BotShelf Vampire BOTSHELF VAMPIRE Register

GROK BOT TOOLS · CHECKLIST

Review a skill learned from a demonstration

Turns a demonstrated workflow draft into instructions with decision rules, failure handling and a safe example. Stops before sending, publishing, payment, deletion or production changes.

No sign-upChecklistGrok BotSkillsUntested

Where it goes

Nothing to paste. This is a list for you to work through with the app open. You can also paste it into a chat and ask the Bot to walk you through it one step at a time.

First three moves

  1. Fill the blanks, starting with the result you expect from one safe example.
  2. Open the learned draft and compare its steps with the demonstrated workflow.
  3. Add the decision rules, failure handling and approval boundary before a safe trial.

Where it stops

Blanks to fill

BlankWhat goes there
[SKILL_NAME]The name of the skill draft learned from the demonstration.
[EXPECTED_RESULT]The observable result and the details you will compare.
[INPUT_SOURCE]The permitted source and access needed for the task.
[SAFE_EXAMPLE]A non-sensitive example that cannot cause external actions.

Replace every bracket. Leave none behind.

The text

Download text.md Fork it Results & questions

Unofficial checklist: turn a skill learned from one demonstration into instructions you can rely on reading.

1. Write [EXPECTED_RESULT] first: what the finished work looks like and which details you will compare.
2. Open [SKILL_NAME], the draft made from your demonstration. Read it against what you actually did. A draft from one pass knows one path only.
3. Check that no login, code or card number was typed during the recording. If one was, remove it from the draft and change that credential. Sign-ins go through the secure handoff, not the recording.
4. Name [INPUT_SOURCE] in the draft: which site or app, which account, and how to tell the right record from a similar one.
5. Add decision rules. For each place where you chose by eye, write the condition. Add when to stop because no choice is clearly right.
6. Add failure handling: which step failed, what was already done, what is left. A finished step is not repeated.
7. Add a missing-data rule: unreadable, absent or old input is reported as a gap. Nothing is filled in from memory.
8. Add the approval boundary: stop before sending, publishing, purchasing, paying, deleting or changing production.
9. Add a description. Teammates and their Bots use it to decide when the skill applies, and a skill cannot be published to a team without one.
10. Pick [SAFE_EXAMPLE]: real enough to exercise the steps, with no private data and no way to cause an outside action.
11. Run the skill once on it. Do not approve any outside action during this run.
12. Compare the output with [EXPECTED_RESULT]. Write down each difference and fix the draft, then run it again.
13. Repeat the safe run whenever the site, app or source format changes. Until it passes again, treat the skill as a draft.

License: MIT. Free, no sign-up. Use is at your own risk. BSV does not run it or set it up for you.

What it adds to the official page

The official page says a learned skill remains a draft that needs rules, failure handling and approval boundaries. This checklist adds an expected-result comparison and a record of what needs another trial.

Sources

The product facts in this text come from these official pages, read on 2026-11-18. Products change: when a page and this text disagree, the page is right.

All Grok Bot tools Download all (ZIP) Search the shelf