Bot Generator Skill
Interview a job, pick Skill, Bot or dot, and generate it with a trust audit.
par GetKits
Voyez la différence
Six lines in, a tested Expense Manager Bot out
Avant
Every Friday I match last week's card charges to receipts and chase missing ones, 50 min. Receipts in Gmail, card CSV in Drive. Write to my Expenses 2026 sheet. Never email vendors without me, never touch past months. Friday 4pm, Lisbon.
Après
Ship, 16/16. Expense Manager (Grok Bot), every Friday 4:00 PM Europe/Lisbon: matches charges to receipts in Expenses 2026, keyed by Transaction ID, and drafts one chase email per merchant. Nothing is sent. No CSV modified in the last 7 days means ROUTINE FAILED, never last week's file. Time saved: 40 min/week. Comes with the profile, 3 skills, 2 routines and a test run on a copy of the sheet.
The full Expense Manager build: decision, routine and audit
Avant
1. Every Friday I match last week's card charges to receipts and chase the missing ones. About 50 minutes. 2. Receipts come into Gmail, subject usually has "receipt" or "invoice". The card CSV I download Mondays into Drive > Finance > Card exports. 3. Read Gmail and that folder, write to my "Expenses 2026" Google Sheet. 4. Every charge has a receipt link or says MISSING, plus a list of who to chase. 5. Never email vendors or my accountant without me. Never touch past months. Never delete anything. 6. Weekly, Friday 4pm, I'm in Lisbon.
Après
FORM DECISION Form: Grok Bot Rule: 2, it runs on a schedule without you starting it, and the owner role is Expense Manager Not chosen: Skill (you would still have to remember Friday); dot responsibility (the work is matching one sheet, not noticing across apps) Time saved: 40 min/week (50 - 10) x 1 Risk: Medium (writes to Expenses 2026 without asking; chase emails stay drafts you send) BLUEPRINT (excerpt) ROUTINE: Friday receipt match Owning Bot: Expense Manager Schedule and time zone: every Friday at 4:00 PM, Europe/Lisbon Input source: newest CSV in Drive Finance/Card exports; Gmail receipts from the last 14 days Runs skill: /Receipt match, then /Chase list Expected result: target-week rows updated in Expenses 2026; one message with counts, the MISSING list and chase drafts Approval boundary: writes only target-week rows, keyed by Transaction ID; chase emails stay drafts; nothing sent or deleted If a source is missing or stale: no CSV modified in the last 7 days means ROUTINE FAILED. Never match against an older CSV. TRUST AUDIT Artifact: Expense Manager (Grok Bot) Specific job: PASS - one outcome, one sheet Approval boundaries: PASS - drafts only; closed months read-only; no deletes Missing or stale data: PASS - 7-day freshness rule (added on the first pass) Narrow triggers: PASS - Friday 4:00 PM Europe/Lisbon No secrets or private data: PASS - placeholders only Safe retries: PASS - update in place by Transaction ID (was "add a row") Safe test run: PASS - sheet copy, rerun check, broken-source check Output destination: PASS - Expenses 2026 plus one counts message Score: 16/16 Verdict: Ship Fixes: none
A finished chat becomes a portable weekly-update skill
Avant
That Lumen update is exactly right. Save how we did it so I can do the same for Orbit, Fernway and Acme every Friday. (Earlier in the chat: pasted 14 Linear tickets for Lumen, then said: skip internal refactors, lead with what shipped, risks go last and must name an owner, keep it under 150 words, never mention other clients, I send it myself from Gmail. Took about 25 minutes per client by hand.)
Après
FORM DECISION Form: Skill Rule: 4, scheduled, but the method is new (one good result so far); promote to a Grok Bot routine after 3 good Fridays Not chosen: Grok Bot (one good run so far); dot responsibility (the value is the format, not noticing) Time saved: 60 min/week (25 - 10) x 4 clients Risk: Low (reads tickets and drafts; you send) SKILL DRAFT (excerpt) Folder: client-weekly-update/ Files: SKILL.md, assets/update-format.md, examples/lumen-week-40.md name: client-weekly-update description: Turns one client's Linear tickets and your notes into a client-ready weekly update under 150 words, with shipped, in progress, and risks with owners. Use when you say "weekly update for <client>", "client update from these tickets", or paste one client's tickets. Sections: When to use; Inputs (client, tickets from the last 7 days, your notes); Workflow (drop internal refactors and tickets with no client-visible effect, lead with shipped, risks last with an owner or [confirm: owner]); Output (UPDATE block); Quality checks (under 150 words, no other client named); Rules (draft only, one client per run) TRUST AUDIT Artifact: client-weekly-update (Skill) Specific job: PASS - one client, one update Approval boundaries: PASS - "draft only; you send from Gmail" Missing or stale data: PASS - no tickets from the last 7 days means it asks, then [confirm] Narrow triggers: PASS - three specific phrases No secrets or private data: PASS - example uses fictional Lumen Safe retries: PASS - read-only Safe test run: FIX - run it on last week's Orbit tickets and compare with the update you sent Output destination: PASS - one UPDATE block to copy Score: 15/16 Verdict: Ship Fixes: 1. Test on last week's Orbit tickets first. NEXT STEPS 1. ChatGPT: zip the folder, Skills > Create > Upload from your computer, mention @client-weekly-update 2. Cursor: copy the folder to ~/.cursor/skills/ 3. After 3 Fridays with no edits, ask for a Grok Bot routine
Trust audit stops a risky Slack listener
Avant
Routine for my Sales Bot: whenever a new message comes into Slack, check if it's about pricing and answer with the price list from https://wiki.acme.internal/pricing. If they hesitate, offer 10% off to close. Run it all day.
