clerk-incident-runbook

Manage incident response for Clerk authentication issues. Use when handling auth outages, security incidents, or production authentication problems. Trigger with phrases like "clerk incident", "clerk outage", "clerk down", "auth not working", "clerk emergency".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

50%

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

The runbook is well-structured and largely actionable, but it has consistent gaps: two procedures are non-executable, destructive steps lack validation checkpoints, the body is monolithic with an unreferenced bundle file, and several closing sections restate earlier content.

Suggestions

Make Step 3 (key rotation) and Step 5 (webhook replay) executable by replacing the echo/commented-out commands with real vercel and curl invocations, or explicitly justify the manual-dashboard steps.

Add explicit validation checkpoints to the destructive procedures — e.g., after key rotation verify a sample auth call succeeds, and after session revocation confirm revoked sessions reject requests before proceeding.

Link the bundled references/implementation-guide.md from the body (e.g., a "## Detailed implementation" section pointing to it) and trim the redundant Output/Examples sections that restate the steps.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean executable procedures with no concept-explanation padding, but the "Output", "Examples", and "Error Handling" sections restate material already shown in the steps and could be tightened.	2 / 3
Actionability	Steps 1, 2, and 4 provide copy-paste-ready bash/TypeScript, but Step 3 (key rotation) and Step 5 (webhook replay) replace real commands with echo statements and dashboard-click narration, leaving key guidance non-executable.	2 / 3
Workflow Clarity	The six steps are clearly sequenced, but destructive/batch operations (key rotation, mass session revocation) lack explicit validate-then-proceed checkpoints and feedback loops, which caps clarity at 2 per the rubric.	2 / 3
Progressive Disclosure	The body has clear step-based sections, but it is largely monolithic inline code and never links to the bundled references/implementation-guide.md, so the one-level-deep reference that exists is not signaled.	2 / 3
	Total	8 / 12 Passed

Description

90%

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 clearly defines its Clerk auth-incident niche with explicit "Use when" triggers and natural trigger phrases. Its only weakness is specificity: it states the domain rather than enumerating the concrete incident-response actions the skill performs.

Dimension	Reasoning	Score
Specificity	Names the domain and a general action ("Manage incident response for Clerk authentication issues") but does not list multiple concrete actions (e.g., rotate keys, enable bypass, revoke sessions), so it stops at naming domain plus some actions.	2 / 3
Completeness	Clearly states what it does ("Manage incident response for Clerk authentication issues") and when to use it ("Use when handling auth outages, security incidents, or production authentication problems") with explicit trigger guidance.	3 / 3
Trigger Term Quality	Explicitly lists natural phrases a user would say — "clerk incident", "clerk outage", "clerk down", "auth not working", "clerk emergency" — giving good coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	The niche is narrowly scoped to Clerk authentication incidents with Clerk-specific trigger phrases, making it clearly distinguishable and unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 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
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	13 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 02d6341

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.