incident-response-incident-response

Use when working with incident response incident response

Quality

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/incident-response-incident-response/SKILL.md

Quality

Content

77%

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

The body delivers a well-structured, highly actionable multi-agent incident-response workflow with explicit sequencing and validation. Its main weaknesses are a monolithic single-file layout and some boilerplate filler that could be trimmed.

Suggestions

Move the per-agent prompts, severity/incident-type catalogs, and success criteria into reference files (e.g. PHASES.md, CONFIG.md) and link them one level deep from the overview.

Delete the generic Instructions bullets and the Extended-thinking commentary, which restate what Claude already knows and pad token usage.

Keep the phase/step skeleton in SKILL.md as a concise overview so the entry point stays lean.

Dimension	Reasoning	Score
Conciseness	The core workflow is dense and task-oriented, but the generic Instructions bullets and the bracketed Extended-thinking commentary are largely boilerplate that adds tokens without actionable value.	2 / 3
Actionability	Each phase gives a concrete Task tool call with a specific subagent_type, a copy-paste-ready prompt, expected output, and required context, matching the fully-executable anchor.	3 / 3
Workflow Clarity	Five numbered phases with 13 sequenced steps, explicit validation (health checks at each rollout stage, rollback triggers), and success-criteria checklists provide clear checkpoints and error-recovery feedback loops.	3 / 3
Progressive Disclosure	The skill is a ~168-line monolith with no bundle files or external references, so all per-agent prompt detail that should be one level deep is inlined rather than split for easy navigation.	2 / 3
	Total	10 / 12 Passed

Description

22%

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 a near-empty stub that repeats the domain name without stating capabilities or quality triggers. It fails to tell Claude what the skill does or when to invoke it beyond a vague domain mention.

Suggestions

Replace the duplicated phrase with concrete actions, e.g. 'Orchestrates multi-agent incident response: triage severity, investigate root cause, mitigate, and run blameless postmortems.'

Expand trigger terms to natural user phrases such as 'production outage', 'SEV-1/P0', 'on-call incident', 'service degradation', or 'incident postmortem'.

Keep the 'Use when...' clause but pair it with an explicit 'what' so both halves of completeness are satisfied.

Dimension	Reasoning	Score
Specificity	The description only restates the domain name twice ("incident response incident response") and names no concrete actions, matching the 'vague or no actions' anchor.	1 / 3
Completeness	It gives a 'when' trigger but no 'what does this do' clause at all, so it answers only half of the required pair, capping completeness at 1.	1 / 3
Trigger Term Quality	It surfaces the natural term "incident response", but the awkward duplication and absence of common variations (outage, SEV, postmortem, on-call) leave coverage incomplete.	2 / 3
Distinctiveness Conflict Risk	The domain is identifiable, but the description is so generic it could overlap with general ops/SRE or observability skills rather than carving a distinct niche.	2 / 3
	Total	6 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rmyndharis/antigravity-skills
Path: skills/incident-response-incident-response/SKILL.md
Commit: e63f7dd

Reviewed: about 23 hours 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.