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".

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/saas-packs/instantly-pack/skills/instantly-incident-runbook/SKILL.md

Quality

Content

57%Weight 40%Scale 1-5

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

The body is a practical, actionable incident runbook with real API calls and an executable diagnostic script, but it mixes instructional prose into code and lacks explicit validation gates on its destructive batch operations. No bundle files are provided, so all content is inline despite being long enough to benefit from splitting.

Suggestions

Add explicit validation checkpoints to the account-health cascade — e.g. re-test account vitals and confirm SMTP/IMAP are 'ok' before resuming accounts or reactivating campaigns — to lift workflow_clarity above the batch/destructive cap of 3.

Move the long TypeScript triage/mitigation blocks into scripts/ files and keep SKILL.md as an overview that links to them, improving progressive disclosure and conciseness.

Convert the instructional console.log recovery steps into either real executable code or concise markdown numbered lists, removing the prose-embedded-in-code padding.

Dimension	Reasoning	Score
Conciseness	The content is dense and domain-specific without re-explaining concepts Claude knows, but embeds prose recovery steps as console.log strings (e.g. 'Step 1: Pause broken accounts', numbered 'Recovery Steps' printed rather than executed) that could be tightened into markdown or real code; not a 2 because it is mostly efficient.	3 / 5
Actionability	Provides concrete executable API calls (client.accounts.pause, campaigns.list, webhooks resume) and a fully runnable bash diagnostic with curl/jq; falls short of 5 because the TypeScript depends on an un-bundled './src/instantly/client' and several recovery actions are emitted as instructional console.log text rather than executable code.	4 / 5
Workflow Clarity	Each incident has a clear Triage -> Mitigation -> Recovery sequence with a severity/response-time table, but the destructive batch cascade (pause all broken accounts, then resume and reactivate campaigns) lacks explicit validation checkpoints before resuming; per the batch/destructive cap this cannot exceed 3, and the warmup section's 'Re-test inbox rates before re-enabling' is the only true validate-before-proceed gate.	3 / 5
Progressive Disclosure	Sections are well-organized by incident type, but the entire runbook is a single ~290-line inline file with no bundle files in references/scripts/assets, and the lone cross-skill pointer ('see `instantly-data-handling`') is an unsignaled backtick mention rather than a clear link; content that could live in scripts/ is inlined.	3 / 5
	Total	13 / 20 Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong: it concisely states the skill's purpose, provides explicit use-when guidance with concrete scenarios, and lists natural trigger phrases that aid distinctiveness. Only specificity is slightly below top because the named actions are high-level IR phases.

Dimension	Reasoning	Score
Specificity	Names the domain ('Instantly.ai incident response') and three concrete phases ('triage, mitigation, and recovery'), which lists several specific actions with only minor gaps in granularity; not a 5 because the named actions are standard IR process phases rather than finely concrete operations.	4 / 5
Completeness	Explicitly states what it does ('Execute Instantly.ai incident response procedures with triage, mitigation, and recovery') and when to use it ('Use when responding to...') with concrete trigger phrases, satisfying both what and when.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural trigger phrases ('instantly incident', 'instantly outage', 'instantly campaign failed', 'instantly emergency', 'instantly runbook') plus situational terms ('campaign failures, account health crises, deliverability drops, API outages') that users would plausibly say.	5 / 5
Distinctiveness Conflict Risk	Scoped to a specific product (Instantly.ai) with distinctive 'instantly'-prefixed triggers, giving it a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 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

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/saas-packs/instantly-pack/skills/instantly-incident-runbook/SKILL.md
Commit: 8585d6d

Reviewed: 13 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.