incident-runbook-templates

Create structured incident response runbooks with step-by-step procedures, escalation paths, and recovery actions. Use when building runbooks, responding to incidents, or establishing incident response procedures.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable commands and clear sequencing, but it is over-long for inline content, repeats SRE knowledge Claude already has, omits error-recovery feedback loops for destructive ops, and references non-existent script files. Weakest on conciseness and progressive disclosure.

Suggestions

Move the two full runbook templates into separate reference files (e.g. references/service-outage-runbook.md, references/database-runbook.md) and keep SKILL.md as a concise overview pointing to them, fixing progressive disclosure and token cost.

Remove or trim content Claude already knows — the SEV1–SEV4 severity table and the best-practices do's/don'ts — or relocate them to a reference, to improve conciseness.

Add explicit feedback loops for destructive steps: after each rollback, pg_terminate_backend, or data deletion, state "verify recovery; if it fails, do X" rather than leaving recovery implicit.

Either create the referenced ./scripts/smoke-test-payments.sh and ./scripts/db-rollback.sh or replace those paths with inline commands so references resolve.

Dimension	Reasoning	Score
Conciseness	Mostly actionable but ~400 lines of full inline templates plus standard SRE knowledge (severity-level definitions, do's/don'ts like "write for 3 AM brain") and full communication templates pad the context and could be tightened or moved to reference files.	2 / 3
Actionability	Copy-paste-ready kubectl, psql, and curl commands with concrete thresholds ("> 5%", "p99 > 2s") and real SQL — fully executable guidance throughout.	3 / 3
Workflow Clarity	Steps are clearly numbered with a verification section and checklists, but destructive operations (rollback, pg_terminate_backend, data deletion) lack explicit validate→fix→retry feedback loops, capping the score per the destructive-ops rule.	2 / 3
Progressive Disclosure	Well-sectioned but monolithic: two complete runbook templates are inline rather than split into reference files, and the body cites ./scripts/smoke-test-payments.sh and ./scripts/db-rollback.sh that do not exist in any bundle directory.	2 / 3
	Total	9 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is a strong example: concrete capabilities, explicit "Use when..." trigger guidance, natural keywords, and a distinct niche. It closely matches the rubric's good_overall_examples.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "step-by-step procedures, escalation paths, and recovery actions" — matching the comprehensive multi-action anchor rather than the partial-action score 2.	3 / 3
Completeness	Explicitly answers both what ("Create structured incident response runbooks with...") and when ("Use when building runbooks, responding to incidents, or...") with an explicit trigger clause.	3 / 3
Trigger Term Quality	Covers natural terms users would say — "building runbooks", "responding to incidents", "incident response procedures" — with good variation, not just jargon.	3 / 3
Distinctiveness Conflict Risk	The incident-response/runbook niche with escalation and recovery triggers is distinct and unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Dicklesworthstone/pi_agent_rust
Commit: e9f9b67

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.