setup-team
Skill1 starsChanged 3 months agoMITView on GitHub
Onboard a business onto the team — read the charter, interview for gaps, seed the knowledge base, and lay out the road to the first sale. Run this first, once.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- link7373/agentic-bi-teamtheir own version, first seen Nov 10, 2026
- rafaelgarrafiel/team_skillstheir own version, first seen Oct 16, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- link7373/agentic-bi-team★ 4same name
- rafaelgarrafiel/team_skills★ 2same 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 repository22 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- build-funnelSkill
- close-dealSkill
- connect-toolsSkill
- create-contentSkill
- define-positioningSkill
- design-offerSkill
- experimentSkill
- grow-referralsSkill
- grow-seoSkill
- health-checkSkill
- launch-campaignSkill
- launch-productSkill
- manage-pipelineSkill
- measureSkill
- plan-strategySkill
- research-marketSkill
- review-monthlySkill
- run-adsSkill
- run-outboundSkill
- run-partnershipsSkill
- tune-revopsSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Interview for gaps: Ask the operator about gaps conversationally — one topic at a time, plain language, multiple-choice where possible.
- Distinctive: line 16
Quick verification: If links were provided (site, store, socials), have market-researcher visit them and record honest first impressions — …
- Distinctive: line 17
Seed the knowledge base: Write:
- Very specific: line 29
If knowledge/business-context.md already has status seeded or active, the team is already set up — confirm with the operator before …
- Very specific: line 43
All nine knowledge files above.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
/setup-team — Bring the Team Online
Inputs: a filled (or partially filled) START-HERE.md.
Agents: Head of Growth leads; market-researcher assists with quick verification lookups.
Steps
- Read the charter. Parse every section of
START-HERE.md. Build a gap list of blank, vague, or contradictory answers. - Interview for gaps. Ask the operator about gaps conversationally — one topic at a time, plain language, multiple-choice where possible. "I don't know" is acceptable; record it as an open question for
/research-market, not a blocker. - Classify the business. Model (B2B / B2C / hybrid), sales motion (self-serve page/marketplace vs conversation-led), maturity (nothing built / assets exist / selling already). These drive every future branch.
- Quick verification. If links were provided (site, store, socials), have market-researcher visit them and record honest first impressions — what exists, what state it's in.
- Seed the knowledge base. Write:
knowledge/business-context.md— the classified picture: product, model, motion, maturity, goals, budget, time, constraints, assets, open questions.knowledge/decision-log.md,knowledge/approvals-log.md,knowledge/results-history.md,knowledge/pipeline.md,knowledge/tool-registry.md,knowledge/budget.md,knowledge/competitors.md— initialized with headers and the operator's approval preferences from the charter. Set each file's status header (stub/seeded) honestly.- Existing customers and live leads go into
knowledge/pipeline.mdnow, with a dated next action each. A business that already sells is not starting from zero, and its existing customers are the first source of testimonials (/grow-referrals) and win-loss insight (/close-deal) — the fastest evidence available.
- Confirm the approval contract. Restate the three gates (money, outbound, publishing) and any charter modifications; record in
knowledge/approvals-log.mdas the standing contract. - Seed the first tool connections. From the charter's existing tools and the plan's likely needs, queue
/connect-toolsfor the 1–2 most urgent categories. Don't connect everything — connect what the next 30 days need. - Set up the rhythm. With operator approval, create two scheduled tasks (per
CLAUDE.md→ Operating rhythm & automation): weekly Monday/measure, first-Monday-monthly/review-monthly. Register both inknowledge/tool-registry.mdunder Scheduled automation. If scheduling tools aren't available, record that and note the rhythm runs manually at session start. - Present the road. Show the zero-to-first-sale sequence from
playbook.md§2, marked up for this business: which steps are done, which are next, expected pace given budget/time. Recommend the immediate next skill (usually/research-market).
Before you start
- Required inputs:
START-HERE.mdin any state — even blank; the interview fills gaps. - If
knowledge/business-context.mdalready has statusseededoractive, the team is already set up — confirm with the operator before re-running (re-setup overwrites the business picture; it does not erase logs or results).
If things go wrong
- Operator can't answer core questions (what they sell, to whom) → record as open questions for
/research-market; never invent answers. - Scheduling tools unavailable → note in tool-registry; the rhythm runs manually.
- Operator goes quiet mid-interview → park progress in
knowledge/pending.mdand seed what's known so far.
Outputs
Seeded knowledge/ base; a road-to-first-sale summary the operator can understand in two minutes; the next step queued. Close with the report per templates/skill-report.md.
Writeback
All nine knowledge files above; setup decisions (tag: other) to knowledge/decision-log.md.
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.

