incident-response
Manage active production incidents through detection, triage, mitigation, communication, and resolution with structured roles and decision-making. Use this skill whenever the user has an active incident, a production issue, a service outage, a security incident, or needs to plan incident response procedures. Triggers on incident response, production incident, outage, service down, site down, P0, P1, severity, downtime, on-call, incident commander, status page, postmortem prep. Also triggers when something is actively broken in production and the user is figuring out what to do.
67
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is an excellent skill description that clearly defines what the skill does (manage production incidents through specific phases), when to use it (explicit trigger clause with comprehensive scenarios), and includes a rich set of natural trigger terms. The description is well-structured, uses third person voice, and is highly distinctive in its domain focus.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: detection, triage, mitigation, communication, resolution, and mentions structured roles and decision-making. These are clear, actionable phases of incident management. | 3 / 3 |
Completeness | Clearly answers both 'what' (manage incidents through detection, triage, mitigation, communication, resolution) and 'when' (explicit 'Use this skill whenever...' clause plus detailed trigger list). Both dimensions are thoroughly addressed. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'production incident', 'outage', 'service down', 'site down', 'P0', 'P1', 'on-call', 'incident commander', 'status page', 'postmortem prep', 'something is actively broken in production'. These are highly natural phrases an engineer would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused on active production incidents with very specific trigger terms like 'incident commander', 'P0', 'P1', 'status page', 'on-call' that are unlikely to overlap with other skills. The domain is clearly scoped to incident response. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-organized incident response skill with strong workflow clarity, a useful severity rubric, and practical communication templates. Its main weaknesses are moderate verbosity (some content Claude would already know about incident management), limited actionability due to its intentionally tool-agnostic nature, and a large amount of inline content that could be better distributed to reference files for progressive disclosure.
Suggestions
Move the detailed severity rubric, roles table, status page templates, and failure patterns into the referenced `references/incident-playbook.md` file, keeping only a compact summary in SKILL.md with clear links.
Trim sections that state things Claude already knows (e.g., 'Required inputs' listing 'communication channels operational', explaining what detection sources are) to reduce token overhead.
Add at least one concrete, tool-specific example (e.g., a sample rollback command, a PagerDuty acknowledgment API call, or a Slack incident channel creation snippet) to increase actionability beyond general process guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is well-structured but includes some content Claude already knows (e.g., explaining what detection sources are, general communication principles). The severity rubric, roles table, and status page patterns earn their place, but sections like 'When to use / When NOT to use' and 'Required inputs' add moderate padding. The failure patterns section, while useful, is lengthy and some items are obvious (e.g., 'Blame culture'). | 2 / 3 |
Actionability | The skill provides structured frameworks, rubrics, and communication templates which are useful, but it's fundamentally a process/instruction skill with no executable code or commands. The guidance is concrete in places (status page templates, severity rubric, mitigation patterns) but remains at the level of general best practices rather than specific, copy-paste-ready artifacts tied to particular tools or systems. The 'stack-agnostic, tool-agnostic' framing inherently limits specificity. | 2 / 3 |
Workflow Clarity | The 10-step workflow is clearly sequenced with explicit validation checkpoints (step 7: 'Verify mitigation. Don't trust dashboards alone; test the user flow') and feedback loops (severity re-evaluation, communicate-before-answers pattern). The phases are well-defined with clear decision points, and the failure patterns section serves as an implicit checklist of what not to skip. | 3 / 3 |
Progressive Disclosure | The skill references a single file (`references/incident-playbook.md`) for deeper content, which is good structure. However, no bundle files are provided, so that reference is a dead link. The SKILL.md itself is quite long (~250 lines) and inlines substantial detail (severity rubric, roles, status page templates, failure patterns) that could be split into the referenced playbook, keeping the main file leaner. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%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
- rampstackco/claude-skills
- Commit
8e70d03
- Reviewed
Table of Contents
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.