Name: runbook-generator
Rating: 67.2 (1 reviews)
Author: alirezarezvani

runbook-generator

Generate operational runbooks from a service name — deployment, incident response, maintenance, and rollback workflows. Templated structure customizable per environment. Use when documenting on-call procedures for a new service, standardizing incident response across teams, or producing runbooks before launching to production.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

The canonical home for this skill is runbook-generator in alirezarezvani/claude-skills

Quality

Content

71%Weight 40%Scale 1-5

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

A well-structured, concise overview of a runbook-generation skill with concrete CLI examples and a clear workflow, but its core value proposition depends on a generator script and a templates reference that are not actually present in the bundle, undermining both actionability and progressive disclosure.

Suggestions

Bundle the referenced `scripts/runbook_generator.py` so the Quick Start and Recommended Workflow commands are actually executable, or remove the script references and inline the runbook template structure directly in SKILL.md.

Bundle `references/runbook-templates.md` (or create the file) so the Reference Docs section points to real content rather than a dangling path.

Add an explicit validate→fix→retry feedback loop to the Recommended Workflow (e.g., 'If the dry-run reveals missing rollback triggers, revise and re-run before storing in VCS') to strengthen workflow clarity for fragile operational docs.

Dimension	Reasoning	Score
Conciseness	The body is lean and direct — tight bullet lists for Core Capabilities, When to Use, Pitfalls, and Best Practices with no over-explanation of concepts Claude already knows — but the Overview line restates the frontmatter description and Recommended Workflow step 1 repeats the Quick Start command, which are minor tokens that could be trimmed.	4 / 5
Actionability	Quick Start gives concrete, copy-pasteable commands with real flags (`python3 scripts/runbook_generator.py payments-api --owner platform --output docs/runbooks/payments-api.md`) covering two common cases, but the referenced generator script is not bundled so the commands cannot actually execute as part of this skill.	4 / 5
Workflow Clarity	Recommended Workflow lays out a clear 5-step sequence (generate → fill in → add verification/rollback → dry-run in staging → store in VCS) with the dry-run step acting as a validation checkpoint, though there is no explicit validate→fix→retry feedback loop. The destructive/batch cap does not apply because runbook generation is non-destructive documentation creation.	4 / 5
Progressive Disclosure	The SKILL.md is well-sectioned and the Reference Docs section signals a one-level-deep reference, but neither referenced bundle file exists — there is no `scripts/` directory (so `runbook_generator.py` is absent) and no `references/` directory (so `runbook-templates.md` is absent) — so navigation is broken and none of the promised bundle content is delivered.	3 / 5
	Total	15 / 20 Passed

Description

92%Weight 40%Scale 1-5

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

A strong description that explicitly states both the concrete capabilities (runbook generation across deployment, incident, maintenance, and rollback workflows with per-environment templating) and clear natural-language triggers, occupying a distinct SRE/operations niche with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	It lists multiple specific concrete actions — 'Generate operational runbooks from a service name', 'deployment, incident response, maintenance, and rollback workflows', and 'Templated structure customizable per environment' — giving comprehensive coverage of the runbook domain.	5 / 5
Completeness	It clearly and explicitly answers both what it does (generate runbooks with the four named workflow types and per-environment templating) and when to use it ('Use when documenting on-call procedures for a new service...'), with concrete trigger phrases.	5 / 5
Trigger Term Quality	It includes good natural trigger phrases a user would say ('documenting on-call procedures', 'standardizing incident response across teams', 'producing runbooks before launching to production'), but lacks common synonyms (playbook, SRE/ops docs) and any file extensions.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (operational runbooks for a named service, SRE/DevOps domain) with distinct triggers (on-call procedures, incident response standardization, pre-production runbooks), giving minimal conflict risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/runbook-generator/SKILL.md
Commit: 19392f7

Reviewed: ~6 hours 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.