agentleFS
Sign inStart free
rafaelgarrafielrafaelgarrafiel/team_skills/skills/ask-team/SKILL.md

ask-team

Skill2 starsChanged 29 days agoMITView on GitHub

Ask which team hat, advisor or flow fits your situation. A router over this plugin and how it sits on mattpocock/skills.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. l3a0/claude-plugins★ 19same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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
  1. Very specific:

    Every advisor and reviewer writes a file under .scratch/<feature-slug>/team/ (contract: team-contribution).

    line 34

≈ “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

Ask Team

The team is two hats the main session wears and eight subagents it dispatches. You keep invoking the skills you already know; the hat runs inside them.

With Matt's skills installed

You runHatWho is dispatched
/grill-with-docs, /grill-meProduct Owner (team-grill)LGPD, security, QA advisors every dispatch; UX when a screen is in play; DBA when data is
/to-specProduct Ownerevery active advisor reviews the draft spec; maintained objections land in ## Team positions
/to-ticketsTech Lead (team-implement)senior developer checks implementability and missing blocking edges
/implementTech Leadone senior developer per ticket in parallel worktrees; QA reviews every branch, UX, DBA, security, LGPD by what the diff touches; two failed rounds escalate to you
/implement, in a cockpitTech Leadafter the merge, offers one knowledge keeper per project touched, to write the delivery's record, ADRs and glossary terms into it; only on your yes
/triageProduct Ownersecurity on suspected vulnerabilities, QA to reproduce
/diagnosing-bugsTech LeadQA locks the red command, senior developer fixes with a regression test
/improve-codebase-architectureTech Leadsenior developer and DBA survey candidates

Unchanged and team-free: /wayfinder, /prototype, /research, /handoff, /resolving-merge-conflicts, /wizard, /code-review on its own.

Standalone

Without Matt's skills, run the hats directly: /team-grill for the interview (embedded rounds, advisors as above) and /team-implement over tickets that already exist in your tracker, or over a spec the Tech Lead splits with your confirmation. Spec and ticket generation, triage, bug diagnosis, wayfinding, prototypes and research are Matt's; install mattpocock-skills to get them.

Where things land

Every advisor and reviewer writes a file under .scratch/<feature-slug>/team/ (contract: team-contribution). Read them where the decision is made: a maintained objection is quoted in the spec, the ticket or the review verdict, never only in a summary.

Which version is installed

Read metadata.version in the frontmatter of this file: it is the version of the skills you are running now. docs/agents/team.md records, on its Team-skills version line, the version that last set the repo up. When the two differ, say so: the skills were updated after the setup, and re-running /setup-team records what the new version added (it asks only the missing sections). A team.md with no such line was written by a version before 0.4.1. Do not look in the installer's lockfile: skills-lock.json and .skill-lock.json hold the source and a hash of each skill, never a semantic version.

Precondition

/setup-team, once per repo. It reuses Matt's tracker and domain settings when they exist and asks for the profile, the advisors, the artifact language and the limits.

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