incident-runbook-templates

Production-ready templates for incident response runbooks covering detection, triage, mitigation, resolution, and communication.

Quality

48%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/incident-runbook-templates/SKILL.md

Quality

Content

52%Scale 1-5

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

The skill provides genuinely useful, actionable incident response templates with concrete commands, but suffers from excessive length and poor content organization. The inline templates are practical but the skill tries to be both a meta-skill for generating runbooks and a runbook itself, creating confusion. Significant token waste from explaining concepts Claude already knows (severity levels, incident management best practices) and from inlining content that should be in separate bundle files.

Suggestions

Move the full runbook templates (Service Outage, Database Incident) into separate bundle files (e.g., templates/service-outage.md, templates/database-incident.md) and reference them from the main SKILL.md with brief descriptions.

Remove the 'Best Practices' do's/don'ts section and the external resource links — Claude already knows incident management principles and these waste tokens.

Remove or drastically compress the severity levels table — this is generic knowledge that doesn't need to be taught to Claude.

Add explicit feedback loops within mitigation procedures: after each mitigation step, include a verification check before proceeding (e.g., 'Verify error rate dropped below 1% before closing').

Dimension	Reasoning	Score
Conciseness	The skill is heavily verbose at ~300+ lines. It explains basic concepts Claude already knows (what severity levels are, do's/don'ts of incident management, links to Google SRE book). The severity table, best practices section, and external resource links add little value for Claude. The templates themselves are useful but could be much more compact.	2 / 5
Actionability	The runbook templates contain concrete, executable bash and SQL commands that are copy-paste ready. The kubectl commands, psql queries, and curl commands are specific and practical. Minor gap: the top-level 'Instructions' section is vague ('Apply relevant best practices and validate outcomes') and the skill conflates being a template generator with being an actual runbook.	4 / 5
Workflow Clarity	The Service Outage Runbook has clear sequenced steps within each mitigation scenario (Steps 1-6 for service down, Steps 1-5 for high latency), includes verification steps and rollback procedures, and has a triage classification table. However, there's no explicit feedback loop (validate → fix → retry) connecting mitigation to verification — the verification section is separate rather than integrated into each mitigation path.	4 / 5
Progressive Disclosure	The skill is a monolithic wall of content with everything inlined. It references `resources/implementation-playbook.md` but no bundle files exist. The database runbook, communication templates, and best practices sections could all be separate files. The severity table and best practices are inlined despite being reference material better suited to separate documents.	2 / 5
	Total	12 / 20 Passed

Description

45%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.

The description identifies a clear domain (incident response runbooks) and lists the phases covered, giving it reasonable specificity and distinctiveness. However, it lacks a 'Use when...' clause, which is critical for skill selection, and the description focuses on what the templates cover rather than what concrete actions the skill performs (e.g., generates, customizes, adapts). The trigger term coverage is adequate but misses common synonyms users might use.

Suggestions

Add an explicit 'Use when...' clause with trigger phrases like 'Use when the user needs to create or customize incident response runbooks, playbooks, or on-call procedures, or mentions outage handling, incident management, or SRE documentation.'

Replace the passive 'Production-ready templates for' with concrete action verbs describing what the skill does, e.g., 'Generates and customizes incident response runbooks...'

Include common synonyms and related terms such as 'playbook', 'on-call', 'outage', 'escalation', 'postmortem', 'SRE' to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (incident response runbooks) and lists several phases (detection, triage, mitigation, resolution, communication), but these are categories rather than concrete actions. It says 'templates for' but doesn't specify what concrete actions the skill performs (e.g., generates, customizes, fills in).	3 / 5
Completeness	Has a reasonable 'what' (production-ready templates for incident response runbooks covering specific phases), but completely lacks a 'when' clause. There is no explicit guidance on when Claude should select this skill, which per the rubric should cap completeness at 3, and the weak 'what' (no concrete actions, just 'templates') brings it to 2.	2 / 5
Trigger Term Quality	Includes relevant terms like 'incident response', 'runbooks', 'detection', 'triage', 'mitigation', 'resolution', and 'communication', which are natural terms in the incident management domain. However, it misses common synonyms and variations like 'on-call', 'outage', 'postmortem', 'playbook', 'SRE', 'incident management', or 'escalation'.	3 / 5
Distinctiveness Conflict Risk	The combination of 'incident response runbooks' with specific phases (detection, triage, mitigation, resolution, communication) creates a fairly distinct niche. There could be minor overlap with general template skills or DevOps/SRE documentation skills, but the specificity to incident response reduces conflict risk.	4 / 5
	Total	12 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/incident-runbook-templates/SKILL.md
Commit: 57c135b

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.