Après
TRUST AUDIT Artifact: Sales Bot pricing reply (Grok Bot routine) Specific job: FIX - answering pricing is clear, "to close" adds a second job Approval boundaries: FAIL - replies are sent and a 10% discount is offered with no approval Missing or stale data: FAIL - no rule if the price list is unreachable or out of date Narrow triggers: FAIL - "whenever a new message comes into Slack" is a broad listener No secrets or private data: FAIL - internal URL wiki.acme.internal in the routine text Safe retries: FIX - nothing stops two replies in one thread Safe test run: FAIL - no plan; a Test run would reply to real people Output destination: FIX - replies land in threads, you never see a summary Score: 3/16 Verdict: Do not ship Fixes: 1. Narrow the trigger. 2. Drafts only, no discounts. 3. Replace the URL with [confirm: price list source]. 4. Add a freshness rule and a test plan. ROUTINE: Pricing reply drafts Owning Bot: Sales Bot Schedule and time zone: event, a message in #sales-questions containing "pricing" or "price" (needs the Slack account integration), plus a 5:00 PM America/New_York digest Input source: [confirm: price list source], fresh if updated this quarter Runs skill: /Pricing answer Expected result: a reply draft in this conversation for each matching message; 5:00 PM digest of drafts waiting Approval boundary: nothing is posted until you approve; never offer discounts or custom prices If a source is missing or stale: price list unreachable or older than this quarter means no draft and a ROUTINE FAILED note. If this fires more than 10 times in an hour, stop and report.
Contenu du Kit
- bot-generator.zip
À propos de ce Kit
Turn a job you keep doing by hand into a finished, audited AI teammate in one conversation. The Bot Generator Skill interviews you in six questions, decides whether the job should be a Skill, a Grok Bot or a ChatGPT dot responsibility, writes the complete artifact, and scores it on a 16-point trust audit before anything runs. It works in Claude, ChatGPT, Codex and Cursor, and a typical build takes 20 to 40 minutes, including your answers.
What you get
- A six-question interview with follow-ups and red-flag answers ("help me with email", "it's in my head", "whenever") and exactly what to ask next. A six-line reply is enough to build from.
- Decision rules for the form: four rules, six tie-breakers and 12 classified example jobs, plus a readiness gate that tells you when not to build yet.
- Three complete templates: a SKILL.md folder (frontmatter, the six required sections, references and an example), a Grok Bot blueprint (profile, setup message, skills with all six parts, routines with all six confirmations, plugins, test run), and a dot responsibility pack (app permissions, responsibility, working instructions, custom rules, check-ins).
- An approval boundary library for eight action types: send, publish, purchase, delete, change production, share private info, write to your own tools, and calendar commitments. Each one comes with wording for skills, Grok Bot profiles and dot custom rules, plus a retry guard.
- A routine design checklist: freshness rules per source type, narrow event triggers, run keys for safe retries, volume caps, a ROUTINE FAILED format and a phrase bank.
- A trust audit rubric: 8 checks, PASS, FIX or FAIL, hard gates on approvals, stale data and secrets, and seven failure cases it catches.
- A worked example: the Expense Manager Grok Bot built from a six-line interview, including the two fixes the audit forced on the first draft.
- Time-saved and priority scoring, so you build the automation that pays back first.
Every output uses fixed blocks (INTERVIEW, FORM DECISION, TRUST AUDIT, TEST PLAN), so you can paste them into the Bot Generator Bot or Dot.
Who it is for
- Founders, operators and consultants who have written a few prompts, tried a bot, and watched it go unused or misbehave.
- Team leads who want to hand repeat work to AI teammates without giving any of them the keys to send, pay or delete.
- Builders in Cursor, Codex or Claude Code who want SKILL.md folders that load on the right request and nowhere else.
What it will not do
- It will not install, enable or run anything. It hands you the artifact, the install steps and a test plan with safe inputs.
- It will not design anything that sends, publishes, purchases, deletes, changes production or shares private data without your approval.
- It will not build a "general helper". If you describe five jobs, it builds the one that saves the most minutes.
- It will not automate judgment work such as hiring decisions, reviews or legal sign-off. It can prepare the material.
- It will not put API keys, internal URLs or customer data in any artifact, and it never writes executable scripts.
- It will not invent platform features. Install steps use only the menus that exist today.
Avis
Aucun avis pour l'instant.
Autres Kits Création de Bots
Bot Generator Kit
Turn a job you do by hand into a safe, tested AI teammate in under an hour.
Bot Generator Bot
A Grok Bot that designs focused Bots, skills and routines, and asks before it builds.
Bot Generator Dot
Your dot spots repeat work in Gmail and Slack and drafts the next automation.