CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

triage

Gatekeep and review GitHub issues and pull requests for Qwen Code maintainers. Use for GitHub Action issue triage, PR admission checks, product-direction review, KISS-focused PR review, and staged bilingual GitHub comments.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 is a dense, highly operational overview: exact commands, a fully specified draft-publishing protocol, and explicit safety guardrails (never execute PR-derived code, label/write restrictions) with validation checkpoints for batch GitHub writes. Its weaknesses are minor — a couple of over-long rule passages and stage detail that lives entirely in the referenced workflow files.

DimensionReasoningScore

Conciseness

The body is telegraphic and assumes competence ("Run staged admission via `gh`. Post comment after each stage.") with no concept explanations, but two passages could be trimmed: the "No fabricated policies" bullet's long exception chain and the PR-enrichments rationale paragraph. Not 5 because those minor instances of over-explanation remain; not 3 because the density is otherwise uniformly lean and operational.

4 / 5

Actionability

Fully executable throughout: exact `gh ... --json` field lists, draft-directory setup commands, a table of exact `actions.jsonl` JSON shapes, the marker-line format, and the publisher invocation with `--dry-run`. Not 4 because the commands and JSON examples cover the common cases copy-paste ready, with no gaps needing inference.

5 / 5

Workflow Clarity

The run sequence is clear (mandatory pre-flight, staged admission, draft-only publishing) with explicit validation for the batch write operations — duplicate guard exit conditions, fail-closed publisher rules, stale-commit skip, dry-run preview. Not 5 because the detailed stage sequence is deferred to the reference files and the pre-flight section's late placement requires a corrective "before any other action" callout; not 3 because validation checkpoints for the risky write path are explicit, not implicit.

4 / 5

Progressive Disclosure

SKILL.md is a genuine overview with well-signaled, one-level-deep references — "Issue → read `references/issue-workflow.md`", "PR → read `references/pr-workflow.md`" — and both files exist in the bundle, pointing back to SKILL.md rather than nesting further. Not 4 because the split is clean: shared rules and publishing protocol inline, per-type stage detail in the two reference files.

5 / 5

Total

18

/

20

Passed

Description

87%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 well-constructed: third-person voice, a clear what, and an explicit "Use for" trigger clause listing concrete scenarios, all scoped to a distinct niche. Its only weakness is that some capability phrasing ("gatekeep", "KISS-focused", "staged bilingual") is insider jargon rather than language a broader set of users would naturally say.

DimensionReasoningScore

Specificity

Names the domain ("GitHub issues and pull requests") and lists several concrete actions — "issue triage, PR admission checks, product-direction review, KISS-focused PR review, and staged bilingual GitHub comments" — with minor gaps such as the somewhat abstract lead verb "Gatekeep". Not 5 because a couple of the listed actions are process jargon rather than fully concrete capabilities; not 3 because coverage goes well beyond 1-2 actions.

4 / 5

Completeness

Explicitly answers both: what — "Gatekeep and review GitHub issues and pull requests for Qwen Code maintainers" — and when — "Use for GitHub Action issue triage, PR admission checks, product-direction review, KISS-focused PR review, and staged bilingual GitHub comments" with concrete trigger scenarios. Not 4 because the "Use for" clause is explicit and specific rather than merely present with room for improvement.

5 / 5

Trigger Term Quality

"issue triage", "PR admission checks", and "PR review" are phrases a maintainer would naturally say, and "GitHub Action" grounds the automation context. Not 5 because common variations like "code review", "gh", or "pull request" (unabbreviated) are missing; not 3 because the natural terms present go beyond a single generic keyword.

4 / 5

Distinctiveness Conflict Risk

The scope is tightly pinned to "Qwen Code maintainers" and GitHub Action-driven triage, forming a clear niche with distinct triggers and minimal overlap with generic code-review or issue-management skills. Not 4 because the maintainer/repo scoping removes even the minor overlap a broader PR-review description would carry.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

QwenLM/qwen-code

Path

.qwen/skills/triage/SKILL.md

Reviewed

Table of Contents

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.