Name: triage-issue
Rating: 76.8 (1 reviews)
Author: docker

triage-issue

Analyze a single GitHub issue for docker/docs — check whether the problem still exists, determine a verdict, and report findings. Use when asked to triage, assess, or review an issue, even if the user doesn't say "triage" explicitly: "triage issue 1234", "is issue 500 still valid", "should we close #200", "look at this issue", "what's going on with #200".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

92%

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

A highly actionable, concise triage workflow with clear sequencing and verification checkpoints; its main weakness is progressive disclosure, as all reference material lives inline in one file with no separate reference files.

Suggestions

Move the area-label catalog (lines 120–129) and the vendored-content/upstream-ownership table into a references file (e.g. references/labels.md), keeping only the routing rule inline so SKILL.md stays a lean overview.

Extract the per-verdict label-API command blocks into a short reference snippet or script so the decision logic in step 6 reads as a compact verdict table rather than repeated command boilerplate.

Add a one-line explicit pre-action checkpoint in step 6 (e.g. 'Confirm the verdict evidence above before issuing any close/label command') to make the verification gate before outward-facing actions unmistakable.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence, and avoids explaining known concepts; the inline area-label list is necessary repo-specific reference data rather than padded context, matching the score-3 'every token earns its place' anchor.	3 / 3
Actionability	Every verdict and investigation step is backed by fully executable gh/gh api commands with concrete jq filters and exact label names, making it copy-paste ready per the score-3 anchor rather than pseudocode at score 2.	3 / 3
Workflow Clarity	Steps 1–7 are explicitly sequenced with verification checkpoints (fetching URLs in step 3, reading current content in step 4, checking PR cross-references before deciding to fix) that gate the verdict, satisfying the score-3 anchor with feedback before the semi-destructive close/label actions.	3 / 3
Progressive Disclosure	It is a well-organized single file but a ~130-line monolith with a bulky inline area-label reference list and no offloaded bundle references; since it exceeds the under-50-line carve-out, it lands at the score-2 'content that could be separate is inline' anchor rather than a 3.	2 / 3
	Total	11 / 12 Passed

Description

100%

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, third-person description that concretely states capabilities, answers both what and when, and supplies a rich set of natural trigger phrases tightly scoped to issue triage for docker/docs.

Dimension	Reasoning	Score
Specificity	"Analyze a single GitHub issue... check whether the problem still exists, determine a verdict, and report findings" lists multiple specific concrete actions, matching the score-3 anchor rather than the partial score-2 example.	3 / 3
Completeness	It states both what (analyze, check existence, determine verdict, report) and when ("Use when asked to triage, assess, or review an issue") with explicit triggers, satisfying the score-3 anchor; it is not missing the 'when' clause that would cap it at 2.	3 / 3
Trigger Term Quality	Natural trigger phrases like "triage issue 1234", "is issue 500 still valid", "should we close #200", "look at this issue", and "what's going on with #200" cover exactly what a user would say, exceeding the score-2 single-keyword bar.	3 / 3
Distinctiveness Conflict Risk	The docker/docs issue-triage niche with distinctive triggers (issue numbers, close/valid phrasings) is unlikely to fire for unrelated skills, fitting the clear-niche score-3 anchor rather than the somewhat-generic score-2.	3 / 3
	Total	12 / 12 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: docker/docs
Commit: 67d0999

Reviewed: about 10 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.