ideogram-incident-runbook

Execute Ideogram incident response with triage, mitigation, and postmortem. Use when responding to Ideogram-related outages, investigating errors, or running post-incident reviews for Ideogram integration failures. Trigger with phrases like "ideogram incident", "ideogram outage", "ideogram down", "ideogram on-call", "ideogram emergency", "ideogram broken".

Quality

90%

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

Quality

Content

80%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.

A highly actionable, lean incident runbook with executable triage and mitigation code and a clear decision tree. Its main gaps are missing explicit verification checkpoints after operational changes and a monolithic structure with no progressive disclosure to reference files.

Suggestions

Add explicit validation checkpoints after each mitigation action (e.g. after `kubectl rollout restart`, verify with a follow-up curl that 5xx/401s have stopped before declaring mitigated).

Split the heavier, less time-critical material — communication templates and postmortem template — into reference files (e.g. references/templates.md) and link to them from SKILL.md so the in-incident body stays lean.

Tighten the 402 "Credits Exhausted" flow with a concrete verification step (re-run the triage curl to confirm generation succeeds after top-up) to close the feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is action-dense — triage scripts, decision tree, per-status code blocks, templates — with no padding explaining concepts Claude already knows; length comes from genuinely distinct scenarios, not verbosity.	3 / 3
Actionability	Provides fully executable curl/kubectl bash blocks and a TypeScript fallback function that are copy-paste ready, plus concrete numbered steps for the manual 402 flow, matching the executable anchor.	3 / 3
Workflow Clarity	Triage is sequenced and the decision tree gives clear branching, but mitigation kubectl ops (rollout restart, set env) lack explicit verification checkpoints — only an implicit "Monitor for resolution" — so per the destructive/batch guideline it cannot reach 3.	2 / 3
Progressive Disclosure	Sections are well-organized and navigable, but the file is a monolithic ~240-line body with no bundle references and no content split out (e.g. templates, fallback impl are inline), fitting the level-2 "content that should be separate is inline" rather than the split-with-references level 3.	2 / 3
	Total	10 / 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.

The description is concise, concrete, and complete — it states specific actions, an explicit Use-when clause, and natural Ideogram-scoped trigger phrases in third person. It is a strong, low-conflict skill description.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "triage, mitigation, and postmortem" — in third person ("Execute"), matching the multiple-specific-actions anchor rather than the domain-only level 2.	3 / 3
Completeness	Answers both what (triage/mitigation/postmortem) and when via an explicit "Use when responding to..." clause plus trigger phrases, satisfying the level-3 requirement that the level-2 example lacks.	3 / 3
Trigger Term Quality	Lists natural on-call phrasings a user would actually say ("ideogram incident", "ideogram outage", "ideogram down", "ideogram on-call", "ideogram emergency", "ideogram broken"), giving good coverage rather than the partial level 2.	3 / 3
Distinctiveness Conflict Risk	All triggers are Ideogram-prefixed and the scope is a narrow incident-response niche, making it unlikely to fire for unrelated skills; this matches the clear-niche anchor, not the overlapping level 2.	3 / 3
	Total	12 / 12 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/ideogram-pack/skills/ideogram-incident-runbook/SKILL.md
Commit: 4c47e33

Reviewed: 1 day 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.