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.

74

Quality

92%

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

85%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.

The body is a well-structured, highly actionable triage workflow with explicit safety checkpoints and verified one-level-deep references. Its main weakness is conciseness: several constraints are repeated across the opening blockquote, Step 8, and the Anti-Patterns section, inflating token cost without adding clarity. Consolidating these would lift the score.

Suggestions

Consolidate the no-autonomous-action guidance: state it once (e.g. in the opening blockquote or Anti-Patterns) and cross-reference rather than repeating the full constraint in Step 8 as well.

Merge the separate Tone, Style, and Content rules for suggested responses into a single compact checklist to cut repetition while preserving the requirements.

Either link supplementary-labels.md from the relevant step (Step 1/2 label handling) or note why it is intentionally unlinked, so every bundle file is discoverable from the body.

DimensionReasoningScore

Conciseness

The 488-line body is mostly domain-specific guidance Claude would not already know, but several constraints are restated multiple times (the no-autonomous-action warning appears in the opening blockquote, Step 8, and Anti-Patterns) and the tone/style/content rules could be consolidated. It is mostly efficient but could be tightened, fitting the middle anchor.

2 / 3

Actionability

Provides concrete tables for issue types, priorities, and recommendation criteria, plus specific tooling ("gh issue list --search", "github-mcp-server-search_issues") and exact search-syntax examples, giving fully executable guidance for an instruction-only skill.

3 / 3

Workflow Clarity

A clearly sequenced Step 0-8 workflow with an explicit safety checkpoint ("0b: Safety scan -- MUST complete before any subsequent steps"), a full-stop protocol, and validation-style gating ("verify whether the merged PR actually addresses the reported problem") matches the top anchor for clear sequencing with checkpoints.

3 / 3

Progressive Disclosure

SKILL.md is an overview pointing to eight one-level-deep reference files, every cited path verified to exist as a real file, each reference signaled with its purpose. The only minor gap is that supplementary-labels.md exists but is not linked from the body, which is negligible against the top anchor.

3 / 3

Total

11

/

12

Passed

Description

100%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.

The description is exemplary: it states concrete capabilities, an explicit output recommendation, and a thorough set of natural-language triggers, all scoped to a distinct niche. It clearly answers both what the skill does and when to use it. No changes needed.

DimensionReasoningScore

Specificity

Names multiple concrete actions -- "duplicate search, label check, reproduction, and ecosystem research" and a concrete output "recommend KEEP/CLOSE/NEEDS INFO" -- matching the top anchor that lists several specific actions.

3 / 3

Completeness

Explicitly answers both what it does (research + KEEP/CLOSE/NEEDS INFO recommendation) and when to use it via an explicit "Use when..." clause, satisfying the top anchor.

3 / 3

Trigger Term Quality

Includes natural phrasings a user would actually say ("triage, evaluate, assess, or check", "is this a duplicate", "should we close this", "check this issue"), giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Scoped tightly to "dotnet/runtime GitHub issue" with distinct triggers and a well-defined niche, making it unlikely to fire for an unrelated skill.

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

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

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.