apollo-incident-runbook

Apollo.io incident response procedures. Use when handling Apollo outages, debugging production issues, or responding to integration failures. Trigger with phrases like "apollo incident", "apollo outage", "apollo down", "apollo production issue", "apollo emergency".

Quality

83%

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

Quality

Content

77%Weight 40%Scale 1-3

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

A highly actionable, well-sequenced incident-response skill with executable diagnostics, a circuit breaker, and a review checklist. Its main weakness is progressive disclosure: the body is a monolithic wall of full implementations while a reference bundle file exists but is never referenced.

Suggestions

Move the full circuit-breaker class and diagnostic script into references/implementation-guide.md and replace them in SKILL.md with a concise summary plus a clearly signaled link, e.g. "**Full implementation**: See [implementation-guide.md](references/implementation-guide.md)".

Make the decision gate explicit: add a short mapping from diagnosis results to the severity handler (e.g. "if status page reports an outage and auth/search return 5xx → run handleP1") so the diagnosis-to-mitigation branch is an explicit checkpoint rather than implied.

Tighten the inline code blocks by trimming the stub handleP2/handleP3 functions to a one-line severity-action table, keeping the body focused on overview and routing.

Dimension	Reasoning	Score
Conciseness	The prose is lean and avoids explaining concepts Claude already knows, but the ~214-line body inlines complete implementations (a full TypeScript circuit-breaker class and a full bash diagnostic script) that could be tightened or moved to the reference file, so not every token earns its place in an overview.	2 / 3
Actionability	Provides fully executable, copy-paste-ready artifacts — a complete bash diagnostic script, a complete CircuitBreaker TypeScript class, severity-keyed degradation handlers, and a post-incident template — meeting the executable-and-specific anchor.	3 / 3
Workflow Clarity	A clear five-step sequence (classify → diagnose → circuit-breaker → degrade → review) is paired with an explicit diagnosis validation step, an auto-recovering circuit-breaker feedback loop, an escalation threshold table, and a post-incident review checklist.	3 / 3
Progressive Disclosure	Sections are well organized, but content that should be separate (full code implementations) is inlined in SKILL.md, and the existing references/implementation-guide.md bundle file is never linked or signaled from the body, leaving it orphaned.	2 / 3
	Total	10 / 12 Passed

Description

90%Weight 40%Scale 1-3

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 well-constructed description with explicit use-when guidance, natural trigger phrases, and a clear Apollo-specific niche. Its only weakness is specificity — it describes the domain at a category level rather than enumerating the concrete response actions the skill delivers.

Suggestions

Replace the generic action categories with the concrete procedures the skill performs, e.g. "Classifies incident severity, runs quick diagnosis, implements a circuit breaker, applies graceful degradation, and produces a post-incident review."

Dimension	Reasoning	Score
Specificity	Names the domain and a few action categories ("incident response procedures", "debugging production issues", "responding to integration failures") but does not list multiple concrete actions like severity classification, diagnosis, or circuit-breaker implementation that the skill actually performs.	2 / 3
Completeness	Explicitly answers both what ("Apollo.io incident response procedures") and when ("Use when handling Apollo outages...") with explicit trigger phrases, satisfying the both-what-and-when anchor.	3 / 3
Trigger Term Quality	Provides good coverage of natural phrases a user would say ("apollo incident", "apollo outage", "apollo down", "apollo production issue", "apollo emergency"), matching the high-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	The Apollo.io-specific niche and "apollo"-prefixed trigger phrases make 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: 1 missing	Warning

	Total	13 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/saas-packs/apollo-pack/skills/apollo-incident-runbook/SKILL.md
Commit: 4c47e33

Reviewed: 1 day 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.