agentleFS
fjrevoredofjrevoredo/mini-diarium/.agents/skills/runbooks/SKILL.md

runbooks

Skill321 starsChanged 7 days agoMITView on GitHub

Route low-frequency Mini Diarium maintenance workflows to one selected runbook. Use only for manual or exceptional project workflows that are intentionally not registered as standalone top-level skills.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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:

    Use this dispatcher to load one specific Mini Diarium runbook from this library.

    line 11
  2. Distinctive:

    After selecting an entry, follow that entry's instructions completely, including any required scripts, assets, evals, or validation steps.

    line 24
  3. Distinctive:

    If the request is ambiguous, ask the user to choose the runbook instead of inventing one.

    line 25
  4. Distinctive:

    If the requested entry is unsupported, say so plainly and do not load an unrelated skill.

    line 26
  5. Distinctive:

    If the requested name is not listed in the table above:

    line 44
  6. Distinctive:

    do not search the filesystem for ad hoc alternatives.

    line 47
  7. Distinctive:

    do not fabricate a new runbook name or workflow.

    line 48

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Runbooks

Use this dispatcher to load one specific Mini Diarium runbook from this library.

This library is manual-first. Do not guess a runbook when the user's request does not clearly match one of the supported entries.

Usage

  • Codex: $runbooks <entry>
  • Claude Code: /runbooks <entry>

Routing Rules

  1. Identify the requested runbook entry from the supported table below.
  2. Load exactly one selected nested ENTRY.md unless the user explicitly asks for a multi-runbook task that genuinely spans several workflows.
  3. After selecting an entry, follow that entry's instructions completely, including any required scripts, assets, evals, or validation steps.
  4. If the request is ambiguous, ask the user to choose the runbook instead of inventing one.
  5. If the requested entry is unsupported, say so plainly and do not load an unrelated skill.

Available Skills

EntryUse forPath
add-localeAdding a brand-new Mini Diarium locale end to endskills/add-locale/ENTRY.md
apply-dependency-prsApplying dependency-update pull requests safelyskills/apply-dependency-prs/ENTRY.md
diagram-maintainerUpdating and validating Mermaid or D2 documentation diagramsskills/diagram-maintainer/ENTRY.md
grillingInterviewing a user relentlessly toward shared understanding via design-tree rounds, then optionally recording an ADRskills/grilling/ENTRY.md
implementation-reviewReviewing a completed implementation against its plan and validationsskills/implementation-review/ENTRY.md
integrate-stale-prManually integrating an external PR that can no longer merge cleanlyskills/integrate-stale-pr/ENTRY.md
pre-releaseRunning the pre-release checklist before taggingskills/pre-release/ENTRY.md
review-external-prReviewing an external contributor PR and drafting the maintainer responseskills/review-external-pr/ENTRY.md
update-app-iconsReplacing the app logo and regenerating platform iconsskills/update-app-icons/ENTRY.md

Unsupported Requests

If the requested name is not listed in the table above:

  • report that runbooks does not provide that entry;
  • do not search the filesystem for ad hoc alternatives;
  • do not fabricate a new runbook name or workflow.

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.