CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

72

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

80%

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

A dense, actionable incident runbook with executable triage and mitigation code and minimal concept padding. Its main gaps are the absence of an explicit verify-resolution feedback loop and no file-based progressive disclosure for the inline templates.

Suggestions

Add an explicit post-mitigation verification step (e.g., 'Re-run Quick Triage to confirm 200 responses before standing down') to close the validate→fix→retry loop in the workflow.

Move the communication and postmortem templates into a one-level-deep reference file (e.g., TEMPLATES.md) so SKILL.md stays a lean overview with well-signaled links, exercising progressive disclosure.

Confirm the cross-skill 'Next Steps' references (exa-data-handling, exa-debug-bundle) resolve to real skills, or mark them as optional to avoid a dead-end reference.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — the Overview states only Exa-specific facts ('requestId field', '10 QPS', 'hello@exa.ai') with no padding about what Exa or HTTP errors are, and code comments are minimal and load-bearing.

3 / 3

Actionability

Provides copy-paste-ready executable bash (the triage and 401/403 curl scripts) plus concrete TypeScript mitigation snippets and fill-in communication/postmortem templates, rather than abstract descriptions.

3 / 3

Workflow Clarity

A clear sequence exists (Quick Triage 'Run First' → Decision Tree → Immediate Actions → Post-Incident) with an upfront HTTP-code checkpoint, but there is no explicit post-mitigation verification step to close a validate→fix→retry loop, leaving the closing checkpoint implicit.

2 / 3

Progressive Disclosure

The single-file body is well-sectioned but monolithic — sizable communication and postmortem templates are inline rather than split into a one-level-deep reference file, and no bundle files are used to keep SKILL.md an overview.

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.

A strong description: concrete actions, an explicit 'Use when' clause, and natural Exa-prefixed trigger phrases in third-person voice. It clearly communicates both capability and activation conditions with no fluff.

DimensionReasoningScore

Specificity

Names three concrete actions — 'triage, mitigation, and postmortem procedures' — matching the anchor that lists multiple specific concrete actions rather than a vague domain label.

3 / 3

Completeness

Explicitly answers both 'what' ('Execute Exa incident response with triage, mitigation, and postmortem procedures') and 'when' ('Use when responding to Exa-related outages...') plus an explicit trigger clause, satisfying the both-what-and-when requirement.

3 / 3

Trigger Term Quality

Provides six natural trigger 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

Exa-specific scope with Exa-prefixed trigger phrases carves a clear niche unlikely to fire for unrelated skills, matching the distinct-triggers anchor.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.