agentleFS
Sign inStart free
VodouAIVodouAI/OS/skills/my-skills/turn-log-smoke/SKILL.md

turn-log-smoke

Skill1 starsChanged 4 months agoApache-2.0View on GitHub

A one-shot skill that runs straight through to a model call, so the turn log gets a real `skill` lane to grade. No menus, no tools, no stopping point.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Every other skill in the catalogue either stops at a numbered menu (STOPPING POINT) or delegates to MCP tools.

    line 19
  2. Distinctive:

    Keep it that way. If this ever grows a menu, a tool call, or a stopping point, it stops being able to verify the thing it exists to verify.

    line 25
  3. Distinctive:

    Do not present a numbered menu or ask the user to choose.

    line 43
  4. Distinctive:

    Do not call a tool, a server, or another skill.

    line 44
  5. Distinctive:

    Do not stop and wait. This skill has no stopping point by design.

    line 45

≈ “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

Turn-log smoke

You are answering a smoke test for Vodou's turn log (PLAN-TRUTHFUL-TURN row P9.1). The point is not the answer — it is that this skill LOADED, contributed a skill lane to the assembled prompt, and reached a model call, so vodou-core turn --last --derive has a turn with a skill lane to reconstruct.

Why this skill exists at all

Every other skill in the catalogue either stops at a numbered menu (STOPPING POINT) or delegates to MCP tools. Both are correct designs and both mean the same thing for P9.1: the turn ends before a model call, so the log never gets a skill lane to grade. Verifying the lane needed a skill whose whole job is to run through — so this is that skill, and nothing else.

Keep it that way. If this ever grows a menu, a tool call, or a stopping point, it stops being able to verify the thing it exists to verify.

What to do

Reply with exactly one short paragraph, in your own words, answering whatever the user asked alongside /skill turn-log-smoke. If they asked nothing, say what the turn log is for in two sentences.

Then, on its own final line, print:

turn-log-smoke: reached the model

That last line is the observable. A turn carrying it, plus a skill lane in turn_events, is P9.1 passing.

What NOT to do

  • Do not present a numbered menu or ask the user to choose.
  • Do not call a tool, a server, or another skill.
  • Do not stop and wait. This skill has no stopping point by design.

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