team-question
Skill11 starsChanged 3 months agoMITView on GitHub
Use for decomposing features into tasks and research questions.
In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- create-team-skillSkill
- version-bumpSkill
- team-code-reviewSkill
- team-designSkill
- team-fixSkill
- team-implementSkill
- team-migrateSkill
- team-planSkill
- team-prSkill
- team-researchSkill
- team-security-reviewSkill
- teamSkill
- team-structureSkill
- team-updateSkill
- team-worktreeSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Before each dispatch or retry, read host dispatch and supply its resolved installed paths.
- Distinctive: line 9
Before artifact work, read artifact schema.
- Distinctive: line 10
Before handling external values, read external-data rules.
- Distinctive: line 14
Before finalizing prose you author, read the writing standards.
- Very specific: line 16
Run the QUESTION phase only, then stop.
- Distinctive: line 33
Never bare-stop with a "describe it" demand when context is available.
≈ “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.
Files
Before each dispatch or retry, read host dispatch and supply its resolved installed paths. Before artifact work, read artifact schema. Before handling external values, read external-data rules.
Team Question
Before finalizing prose you author, read the writing standards.
Run the QUESTION phase only, then stop. The phase writes, in docs/plans/<id>/:
1-task.md— the human's full intent. Never read byresearcherorfile-finder.2-questions.md— neutral research questions without intent; the only fileresearcherandfile-finderread.3-prd.md— only under## Conditional PRDinskills/team/playbooks/question.md.4-repos.md— only when the topic spans more than one repository: each involved repo's slug, absolute path, and role.
Execution
Resolve
$ARGUMENTSto a description:- Empty: discover, do not demand. Read recent
git logactivity and the repo'sREADME/CLAUDE.mdto propose a likely topic; useAskUserQuestionwith labeled options only for a genuine gap in intent. Never bare-stop with a "describe it" demand when context is available. - Ticket-only: ask the user for context, or fetch the issue body through a configured tracker integration.
- Issue URL: run
gh issue view <url> --json title,body(or equivalent) and use the title plus body as the description. - Free text: use directly.
A ticket identifier (e.g.
ENG-1234) is recorded asticketIdin1-task.mdfrontmatter. The orchestrator calls no ticketing system.- Empty: discover, do not demand. Read recent
- Choose
<kebab-topic>: a 2–4 word kebab-case slug derived from the description. Resolve<team-question-skill-dir>to the absolute directory containing thisSKILL.md. From the repository root, run"<team-question-skill-dir>/scripts/prepare-plan-dir.sh" [--ticket <TICKET>] <kebab-topic>, passing--ticketonly when a ticket identifier is present. Itsdir=line isdocs/plans/<id>/. - Handle its exit code. Exit 2: fix the topic or ticket its stderr names and rerun. Exit 1 or 3: stop and report its stderr.
- Resume detection from its
state=line:new: the questioner writes every artifact.questions-only: re-read1-task.mdinstead of overwriting it; the questioner only writes2-questions.md.complete: skip dispatch and go to the report.
- Dispatch the
questioneragent with the full description and the target directorydocs/plans/<id>/. It writes the artifacts above. - Stop once the rerun reports
state=complete: rerun the step 2 command with--date <date>from its firstdate=line. Do not continue to RESEARCH. Any other state means the questioner did not write1-task.mdand2-questions.md; report that and stop.
Report:
- Path to
1-task.mdand2-questions.md(and3-prd.md/4-repos.mdwhen written) - Topic slug and
<id> - Mode: single-repo, or multi-repo with the involved repo slugs
- Tell the user: "Next: run
/team-research docs/plans/<id>/"
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
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.

