0025 — Operate skills: write-runbook, incident-diagnosis, post-mortem, inspect-deployment #44

New Issue

Claude · 2026-06-28T17:12:43Z

Claude commented

2026-06-28 17:12:43 +00:00

Type: HITL
Parent PRD: docs/prd/chunk-3-skills-library.md

What to build

The 4 operate phase skills. All are new. Authored via write-skill (0018), evals via write-eval (0017).

Skills and trigger descriptions:

Flat name	Trigger description
`write-runbook`	Write runbook, operational guide, on-call playbook
`incident-diagnosis`	Diagnose this incident, analyse these logs, root cause analysis
`post-mortem`	Write post-mortem, incident review, after-action report
`inspect-deployment`	Check deployment health, container status, what's running

Key constraints per skill:

write-runbook: covers common failure modes, detection steps, remediation steps, and escalation path; written for on-call engineers under pressure
incident-diagnosis: produces structured finding with confidence levels; never recommends production remediation directly — diagnosis only, human approves remediation
post-mortem: blameless format; covers timeline, root cause analysis, and governance change (what process/rule changes prevent recurrence)
inspect-deployment: read-only; uses Docker MCP and/or K8s MCP when configured; summarises health without modifying state

Implementation notes

Follow the per-skill workflow defined in docs/notes/skill-implementation-workflow.md.

Known upstream sources to review:

bmad-method/bmad-method — BMAD ops role patterns
Google SRE book patterns for blameless post-mortem and runbook formats (public domain principles)
Search agentskills.io and GitHub for open-source ops/operate skill implementations

Acceptance criteria

All 4 SKILL.md files exist at .agents/skills/<skill-name>/SKILL.md; metadata.category: operate; authoring standard met
incident-diagnosis explicitly states it produces diagnosis only and does not recommend production remediation
post-mortem uses blameless format
inspect-deployment is read-only; uses MCP when available
source: fields populated for any adopted upstream content
Each skill has a co-located eval at .agents/evals/operate/<skill-name>/eval.yaml via write-eval
install.sh deploys all 4 to ~/.agents/skills/
HITL: human runs behavioral test per skill
HITL: human reviews each SKILL.md and eval before committing
Per-skill process followed for all 4 skills: source discovery → source review → conflict check → synthesis grill → co-write iteratively
Trigger description for each skill tested against explicit, implicit, and negative queries before body written
eval.yaml for each skill contains all 5 required test types
Body ≤500 lines for each skill
docs/spec/overview.md updated to reflect all 4 skills deployed

Blocked by

0016 (per-skill workflow)
0017 (write-eval)
0018 (write-skill)

**Type:** HITL **Parent PRD:** `docs/prd/chunk-3-skills-library.md` ## What to build The 4 operate phase skills. All are new. Authored via `write-skill` (0018), evals via `write-eval` (0017). **Skills and trigger descriptions:** | Flat name | Trigger description | |---|---| | `write-runbook` | Write runbook, operational guide, on-call playbook | | `incident-diagnosis` | Diagnose this incident, analyse these logs, root cause analysis | | `post-mortem` | Write post-mortem, incident review, after-action report | | `inspect-deployment` | Check deployment health, container status, what's running | **Key constraints per skill:** - `write-runbook`: covers common failure modes, detection steps, remediation steps, and escalation path; written for on-call engineers under pressure - `incident-diagnosis`: produces structured finding with confidence levels; never recommends production remediation directly — diagnosis only, human approves remediation - `post-mortem`: blameless format; covers timeline, root cause analysis, and governance change (what process/rule changes prevent recurrence) - `inspect-deployment`: read-only; uses Docker MCP and/or K8s MCP when configured; summarises health without modifying state ## Implementation notes Follow the per-skill workflow defined in `docs/notes/skill-implementation-workflow.md`. **Known upstream sources to review:** - `bmad-method/bmad-method` — BMAD ops role patterns - Google SRE book patterns for blameless post-mortem and runbook formats (public domain principles) - Search agentskills.io and GitHub for open-source ops/operate skill implementations ## Acceptance criteria - [ ] All 4 SKILL.md files exist at `.agents/skills/<skill-name>/SKILL.md`; `metadata.category: operate`; authoring standard met - [ ] `incident-diagnosis` explicitly states it produces diagnosis only and does not recommend production remediation - [ ] `post-mortem` uses blameless format - [ ] `inspect-deployment` is read-only; uses MCP when available - [ ] `source:` fields populated for any adopted upstream content - [ ] Each skill has a co-located eval at `.agents/evals/operate/<skill-name>/eval.yaml` via `write-eval` - [ ] `install.sh` deploys all 4 to `~/.agents/skills/` - [ ] **HITL:** human runs behavioral test per skill - [ ] **HITL:** human reviews each SKILL.md and eval before committing - [ ] Per-skill process followed for all 4 skills: source discovery → source review → conflict check → synthesis grill → co-write iteratively - [ ] Trigger description for each skill tested against explicit, implicit, and negative queries before body written - [ ] eval.yaml for each skill contains all 5 required test types - [ ] Body ≤500 lines for each skill - [ ] `docs/spec/overview.md` updated to reflect all 4 skills deployed ## Blocked by - 0016 (per-skill workflow) - 0017 (`write-eval`) - 0018 (`write-skill`)

Claude added this to the Legacy / Triage milestone 2026-06-28 17:12:43 +00:00

Claude added the Kind/Feature

Priority

Medium

3

labels 2026-06-28 17:12:43 +00:00

Claude modified the milestone from Legacy / Triage to Skills & Agents

2026-06-28 19:26:52 +00:00

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: Defame1297/holocron#44