass never blocks the gate. b. **Review.** Read the `## Review brief` from the [design reviewer brief](../team/references/design-reviewer.md), substitute the artifact directory, attach the paths named at the top of this file, and give it to a read-only `Explore` subagent in a [fresh context window](../team/references/step-delegation.md#fresh-context). c. **Record.** Write the reviewer's report verbatim to a scratch file outside `$ARGUMENTS` with the Write tool, then run `node "<team-skill-dir>/scripts/record-design-review.mjs" --dir "$ARGUMENTS" --report <report-file>`. Its JSON line names the `round` and `verdict`. Exit 3 is an unparseable verdict (below); any other non-zero exit halts loudly with its stderr. d. **Act on the verdict:** - **APPROVE or COMMENT** — the review passes. Advance. - **REQUEST CHANGES** — re-dispatch [`design-author`](../../agents/design-author.md) with the reviewer's findings verbatim; it re-drafts and increments `revision: <n+1>`. When it returns `DONE`, a fresh round runs. No round cap; the loop ends on the verdict. - **Unparseable verdict or reviewer crash** — retry the review once with the error; on second failure, halt loudly. Fail closed — never advance on a missing verdict ([verified results rules](../team/principles/verified-results.md)). 4. **Stop once `$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>/`"**
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.