Name: incident-responder
Rating: 40.8 (1 reviews)
Author: administrakt0r

incident-responder

Expert SRE incident responder specializing in rapid problem resolution, modern observability, and comprehensive incident management.

Quality

40%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/incident-responder/SKILL.md

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

Quality

Content

31%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 presents a comprehensive but generic SRE playbook that largely restates knowledge Claude already has, with abstract guidance and no executable commands. Its one external reference is broken and most content that belongs in supporting files is inlined.

Suggestions

Trim restated SRE concepts ('Behavioral Traits', 'Response Principles', severity-tier definitions) to only what is non-obvious or project-specific, and cut the closing aphorism.

Add concrete, executable examples for at least the common cases (e.g. rollback commands, canary/feature-flag toggles, metric/burn-rate queries, status-page update templates).

Either create the referenced 'resources/implementation-playbook.md' (and align the path with the actual bundle directory) or move the severity/tooling/post-mortem detail into separate reference files and link to them one level deep.

Dimension	Reasoning	Score
Conciseness	The body is a long wall of generic SRE knowledge Claude already knows (incident command roles, severity tiers, error budgets, circuit breakers) plus padded sections ('Behavioral Traits', 'Response Principles', closing aphorism) that add little novel instruction.	2 / 5
Actionability	Guidance is high-level and descriptive ('Quick wins: Traffic throttling, feature flags, circuit breakers') with no concrete commands, queries, or code; Claude is told what to consider, not what to run.	2 / 5
Workflow Clarity	There is a clear phased sequence (first 5 minutes, investigation, resolution, post-incident) with validation sections present, but checkpoints are implicit and abstract rather than concrete verify-and-proceed gates.	3 / 5
Progressive Disclosure	No bundle files exist and the single reference points to a non-existent 'resources/implementation-playbook.md'; nearly 200 lines of separable material (severity tables, tool lists, post-mortem process) are inlined into one monolithic file.	2 / 5
	Total	9 / 20 Passed

Description

48%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 identifies a clear, distinct domain but relies on abstract capability language and omits any explicit 'when to use' trigger guidance. It is recognizable but not actionable enough to reliably trigger on natural user phrasing.

Suggestions

Add a concrete 'Use when ...' clause naming natural trigger phrases such as production outages, on-call incidents, SEV/P0 escalation, or incident post-mortems.

Replace abstract capability nouns with concrete actions (e.g. 'triages severity, stabilizes services via rollback/traffic shifting, coordinates incident command, runs blameless post-mortems').

Include common synonyms users actually say (outage, on-call, SEV-1/P0, post-mortem) to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Expert SRE incident responder') but its capabilities are abstract ('rapid problem resolution, modern observability, and comprehensive incident management') with no concrete, enumerated actions.	2 / 5
Completeness	It gives a clear 'what' (expertise in SRE incident response) but no explicit 'when' trigger clause; per the rubric a missing 'Use when...' clause caps completeness at 3.	3 / 5
Trigger Term Quality	It includes relevant natural terms ('incident responder', 'SRE', 'incident management', 'observability') but omits common variations users say (e.g. 'outage', 'on-call', 'production down') and lacks any 'Use when' phrasing.	3 / 5
Distinctiveness Conflict Risk	The SRE incident-response niche is fairly distinct with minimal overlap risk against other skills, though adjacent observability or DevOps skills could partially overlap.	4 / 5
	Total	12 / 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-responder/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.