CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

79

Quality

100%

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

100%

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

The SKILL.md body is a lean, action-oriented overview that gives exact commands and guardrails while deferring stage detail to real, one-level-deep reference files. It includes explicit pre-flight validation checkpoints and duplicate-guard idempotency logic, scoring at the top of every dimension.

DimensionReasoningScore

Conciseness

The body is dense with operational content (exact gh JSON fields, --body-file vs --body distinction, guardrails) and assumes Claude's competence without explaining basic PR/Git concepts; it exceeds level 2 because there is no conceptual padding, only a couple of long enrichments/cross-reference lines.

3 / 3

Actionability

Provides copy-paste-ready executable commands — 'gh issue view "$NUM" --repo "$REPO" --json ...', 'enter_worktree(name: "triage")', 'exit_worktree(action: "remove")', the env-resolution chain, and the exact comment marker — matching the level-3 anchor for fully executable guidance.

3 / 3

Workflow Clarity

Clear sequence (Resolve -> Fetch -> Rules -> Duplicate Guard -> Format -> Pre-flight -> Workflow) with explicit validation checkpoints — the 'DO NOT SKIP' pre-flight checks, testing-evidence rules, and duplicate-guard exit-vs-rerun branching provide the feedback loops the level-3 anchor rewards; level 2's missing-checkpoint gap does not apply.

3 / 3

Progressive Disclosure

Body is a well-signaled overview that delegates detail to two verified, one-level-deep reference files ('Issue -> read references/issue-workflow.md', 'PR -> read references/pr-workflow.md'), both of which exist; content is appropriately split with easy navigation, matching the level-3 anchor.

3 / 3

Total

12

/

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.

The description is third-person, concise, and explicitly pairs concrete capabilities with a 'Use for ...' trigger clause, satisfying all four dimensions at the top of the scale. It is well-targeted to its maintainer audience without vague fluff or over-claims.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'issue triage, PR admission checks, product-direction review, KISS-focused PR review, and staged bilingual GitHub comments' — matching the level-3 anchor that lists several specific concrete actions; it is above level 2 which only names a domain and some actions.

3 / 3

Completeness

Answers both 'what' ('Gatekeep and review GitHub issues and pull requests') and 'when' with an explicit 'Use for ...' trigger clause enumerating the scenarios; this meets the level-3 anchor requiring explicit what-and-when triggers.

3 / 3

Trigger Term Quality

Natural maintainer-facing terms ('GitHub issues', 'pull requests', 'PR review', 'issue triage', 'GitHub Action') give good coverage of what a user would say to invoke this skill; it exceeds level 2's 'some relevant keywords but missing common variations'.

3 / 3

Distinctiveness Conflict Risk

Scoped to a clear niche — GitHub issue/PR triage for Qwen Code maintainers with distinct CI-triage triggers — making it unlikely to fire for the wrong skill; level 2's 'could still overlap' does not apply.

3 / 3

Total

12

/

12

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.

Validation15 / 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
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.