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".
85
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 a well-structured skill description with strong trigger terms and clear 'when' guidance. Its main weakness is that the 'what' portion is somewhat general — it describes categories of response (outages, production issues, integration failures) rather than specific concrete actions the skill teaches. Adding 2-3 specific procedures would strengthen it further.
Suggestions
Add specific concrete actions to improve specificity, e.g., 'Guides through runbook steps including checking Apollo status, reviewing API error logs, escalating to Apollo support, and implementing fallback data flows.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Apollo.io incident response) and some actions (handling outages, debugging production issues, responding to integration failures), but doesn't list specific concrete actions like 'check status page', 'restart services', 'rollback deployments', etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (Apollo.io incident response procedures) and 'when' (handling outages, debugging production issues, integration failures) with an explicit 'Use when' clause and a 'Trigger with phrases' section. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say: 'apollo incident', 'apollo outage', 'apollo down', 'apollo production issue', 'apollo emergency'. These are realistic phrases someone would use in an urgent situation. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — scoped specifically to Apollo.io incidents and production issues. The 'apollo' prefix on all trigger terms makes it very unlikely to conflict with generic incident response or other integration skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable incident runbook with executable code, clear severity classification, and a well-sequenced workflow. Its main weakness is length — the full circuit breaker implementation and diagnostic script could be split into referenced files to improve token efficiency. The redundant Output section summarizing what was already presented adds unnecessary tokens.
Suggestions
Move the full circuit breaker TypeScript implementation and bash diagnostic script to separate referenced files (e.g., `See [circuit-breaker.ts](src/resilience/circuit-breaker.ts)`) to reduce inline bulk.
Remove the Output section at the end — it merely summarizes what the steps already contain and wastes tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly well-structured but includes some verbose elements — the full circuit breaker implementation (~40 lines of TypeScript) and the degradation handlers with placeholder comments add bulk. The post-incident template is useful but lengthy. Some sections like the Output summary at the end repeat what's already shown above. | 2 / 3 |
Actionability | Highly actionable with executable bash diagnostic scripts, complete TypeScript circuit breaker implementation, specific curl commands with real Apollo endpoints, and a concrete severity classification table with response times. Everything is copy-paste ready. | 3 / 3 |
Workflow Clarity | Clear 5-step sequential workflow from classification through diagnosis, mitigation (circuit breaker), degradation handling, and post-incident review. The escalation table provides explicit validation checkpoints (P1 > 15 min → page on-call). The circuit breaker itself implements a feedback loop (closed → open → half-open → closed). | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections, but it's monolithic — the full circuit breaker implementation and diagnosis script could be referenced as separate files rather than inlined. The Resources section provides external links, and there's a pointer to apollo-data-handling, but the main content is quite long for a single SKILL.md. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
70e9fa4
- 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.