agentleFS
Sign inStart free
AtlasOmniaAtlasOmnia/hermes-custom-pack/skills/hermes-nightly-self-check-decisions/SKILL.md

hermes-nightly-self-check-decisions

Skill75 starsChanged 4 months agoMITView on GitHub

hermes-nightly-self-check-decisions — Record decisions from nightly self-check findings so behavior is consistent.

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write the decision as an executable rule (what to do), not a description of what was done.

    line 27
  2. Distinctive:

    If the finding is resolved by a change to config, skills, or process, note where that change lives so the next check can verify it.

    line 28
  3. Distinctive:

    Do not record credentials, tokens, or private paths in the log — reference locations by role (for example "the primary model endpoint" or …

    line 29
  4. Distinctive:

    If the same class of finding recurs, the decision should tighten the check or the rule, not just repeat the note.

    line 30

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Hermes Nightly Self-Check — Decisions Log

Purpose: Record decisions made from hermes-nightly-self-check findings so behavior is consistent across sessions.

How to record

Each entry captures one finding and the decision it produced. Use this format:

### YYYY-MM-DD — Short issue title (Issue #N)
- Issue: What the self-check flagged — the symptom, where it came from, and why it happened.
- Decision: The rule or fix chosen, stated so a future session can apply it without re-litigating.

Rules:

  • One entry per finding; append chronologically under Decision history.
  • Write the decision as an executable rule (what to do), not a description of what was done.
  • If the finding is resolved by a change to config, skills, or process, note where that change lives so the next check can verify it.
  • Do not record credentials, tokens, or private paths in the log — reference locations by role (for example "the primary model endpoint" or "the profile config") instead.
  • If the same class of finding recurs, the decision should tighten the check or the rule, not just repeat the note.

Decision history

Starter template (Example #1)

  • Issue: Nightly check flagged a mismatch between two config locations for the same setting.
  • Decision: Keep one location canonical; document the relationship so future checks do not flag it as a conflict.

Setup flow (Example #2)

  • Issue: A tool call failed because an argument was passed as null.
  • Decision: Always specify an explicit value; never pass null or omit the argument. Default to the safest explicit value when unsure.

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.

Reviews can't be read right now.

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