agentleFS
grace-methodgrace-method/grace-plugin/skills/operations/SKILL.md

operations

Skill0 starsChanged 2 months agoMITView on GitHub

Production readiness and operations guidance. Readiness checklist, user-manual maintenance, incident lifecycle, and RCCA. Use before first release or when managing production systems.

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 3

    Distinctive

    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 skill for live-system readiness and ongoing operational handling.

    line 12
  2. Distinctive:

    Before first release, present the production readiness checklist.

    line 27
  3. Distinctive:

    Use the templates in this skill directory when scaffolding or substantially reshaping operational artifacts.

    line 64

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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

Operations

Use this skill for live-system readiness and ongoing operational handling.

Current Project Context

Production Readiness

!cat docs/06-operations/production-readiness.md 2>/dev/null || echo "No production readiness artifact found."

User Manual

!cat docs/06-operations/user-manual.md 2>/dev/null || cat docs/06-operations/runbook.md 2>/dev/null || echo "No user manual found. It should have been created during design; see the design-review skill."

Recent Incident Records

!find docs/06-operations/incidents -name "*.md" | sort 2>/dev/null || echo "No incident records found."

Interaction Pattern

  1. Before first release, present the production readiness checklist.
    • Monitoring and alerting: are key signals defined?
    • User Manual: does it exist from Stage 3, and has Operations extended it with the machine-facing material — deployment, restart, rollback, on-call? Operations maintains this document; it does not author it at go-live.
    • Keep futures out of the manual. It describes present behaviour, because an operator acts on it directly. Anything designed but not yet shipped stays in the marked <!-- UNSHIPPED: R-NNN --> block that the release's closure step removes, so nobody follows a procedure the product will not perform.
    • Rollback plan: is there a tested path to restore prior state?
    • Operational ownership: is responsibility explicit?
  2. Review the roadmap at the product's own operating cadence.
    • The rhythm comes from the User Manual's calendar — whatever beat the operator actually runs (monthly close, release train, weekly review).
    • Invoke the roadmap skill. This trigger answers what closure cannot: external drift — the world moving, needs changing, the goal shifting. Internal staleness is handled at release closure; drift can only be noticed.
    • It is also the one trigger that recurs when no work is happening, so a missed review is itself an attrition signal worth naming to the human.
  3. For steady-state operations, guide the incident lifecycle.
    • Detect -> Triage -> Respond -> Resolve -> RCCA
  4. Route RCCA findings back to the right stage.
    • Analysis for flawed assumptions or goals
    • Design for structural gaps
    • Implementation for code defects
    • Operations for process, monitoring, or configuration gaps
  5. Route resulting bugs and enhancements back into the normal change pipeline.
    • Operations should not become an untracked side channel for product change.

Outputs

Produce or update these artifacts as needed:

  • docs/06-operations/production-readiness.md
  • docs/06-operations/user-manual.md — extend and maintain; it is created in Stage 3
  • docs/06-operations/incidents/incident-*.md
  • docs/ROADMAP.md — reviewed at the operating cadence via the roadmap skill; not owned here

Use the templates in this skill directory when scaffolding or substantially reshaping operational artifacts.

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.