triage-issue

Use when triaging a GitHub issue - analyzes issue, checks for duplicates, categorizes, and drafts response

Quality

81%

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

Quality

Content

77%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.

Highly actionable and well-sequenced with strong validation checkpoints, but the document is long and monolithic with some template redundancy. Splitting the response templates into a reference file would improve token efficiency and progressive disclosure.

Suggestions

Move the per-type response templates (USER ERROR, OLD VERSION, NEEDS INFO, DUPLICATE, FEATURE REQUEST) into a references/ file and link to it, reducing SKILL.md length and redundancy.

Tighten the security analysis prose — the Hetzner CI/cancellation guidance is useful domain knowledge but could be condensed into a few bullet points rather than multi-line paragraphs.

Add a brief note at the top of Step 5 that templates are illustrative and should be adapted, to avoid Claude copying boilerplate verbatim.

Dimension	Reasoning	Score
Conciseness	The skill is ~270 lines with mostly efficient, concrete content, but the per-type response templates are verbose and partially duplicative (repeated 'Hi @{author}' blocks) and could be tightened, fitting 'mostly efficient but could be tightened' rather than the lean top anchor.	2 / 3
Actionability	It provides fully executable `gh` commands, concrete classification and action tables, copy-paste response templates, and a filled-in output template, matching the 'fully executable; copy-paste ready' anchor.	3 / 3
Workflow Clarity	A clear six-step sequence (with a diagram) is backed by a classification checklist and a 'Verify Independently' security checkpoint that functions as a validate-before-acting loop, matching 'clear sequence with explicit validation steps and checklists'.	3 / 3
Progressive Disclosure	No bundle files (references/, scripts/, assets/) exist and the body is a single monolithic document; section organization is reasonable, but content such as the response templates could be split into referenced files, fitting 'some structure but content that should be separate is inline'.	2 / 3
	Total	10 / 12 Passed

Description

85%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.

A strong description with explicit trigger guidance and concrete, multiple actions. The only weakness is trigger-term coverage, which uses one natural phrase rather than a spread of synonyms users might say.

Suggestions

Broaden trigger terms to include variations users naturally say, e.g. 'Use when triaging, reviewing, labeling, or responding to a GitHub issue'.

Dimension	Reasoning	Score
Specificity	The description names multiple concrete actions — 'analyzes issue', 'checks for duplicates', 'categorizes', and 'drafts response' — rather than vague language, matching the top anchor for listing several specific actions.	3 / 3
Completeness	It explicitly answers both 'what' (analyzes, checks duplicates, categorizes, drafts response) and 'when' via the explicit 'Use when triaging a GitHub issue' trigger clause, matching the top anchor.	3 / 3
Trigger Term Quality	'triaging a GitHub issue' includes natural terms a user might say, but coverage of common variations is thin (e.g. no synonyms like 'review', 'label', 'respond to issue'), so it sits at 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	'triaging a GitHub issue' carves out a clear, narrow niche with distinct triggers unlikely to collide with other skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	11 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: mysticaltech/terraform-hcloud-kube-hetzner
Path: .claude/skills/triage-issue/SKILL.md
Commit: a8b696d

Reviewed: 11 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.