Name: ci-scan
Rating: 75.2 (1 reviews)
Author: dotnet

ci-scan

Analyze recent dotnet/machinelearning MachineLearning-CI failures locally, identify stable failure signatures, deduplicate them against Known Build Error issues, and draft up to three actionable KBE issues. Use when asked to scan ML.NET CI, investigate recurring main-branch failures, or run the former ci-scan agent locally.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%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-structured instruction-only workflow that is lean, actionable, and built around explicit validation/approval checkpoints appropriate to a destructive batch operation. Progressive disclosure is clean, with both referenced files present and one level deep.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no basic concepts explained, no padding; every section (Inputs, Workflow, Local substitutions, Validation) earns its place.	5 / 5
Actionability	Provides concrete commands (`gh auth status`), concrete state paths (`/tmp/mlnet-ci-scan/`), and specific substitution rules, but the core scan mechanics are delegated to the referenced playbook rather than stated inline, leaving minor gaps.	4 / 5
Workflow Clarity	An 8-step sequence carries explicit checkpoints and approval gates for a batch/issue-writing operation ("Do not create issues", "Cap the run at three drafts", "Apply drafts only after the user explicitly approves"), plus a dedicated Validation section with named gates.	5 / 5
Progressive Disclosure	The SKILL.md is a concise overview that links to two one-level-deep, clearly-signaled reference files (playbook.md and ci-scan.instructions.md), both verified to exist, with content appropriately split and easy to navigate.	5 / 5
	Total	19 / 20 Passed

Description

92%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 concise yet comprehensive, clearly stating four concrete capabilities and an explicit natural-language trigger clause tied to a specific ML.NET CI domain. It avoids verbosity and over-claims while remaining highly distinctive.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Analyze recent ... failures locally", "identify stable failure signatures", "deduplicate them against Known Build Error issues", and "draft up to three actionable KBE issues" — giving comprehensive coverage with no generic filler.	5 / 5
Completeness	Explicitly answers "what" via four named actions and "when" via the "Use when asked to scan ML.NET CI, investigate recurring main-branch failures, or run the former ci-scan agent locally" clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ("scan ML.NET CI", "investigate recurring main-branch failures", "run the former ci-scan agent locally") with good synonym coverage, though a couple of common variants (e.g. "CI failures", "build breaks") are not present.	4 / 5
Distinctiveness Conflict Risk	The niche is highly specific (ML.NET CI failures, KBE issues, the former ci-scan agent) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

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/machinelearning
Path: .github/skills/ci-scan/SKILL.md
Commit: cd2fbd6

Reviewed: 10 days ago

Table of Contents

Discovery Implementation Validation

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.