instantly-incident-runbook
Execute Instantly.ai incident response procedures with triage, mitigation, and recovery. Use when responding to campaign failures, account health crises, deliverability drops, or Instantly API outages. Trigger with phrases like "instantly incident", "instantly outage", "instantly campaign failed", "instantly emergency", "instantly runbook".
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 that clearly identifies its domain (Instantly.ai incident response), provides explicit 'Use when' and 'Trigger with' clauses, and includes platform-specific trigger terms that minimize conflict risk. The main weakness is that the capability actions (triage, mitigation, recovery) are somewhat generic incident response terminology rather than concrete, platform-specific actions.
Suggestions
Replace generic terms like 'triage, mitigation, and recovery' with more specific actions such as 'pause failing campaigns, rotate sending accounts, diagnose deliverability issues, check DNS/SPF/DKIM records'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Instantly.ai incident response) and lists some actions (triage, mitigation, recovery), but these are fairly generic incident response terms rather than concrete, specific actions like 'pause affected campaigns', 'rotate sending accounts', or 'check DNS records'. | 2 / 3 |
Completeness | Clearly answers both 'what' (execute incident response procedures with triage, mitigation, and recovery) and 'when' (campaign failures, account health crises, deliverability drops, API outages) with explicit trigger phrases provided. | 3 / 3 |
Trigger Term Quality | Includes a strong set of natural trigger terms that users would actually say: 'instantly incident', 'instantly outage', 'instantly campaign failed', 'instantly emergency', 'instantly runbook', plus contextual phrases like 'campaign failures', 'account health crises', 'deliverability drops', and 'Instantly API outages'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — the combination of 'Instantly.ai' as a specific platform plus 'incident response' creates a clear niche. The trigger terms are platform-specific and unlikely to conflict with other 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 for each scenario, clear severity classification, and well-structured workflows with validation steps. The main weakness is its length—it could benefit from splitting per-incident procedures into separate files with the SKILL.md serving as an overview/router. Minor conciseness improvements could be made by trimming console.log narration lines.
Suggestions
Consider restructuring as an overview file that links to separate per-incident runbook files (e.g., incident-bounce-protect.md, incident-webhook-failure.md) to improve progressive disclosure and reduce token load.
Trim console.log statements that merely narrate the process (e.g., '=== P1 TRIAGE: Campaign Health ===') since Claude can adapt output formatting to context.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly efficient for its scope but includes some redundancy—console.log instructions that essentially narrate what's happening could be trimmed. The severity table and error handling table are well-structured, but some recovery steps are repeated in slightly different forms across incidents. | 2 / 3 |
Actionability | Provides fully executable TypeScript code for each incident type with concrete API calls, specific status codes to check, and a ready-to-run bash diagnostic script. Each incident has clear, copy-paste-ready triage and mitigation code with specific endpoints and parameters. | 3 / 3 |
Workflow Clarity | Each incident follows a clear triage → mitigation → recovery sequence with explicit validation checkpoints (e.g., test vitals, check bounce rates, verify webhook delivery). The bounce protect section includes a prevention checklist, and the warmup section has a clear multi-step recovery with a wait-and-retest feedback loop. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers per incident type and a quick diagnostic script, but the file is quite long (~200+ lines of code) and could benefit from splitting detailed incident procedures into separate files. The single reference to 'instantly-data-handling' at the end is good but the main body could be an overview with links to per-incident detail files. | 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
4dee593
- 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.