Name: ci-scan-feedback
Rating: 68 (1 reviews)
Author: dotnet

ci-scan-feedback

Audit the local dotnet/machinelearning ci-scan skill using recent ci-scan issues, maintainer feedback, and an optional local scan report, then draft targeted prompt improvements. Use when reviewing scanner quality, investigating false-positive KBEs, or improving the local ci-scan methodology.

Quality

83%

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

78%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.

A well-structured, concise instruction-only skill with a clear sequenced workflow and good guardrails. Could tighten a few clarifications and make the proposed-edit step more concrete.

Suggestions

Tighten the 'when'/'how' in step 7 ('Translate each confirmed failure mode into the smallest rule-shaped edit') with a one-line example of what a rule-shaped edit looks like.

Add an explicit verification step for proposed edits (e.g., re-checking the edit against the rubric row it addresses) to strengthen the workflow's feedback loop.

Trim the parenthetical clarifications in the Inputs table and the opening note about not depending on GitHub Actions logs where the information is implied by the workflow.

Dimension	Reasoning	Score
Conciseness	Lean, instruction-only body with no over-explanation of concepts Claude already knows; a few clarifying phrases (inputs defaults, the no-tracker-issue note) could be trimmed but generally earn their place.	4 / 5
Actionability	Concrete, specific guidance throughout (e.g., 'Collect open and closed dotnet/machinelearning issues whose title starts with [ci-scan]'), a rubric scoring checklist, and a defined output format; a few steps like 'smallest rule-shaped edit' stay somewhat abstract.	4 / 5
Workflow Clarity	An 8-step sequenced workflow with a safety checkpoint (untrusted-data handling), an explicit scoring checklist, and an edit-gate; the skill only proposes changes so the destructive-cap does not apply, though an explicit verify-the-proposed-edit loop is absent.	4 / 5
Progressive Disclosure	Under 50 lines with well-organized sections (Inputs, Workflow, Output) and clearly signaled one-level-deep markdown links to the sibling ci-scan skill's files; no bundle directories exist to verify.	5 / 5
	Total	17 / 20 Passed

Description

87%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: third-person, concise, with explicit what/when guidance and a distinct niche. Minor room to broaden trigger synonyms and enumerate more sub-actions.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete actions ('Audit the local dotnet/machinelearning ci-scan skill', 'draft targeted prompt improvements') plus named inputs (issues, maintainer feedback, local scan report), but stops short of a comprehensive enumeration of distinct sub-actions.	4 / 5
Completeness	Explicitly answers both 'what' (audit the ci-scan skill and draft targeted prompt improvements) and 'when' with concrete trigger phrases in a 'Use when...' clause.	5 / 5
Trigger Term Quality	'Use when reviewing scanner quality, investigating false-positive KBEs, or improving the local ci-scan methodology' provides good natural-phrase coverage for the niche, though it leans on jargon and omits common synonyms.	4 / 5
Distinctiveness Conflict Risk	Targets a tight, specific niche (dotnet/machinelearning ci-scan) with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 4 suspicious	Warning

	Total	15 / 16 Passed

Repository: dotnet/machinelearning
Path: .github/skills/ci-scan-feedback/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.