CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

72

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

80%

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

A strongly actionable, lean incident runbook built from executable code, but it is a monolithic single file with no progressive file-splitting and lacks explicit validation feedback loops for its batch/destructive operations.

Suggestions

Add explicit validation checkpoints between batch/destructive steps — e.g., after pausing broken accounts, verify each is paused before reactivating, and re-test webhook delivery before closing the incident.

Split each incident into its own reference file under ./references/ (e.g., campaign-health.md, bounce-protect.md) and keep SKILL.md as an overview with one-level-deep links, improving progressive_disclosure.

Add a verify/recovery-checklist section confirming resolution (e.g., campaign status returns to active, bounce rate under threshold) before declaring an incident closed.

DimensionReasoningScore

Conciseness

The body is lean executable code and tables with no padding explaining what Instantly or email warmup is; every section earns its place, matching the lean-and-efficient anchor rather than the could-be-tightened anchor at 2.

3 / 3

Actionability

Fully executable TypeScript with real client methods and a copy-paste bash/curl+jq diagnostic script provide concrete, ready-to-run guidance, matching the fully-executable anchor rather than the pseudocode anchor at 2.

3 / 3

Workflow Clarity

Triage→mitigation→recovery sequences are present and recovery steps are numbered, but batch/destructive operations (pausing accounts, removing bounced leads) lack explicit validate-then-proceed checkpoints, capping it at 2 per the feedback-loop guideline.

2 / 3

Progressive Disclosure

No bundle files exist and the ~290-line body is a single monolithic file holding every incident inline; it is well-sectioned but content that could be split into reference files is not, matching the 'could be better organized / should be separate is inline' anchor at 2.

2 / 3

Total

10

/

12

Passed

Description

100%

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-crafted description: third-person voice, concrete actions, explicit 'Use when' trigger guidance, and distinct Instantly-scoped trigger phrases. No vague fluff or over-claims.

DimensionReasoningScore

Specificity

Names the domain (Instantly.ai incident response) and multiple concrete actions — 'triage, mitigation, and recovery' — matching the multiple-specific-actions anchor rather than the partial domain-only anchor at 2.

3 / 3

Completeness

Clearly answers 'what' ('Execute...procedures with triage, mitigation, and recovery') and 'when' ('Use when responding to campaign failures...outages') with explicit triggers, matching the both-answered anchor.

3 / 3

Trigger Term Quality

Explicit natural trigger phrases ('instantly incident', 'instantly outage', 'instantly campaign failed', 'instantly emergency', 'instantly runbook') are exactly what a user would say, satisfying good coverage rather than the missing-variations anchor at 2.

3 / 3

Distinctiveness Conflict Risk

A narrow Instantly.ai-specific niche with 'instantly'-prefixed triggers makes it unlikely to fire for unrelated skills, matching the clear-distinct-niche anchor.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.