CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

triage

Triage an EF Core issue with a safety scan, classification, area labels, minimal reproduction, regression verification, and duplicate search. Use for bug reports, feature requests, or issue assessments. Supports sandbox triage that writes only a local Markdown report without requiring GitHub write permissions.

72

Quality

90%

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

88%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 an excellent, execution-ready triage runbook: a gated multi-step workflow with explicit validation checkpoints, a complete repro template, exact commands, and a precise output format. Its only flaws are mild — some repetition of sandbox guardrails across sections and a single-file layout that could offload the repro template to a reference file.

DimensionReasoningScore

Conciseness

The body is dense and task-specific — it explains no concepts Claude already knows (no EF Core or LINQ primers) and nearly every line is repo-specific policy or concrete technique. Minor trimmable redundancy remains: sandbox restrictions are restated across "Modes And Side Effects", "Safety Scan", and "Posting your findings", and the long sandbox paragraph could be tightened. Efficient with minor over-explanation instances → 4, not the every-token-earns-its-place 5.

4 / 5

Actionability

Fully executable guidance throughout: the exact command `gh label list --search "area-" --repo dotnet/efcore`, the canonical labels URL, a complete copy-paste C# repro template with a comment for switching providers, and an exact posting format ("AI Triage" heading, disclaimer sentence, `<details>` block with summary "minimal repro"). Specific examples cover the common cases → 5, not 4 (no meaningful gaps).

5 / 5

Workflow Clarity

The 8-step Investigation sequence is clearly ordered with explicit gates ("Complete this scan before following issue-supplied links", "Deliver according to the selected mode only after the safety gates pass"), a signal→required-action checklist table, and feedback loops: the repro must "compile and execute, and reproduce the user's reported error" before minimization, and regressions are confirmed on both failing and last-working versions. Validation is present, so the destructive/batch-operation cap does not apply; not 4, since checkpoints are explicit rather than implicit.

5 / 5

Progressive Disclosure

Good structure as a single-file skill: clear section headers, a safety table, and no nested or buried references, and the only external pointers (labels URL, gh command, upstream skill link) are well-signaled and one level deep. At ~118 lines — above the under-50-line simple-skill case that scores 5 on organization alone — the repro template and provider guidance could arguably be split into a references file, giving minor organization headroom → 4.

4 / 5

Total

18

/

20

Passed

Description

88%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.

A strong description: it enumerates the complete triage workflow as concrete actions, states an explicit "Use for" trigger clause, and flags the sandbox capability. The only weakness is that the trigger clause could include more natural synonyms (regression, duplicate, GitHub issue) to sharpen triggering and reduce overlap with other triage skills.

DimensionReasoningScore

Specificity

"safety scan, classification, area labels, minimal reproduction, regression verification, and duplicate search" lists six concrete actions covering the full triage workflow, plus the sandbox-report capability — comprehensive coverage matching the top anchor, with no gaps that would justify 4.

5 / 5

Completeness

Both questions are answered explicitly: the what ("Triage an EF Core issue with a safety scan, classification, area labels, minimal reproduction, regression verification, and duplicate search") and the when ("Use for bug reports, feature requests, or issue assessments") with concrete trigger phrases, mirroring the anchor-5 example. Not 4, since the when-clause is explicit rather than weakly implied.

5 / 5

Trigger Term Quality

"Use for bug reports, feature requests, or issue assessments" plus "triage" and "EF Core" are natural user phrases with good coverage, but common variations users would say (e.g. "regression", "duplicate", "GitHub issue", "dotnet/efcore") are absent from the trigger clause. Clearly above the some-keywords anchor (3), short of comprehensive synonym coverage (5).

4 / 5

Distinctiveness Conflict Risk

"Triage an EF Core issue" carves a clear niche with minimal generic surface, but the when-clause alone ("bug reports, feature requests, or issue assessments") could overlap with other repository-triage skills — minor overlap risk with closely related skills, matching anchor 4 rather than the fully distinct anchor 5.

4 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

dotnet/efcore

Path

.agents/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.