CtrlK
BlogDocsLog inGet started
Tessl Logo

issue-triage

Triage a dotnet/runtime GitHub issue with duplicate search, label check, reproduction, and ecosystem research, then recommend KEEP/CLOSE/NEEDS INFO. Use when asked to triage, evaluate, assess, or check a specific GitHub issue. Also use when asked "is this a duplicate", "should we close this", "check this issue", "what do you think about this issue", or when given a dotnet/runtime issue URL or number and asked for an opinion. Handles bug reports, API proposals, enhancements, performance regressions, and questions.

68

Quality

85%

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

70%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 well-sequenced, validation-rich triage workflow with strong safety gates and concrete search guidance, but it is verbose in places and critically depends on reference files that are absent from the bundle. The main risk is that the progressive-disclosure structure points to non-existent paths.

Suggestions

Ship the referenced bundle files (references/bug-triage.md, references/output-format.md, references/api-proposal-triage.md, references/area-label-heuristics.md, references/perf-regression-triage.md, references/question-triage.md, references/enhancement-triage.md, references/triage-patterns.md) so the signaled navigation resolves.

Tighten the 'Triage Mindset' and tone/style prose into concise bullets or move them to a reference file to reduce the ~480-line body length and improve token efficiency.

Inline the minimal output-format template skeleton in SKILL.md so the core deliverable is actionable even before the reference files are opened.

DimensionReasoningScore

Conciseness

At ~480 lines the body is mostly efficient and does not explain concepts Claude already knows, but several coaching/philosophy sections (notably 'Triage Mindset', tone guidelines, and expanded prose) could be tightened, sitting at the lower edge of anchor 3 rather than the padding of anchor 2.

3 / 5

Actionability

Provides concrete executable guidance — real search syntax ('Search: "keyword1 keyword2" in:title,body repo:dotnet/runtime'), specific labels, and classification tables — but the core executable output template is delegated to reference files, leaving minor gaps typical of anchor 4.

4 / 5

Workflow Clarity

Steps 0-8 are clearly sequenced with explicit validation checkpoints (safety scan 'MUST complete before any subsequent steps', the full-stop protocol, 'Do not proceed until they choose') and feedback loops for this risky/post-to-GitHub context, matching anchor 5.

5 / 5

Progressive Disclosure

Sectioning and one-level-deep reference signaling are well done, but scoring against the actual bundle structure reveals the references/ directory is empty — the 9+ referenced files (bug-triage.md, output-format.md, etc.) do not exist, so the signaled navigation is broken, capping this at anchor 3.

3 / 5

Total

15

/

20

Passed

Description

100%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 exemplary: it specifies concrete actions, lists comprehensive natural trigger phrases, explicitly answers both what and when, and is tightly scoped to dotnet/runtime triage with low conflict risk. No improvements needed.

DimensionReasoningScore

Specificity

Names multiple concrete actions ('duplicate search, label check, reproduction, and ecosystem research') plus the output ('recommend KEEP/CLOSE/NEEDS INFO') and five handled issue types, giving comprehensive coverage rather than the minor gaps of anchor 4.

5 / 5

Completeness

Explicitly answers both 'what' (the triage actions and KEEP/CLOSE/NEEDS INFO output) and 'when' ('Use when asked to triage... Also use when asked...') with concrete trigger phrases, matching the anchor 5 example.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases users would actually say ('is this a duplicate', 'should we close this', 'check this issue', 'what do you think about this issue') plus the verbs 'triage, evaluate, assess, or check' — matching the synonyms-and-natural-phrases coverage of anchor 5.

5 / 5

Distinctiveness Conflict Risk

Clearly scoped to 'dotnet/runtime GitHub issue' with a distinct niche and repository-specific triggers, giving minimal overlap with other skills as required by anchor 5.

5 / 5

Total

20

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 12 missing, 1 suspicious

Warning

referenced_paths_exist

Referenced path issues: 17 missing

Warning

Total

14

/

16

Passed

Repository
dotnet/runtime
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.