exa-incident-runbook

Execute Exa incident response with triage, mitigation, and postmortem procedures. Use when responding to Exa-related outages, investigating errors, or running post-incident reviews for Exa integration failures. Trigger with phrases like "exa incident", "exa outage", "exa down", "exa on-call", "exa emergency", "exa broken".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

80%

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 and concise with executable scripts and templates, but workflow validation is implicit and the runbook is monolithic rather than progressively split across referenced files.

Suggestions

Add explicit validation gates before and after mitigation actions (e.g. "Confirm the triage HTTP code, then apply the fix; re-run Quick Triage to verify recovery before closing") to turn implicit checks into clear feedback loops.

Move the communication and postmortem templates into a referenced bundle file (e.g. references/templates.md) and link to it from the body, reducing inline bulk while keeping the main runbook as a navigable overview.

Add a retry-with-backoff then re-check-status checkpoint in the 5xx/429 sections so error-recovery has an explicit validate-before-escalate loop rather than a one-shot action.

Dimension	Reasoning	Score
Conciseness	The runbook is lean and assumes Claude's competence, surfacing only Exa-specific facts Claude would not know (e.g. requestId field, 10 QPS limit, hello@exa.ai) with no generic-concept padding.	3 / 3
Actionability	It provides fully executable bash/curl triage and evidence-collection scripts, runnable TypeScript fallback examples, and copy-paste-ready communication/postmortem templates.	3 / 3
Workflow Clarity	A clear sequence exists (Quick Triage "Run First" → Decision Tree → Immediate Actions → Post-Incident), but validation checkpoints are implicit and there are no explicit validate-fix-retry gates before mitigation actions; the scoring note caps destructive-adjacent workflows at 2.	2 / 3
Progressive Disclosure	Sections are well-organized, but it is a monolithic single-file runbook with no bundle files, and the long communication/postmortem templates that could be split out are inline; the only references are cross-skill mentions rather than one-level-deep bundle references.	2 / 3
	Total	10 / 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 strong across all dimensions: it names concrete actions, includes natural trigger phrases, explicitly states both what it does and when to use it, and occupies a distinct, low-conflict niche.

Dimension	Reasoning	Score
Specificity	It lists multiple concrete actions — "triage, mitigation, and postmortem procedures" — matching the score-3 anchor of enumerating several specific actions rather than vague language.	3 / 3
Completeness	It explicitly answers both what ("Execute Exa incident response...") and when ("Use when responding to Exa-related outages...") with explicit trigger guidance, so it does not cap at 2.	3 / 3
Trigger Term Quality	It provides six natural phrases a user would actually say ("exa incident", "exa outage", "exa down", "exa on-call", "exa emergency", "exa broken"), giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	The skill is a clearly Exa-specific niche with "exa"-prefixed triggers, making it unlikely to fire for or conflict with unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 3022dd3

Reviewed: 2 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.