incident-response-incident-response

Use when working with incident response incident response

Quality

40%

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

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 delivers a concrete, well-sequenced multi-agent incident-response workflow with copy-paste-ready task prompts, but it is weakened by boilerplate padding, a meta 'extended thinking' block, missing validation gates across destructive phases, and a monolithic structure with no file-level disclosure.

Suggestions

Remove the generic 'Instructions' bullets and the '[Extended thinking: ...]' block; they restate what Claude already knows and add tokens without actionability.

Add explicit validation checkpoints between phases (e.g. 'Confirm severity classification before mitigation', 'Validate fix in staging before emergency deployment') to satisfy the destructive/batch feedback-loop requirement.

Move per-phase prompt details into referenced runbook files (e.g. references/phase-detection.md) and keep SKILL.md as a concise overview with one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The phased task definitions are mostly efficient, but the generic 'Instructions' boilerplate ('Clarify goals...', 'Apply relevant best practices...') and the '[Extended thinking: ...]' meta-block are unnecessary padding that could be trimmed.	3 / 5
Actionability	Each step gives a concrete Task-tool call with a specific subagent_type and a detailed, copy-paste-ready prompt string, but the $ARGUMENTS/$SEVERITY placeholders and unevaluated subagent types leave minor gaps.	4 / 5
Workflow Clarity	Phases 1-5 are clearly sequenced with numbered steps and context handoffs, but the workflow involves destructive/batch operations (rollback, traffic rerouting, emergency deployment) without consistent validation gates between phases, triggering the cap at 3.	3 / 5
Progressive Disclosure	The file has clear section headers but is a single monolithic document with all per-phase runbook detail inlined and no references to separate files, so structure is present but content that should be split is not.	3 / 5
	Total	13 / 20 Passed

Description

23%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 severely weak: it names no concrete capability, omits any 'what' statement, and repeats the domain phrase tautologically. It only barely conveys a trigger and a domain, leaving it generic and conflict-prone.

Suggestions

State concretely what the skill does, e.g. 'Orchestrates multi-agent incident response: detection, mitigation, root-cause analysis, and blameless postmortem.'

Replace the tautological 'incident response incident response' with varied natural triggers users actually say, e.g. 'Use during production outages, SEV-1/P0 incidents, on-call escalations, or postmortem authoring.'

Add distinguishing scope so it does not collide with generic SRE or observability skills, e.g. scoped to multi-agent incident command workflows.

Dimension	Reasoning	Score
Specificity	The description 'Use when working with incident response incident response' names no concrete actions at all, only repeating the domain tautologically, matching the 'entirely vague; no concrete actions' anchor.	1 / 5
Completeness	Only a 'when' clause is present ('Use when working with incident response incident response') with no 'what' describing what the skill does, matching the 'only when present without what' anchor.	2 / 5
Trigger Term Quality	'incident response' is a natural term a user might say, but it appears only once (brokenly repeated) with no synonyms or variations like outage, SEV, on-call, or postmortem, falling below the midpoint.	2 / 5
Distinctiveness Conflict Risk	'incident response' is a recognizable domain, but the description gives no distinguishing triggers or scope detail, so it could still overlap with related SRE/on-call skills.	3 / 5
	Total	8 / 20 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: 3eff4af

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.