agentleFS
Sign inStart free
cobusgreylingcobusgreyling/grok-bot-templates/skills/package-evidence/SKILL.md

package-evidence

Skill14 starsChanged 3 months agoMITView on GitHub

Paste this into Grok Bot after a successful run: Save the process we just used as a skill called “Package Evidence”. A useful skill states the six fields from Skills and routines. An agent or Bot run finished and a human needs an evidence pack before a ship/block verdict — what happened, what was verified, what was not. No claim is marked verified without an artifact pointer. Missing tests are listed as missing, not implied by a green story. Evidence…

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Run notes, logs, diffs, or conversation

    line 16
  2. Distinctive:

    Test or review output when it exists

    line 18
  3. Distinctive:

    Do not issue the verdict. That is the human's job.

    line 26
  4. Distinctive:

    No claim is marked verified without an artifact pointer.

    line 30
  5. Distinctive:

    Do not merge, deploy, or tag a release.

    line 40

≈ “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

Package Evidence

Paste this into Grok Bot after a successful run:

Save the process we just used as a skill called “Package Evidence”.

A useful skill states the six fields from Skills and routines.

1. When to use it

An agent or Bot run finished and a human needs an evidence pack before a ship/block verdict — what happened, what was verified, what was not.

2. Required inputs and access

  • Run notes, logs, diffs, or conversation
  • The original request and constraints
  • Test or review output when it exists

3. Sequence of work

  1. Restate the request and the claimed outcome.
  2. Collect artifacts that actually exist (links, files, command output).
  3. Mark each claim verified / unverified / contradicted.
  4. List residual risk and what a human still has to look at.
  5. Do not issue the verdict. That is the human's job.

4. How to validate the result

No claim is marked verified without an artifact pointer. Missing tests are listed as missing, not implied by a green story.

5. What to return

Evidence pack: Request, Artifacts, Verified, Unverified, Residual risk, Questions for the verdict.

6. What requires approval

Do not merge, deploy, or tag a release. Do not write the human's rationale for them.

Type / in the composer to reference a saved skill. If it does not appear, open Settings → Plugins → Yours and enable it for this Bot.

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