setup
Skill1 starsChanged 4 months agoMITView on GitHub
One-time onboarding interview that teaches the copilot your company — populates messaging.md, icp.md, and guardrails.md so every other skill works for your business instead of a generic template. Use when the rep says "setup", "set up the copilot", "onboard", "configure this for my company", or when any skill reports that the reference files still contain `<PLACEHOLDER>` content.
191 other projects use a version of this.
Adopted by
Most recently taken up by
- hydra-db/hydradb-claude-codetheir own version, first seen Nov 8, 2026
- WALKERKILLER/Look-Tongji-Notestheir own version, first seen Nov 8, 2026
- steerlabs/opensteertheir own version, first seen Nov 8, 2026
- ansvisor/ansvisortheir own version, first seen Nov 8, 2026
- dsifry/metaswarmtheir own version, first seen Nov 8, 2026
- anombyte93/prd-taskmastertheir own version, first seen Nov 8, 2026
Used with
Projects with it also use add-voice-transcription, add-discord and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
juancruzmunozalbeloSkilladd-voice-transcription
Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.
Also in 5 projects that use this
MicrosoftSkilladd-discord
Add Discord bot channel integration via Chat SDK.
Also in 11 projects that use this
MicrosoftSkilladd-slack
Add Slack channel integration via Chat SDK.
Also in 11 projects that use this
juancruzmunozalbeloSkilladd-telegram-swarm
Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".
Also in 7 projects that use this
- +8 more from microsoft
Other versions191 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 191
- anthropics/knowledge-work-plugins★ 35ksame name
- garrytan/gbrain★ 32ksame name
- gavrielc/nanoclaw★ 31ksame name
- nanocoai/nanoclaw★ 31ksame name
- qwibitai/nanoclaw★ 31ksame name
- Q00/ouroboros★ 6.3ksame name
- pytorch/executorch★ 5.2ksame name
- agenticnotetaking/arscontexta★ 3.5ksame name
- aws/agent-toolkit-for-aws★ 3.4ksame name
- spotify/portal-ai-plugins★ 2.8ksame name
181 more not listed
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 repository14 other files it gives its agents.
- account-briefSkill
- battlecardSkill
- build-listSkill
- dojoSkill
- draft-sequenceSkill
- handle-replySkill
- meeting-prepSkill
- post-callSkill
- reactivateSkill
- signal-watchSkill
- voice-interviewSkill
- what-worksSkill
- work-inboundSkill
- write-emailSkill
The file
Files
Setup
The copilot ships as a template. This skill fills the three reference files — references/messaging.md, references/icp.md, references/guardrails.md — with the rep's real company, ICP, and messaging, so every other skill drafts on-brand from day one. Run it once; rerun anytime positioning changes.
How to run it
A conversation, not a form. Ask in batches by section, react to answers, and pull real language out of the rep (their words become the messaging). If they can paste an existing positioning doc, sales deck, one-pager, or website URL, take it — extract everything you can from it first, then only ask what's still missing. Confirm each drafted section back before writing it.
Tell the rep up front: budget ~30 minutes, and it's fine to leave a section rough and refine later — a filled file the skills can use beats a perfect one that never ships.
What to gather (map each answer to its destination)
A. Company + positioning → messaging.md
- Company name, one sentence on what the product does, and the category it competes in.
- The one-line position, and the plainer version a prospect would actually say back.
- The core 30-second narrative: what shifted in the market, why the status quo fails, why you.
- 3-5 genuine differentiators — for each, the "so what" business outcome. Push on honesty: can a competitor also claim this? If yes, it's not a differentiator.
- The claims you must NOT make (categories a competitor owns, superlatives you can't back, anything legal hasn't cleared).
- Proof points: customers/scale, third-party validation, quantified outcomes — and which are cleared for cold email vs. need sign-off.
- Anything unreleased or uncleared that must never appear in outbound.
- Any live campaign/webinar/content offer to use as a low-friction CTA (optional).
- Banned words + voice rules for the audience.
B. Who you sell to → icp.md
- Tier 1 / Tier 2 / Tier 3 definitions (who to pursue now, qualify, and never touch).
- Tier 1 firmographics: verticals, size/revenue/stage, geography.
- The observable tech/product/org signals that mean "they have the problem you solve."
- The five 10-point scoring attributes (2 pts each) — keep them evidence-based.
- The trigger events that make the pain urgent NOW, how to spot each, and which is the primary play (⭐).
- The buying committee mapped to the three archetypes — Champion (technical/hands-on evaluator), Practitioner (power user/program owner), Economic Buyer (exec who signs) — with real titles for each.
- What Tier 1 buyers are like (how they evaluate, where they research, what proof lands).
- Real pain quotes per archetype (from calls, reviews, communities) — gold for personalization.
C. Operating rules → guardrails.md
- Enrichment row cap (default 25) and credit threshold that requires a yes (default 500).
- Cold-email word cap (default 80) and whether the sending domain is healthy or needs call-first protection.
- Escalation contacts: your marketing lead (owns campaigns/lists/messaging questions) and your admin (owns the plugin/connectors/workflow) — name and role for each.
Producing the files
Fill each reference file in place, replacing every <PLACEHOLDER> with the rep's answers and removing the template banner line at the top. Keep the existing structure and headings — the other skills depend on them (they reference "Hook #N", "the 10-point rubric", "the trigger events", the three archetype names). Where the rep genuinely has nothing yet, leave a clearly-marked TODO: rather than inventing content — never fabricate proof points, customers, or claims.
Also confirm the tool stack the rep will connect (CRM, research, enrichment, sequencer, Slack) and point them to SETUP.md for the connector steps.
The exit test
After writing, draft one sample cold email using only the newly-filled references (via the write-email skill's rules). Show it to the rep. If it sounds on-brand and accurate, setup is done. If it's off, the gap is in the references — fix the specific section and redraft. Don't call setup complete until the sample would genuinely go out.
Then point the rep at the voice interview: "Run voice interview next (15 min) so drafts sound like you, not just on-brand."
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.

