Name: incident-response-incident-response
Rating: 39.2 (1 reviews)
Author: administrakt0r

Blog Docs Log in Get started

incident-response-incident-response

Use when working with incident response incident response

Quality

37%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/incident-response-incident-response/SKILL.md

The canonical home for this skill is incident-response-incident-response in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

38%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 skill is a verbose, monolithic multi-agent incident-response playbook with clear phase sequencing but significant padding, invented subagent types, no validation feedback loops, and a broken external reference. It reads more like generated boilerplate than a lean, navigable skill.

Suggestions

Cut the extended-thinking meta-block and the generic 'Clarify goals / Apply best practices' instructions — they restate what Claude already does and inflate the token budget.

Add explicit validation checkpoints between phases (e.g. 'Confirm mitigation held for 10 min before declaring resolved; if regressed, return to Phase 2') to satisfy the destructive-operation feedback-loop requirement.

Either create the referenced 'resources/implementation-playbook.md' (under the standard 'references/' directory) or remove the broken reference, and move the long per-step prompts and coordination protocols into separate reference files.

Dimension	Reasoning	Score
Conciseness	The body includes an unnecessary extended-thinking meta-block, generic instructions Claude already knows ('Clarify goals... Apply relevant best practices'), and duplicated use/do-not-use trigger sections restating the domain.	2 / 5
Actionability	It gives concrete Task-tool prompt structure with numbered actions and expected outputs, but the subagent_type values (e.g. 'incident-responder', 'error-debugging::debugger') are invented and non-resolvable, with no executable code or commands.	3 / 5
Workflow Clarity	The 5-phase/13-step sequence is clearly laid out, but this is a destructive/batch production skill lacking explicit validate->fix->retry feedback gates between phases, capping the score.	3 / 5
Progressive Disclosure	No bundle files exist and the sole reference ('resources/implementation-playbook.md') is broken and in a non-standard directory, while all detailed prompts and protocols are inlined in a monolithic ~165-line body.	2 / 5
	Total	10 / 20 Passed

Description

36%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 malformed and weak: it duplicates 'incident response incident response', provides only a trigger clause with no statement of what the skill does, and lacks synonym coverage. It barely communicates the skill's purpose or distinct trigger surface.

Suggestions

Rewrite the description to state what the skill does in third person (e.g. 'Orchestrates multi-agent incident response: triage, mitigation, root-cause, and blameless postmortem') before the trigger clause.

Expand trigger terms to include natural user phrasings users actually say: 'production outage', 'SEV/P0', 'on-call incident', 'postmortem', 'service degradation'.

Remove the duplicated 'incident response incident response' string, which reads as a templating artifact and hurts specificity and distinctiveness.

Dimension	Reasoning	Score
Specificity	The description names the domain ('incident response') but states zero concrete actions — there is no verb describing what the skill does, only a trigger clause.	2 / 5
Completeness	Only a 'when' clause ('Use when working with incident response incident response') is present with no 'what' — matching the 'only when is present without what' anchor.	2 / 5
Trigger Term Quality	'incident response' is a natural user phrase, but it is duplicated and missing common variations/synonyms such as outage, SEV, postmortem, or on-call.	3 / 5
Distinctiveness Conflict Risk	Incident response is a recognizable niche, but the bare description could still overlap with monitoring, alerting, and on-call skills.	3 / 5
	Total	10 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/incident-response-incident-response/SKILL.md
Commit: 57c135b

Reviewed: 4 days 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.