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".

62

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

Quality

Content

50%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.

The runbook is well-structured and covers a realistic range of Instantly incidents with mostly concrete code, but it leans on an unbundled client wrapper, narrates recovery steps via console.log, and lacks validation checkpoints around batch operations. It is a solid single-file reference but not maximally executable or concise.

Suggestions

Replace the unbundled 'InstantlyClient' TypeScript wrapper with real Instantly API v2 REST calls (as the bash diagnostic already uses) or ship the client in scripts/, so the incident handlers are executable rather than illustrative.

Cut the console.log narration of recovery steps and instead execute the actual calls (e.g., POST /campaigns/{id}/activate), removing token bloat while making the steps actionable.

Add explicit validation checkpoints before batch/destructive actions, e.g. confirm all accounts report healthy vitals before reactivating campaigns and verify the bounce rate has dropped before re-enabling a campaign.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows, but recovery steps are narrated via console.log prose rather than executed, and the repeated TypeScript handler pattern inflates the ~290-line body; it could be tightened rather than padded.

2 / 3

Actionability

The bash diagnostic script and inline REST endpoints are concrete, but the core incident handlers depend on an unbundled 'InstantlyClient' from './src/instantly/client' with methods that do not map directly to Instantly API v2, leaving the primary code illustrative rather than copy-paste executable.

2 / 3

Workflow Clarity

Each incident follows a clear Triage → Mitigation/Recovery sequence, but batch/destructive operations (pausing accounts, reactivating campaigns) lack explicit validation checkpoints, capping this at level 2 per the destructive-operation guideline.

2 / 3

Progressive Disclosure

Section headers and tables are well organized, but everything sits inline in a single ~290-line file with no one-level-deep references; per-incident runbooks could be split into separate files for easier navigation.

2 / 3

Total

8

/

12

Passed

Description

100%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 strong, well-scoped description that explicitly states capabilities, use conditions, and natural trigger phrases in third-person voice. It clearly answers both what the skill does and when to invoke it.

DimensionReasoningScore

Specificity

Names the domain and lists multiple concrete actions — 'triage, mitigation, and recovery' — matching the level-3 anchor of multiple specific concrete actions.

3 / 3

Completeness

Explicitly answers both what (execute incident response procedures with triage, mitigation, recovery) and when ('Use when responding to campaign failures, account health crises, deliverability drops, or Instantly API outages') with explicit triggers.

3 / 3

Trigger Term Quality

Provides good coverage of natural phrases users would say — 'instantly incident', 'instantly outage', 'instantly campaign failed', 'instantly emergency', 'instantly runbook' — matching the level-3 anchor.

3 / 3

Distinctiveness Conflict Risk

Scoped to a clear niche (Instantly.ai) with product-specific triggers, making it unlikely to fire for the wrong skill.

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.