Tessl • The management layer for AI agent skills

SkillPublic

dotnet-inspect-private-feeds

Inspect packages from private or folder NuGet feeds using explicit sources, mapping and noninteractive authentication; preserve source authority and distinguish failures from package absence.

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

90%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 dense, highly actionable reference for private/local NuGet feed inspection with executable commands, concrete configuration examples, and strong failure-diagnosis guidance. Its only weaknesses are the absence of an explicit validation feedback loop and the lack of any bundle structure to offload the deep authentication detail.

Dimension	Reasoning	Score
Conciseness	The body is lean and imperative with zero padding — lines like "An override does not disable mapping" and "A `401` means unreadable source, not absent package" carry only non-obvious, tool-specific behavior and never explain concepts Claude already knows.	5 / 5
Actionability	Fully executable throughout: copy-paste `dnx dotnet-inspect -y -- package MyCompany.Widget@1.2.3 --nugetconfig ./NuGet.Config` commands with flags, `dotnet tool install --global Microsoft.Artifacts.CredentialProvider.NuGet.Tool`, a concrete `<packageSourceMapping>` XML block, and named environment variables such as `ARTIFACTS_CREDENTIALPROVIDER_EXTERNAL_FEED_ENDPOINTS`.	5 / 5
Workflow Clarity	Sections sequence configuration ("Select and pin the source") through mapping, authentication, declaration sharing, and diagnosis, with real checkpoints like "Check provider discovery, endpoint matching, token scope and expiry before changing the ID"; however, there is no explicit ordered validate-then-fix-then-retry loop, so it sits at 'clear sequence with most checkpoints' rather than the full feedback-loop anchor.	4 / 5
Progressive Disclosure	Sections are well organized and depth is delegated via clearly signaled one-level pointers (`--help`, `explain "<question>"`, `skill compatibility`), but no bundle files exist and the 122-line body inlines deep credential-provider environment-variable detail; it exceeds the under-50-line simple-skill exception, so structure is good rather than exemplary.	4 / 5
	Total	18 / 20 Passed

Description

71%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 specific, third-person description with concrete actions and a clear niche, undermined by the missing 'Use when...' trigger clause and limited synonym coverage. Adding explicit trigger guidance would raise completeness from its capped 3.

Suggestions

Add an explicit trigger clause to the description, e.g. "Use when package evidence lives outside NuGet.org, or a private/local feed requires authentication" — the body already contains this guidance, so surface it in the description to lift completeness.

Include natural synonyms users would say, such as "Azure Artifacts", "GitHub Packages", "local or folder feed", and "authenticated feed", to improve trigger-term coverage.

State the 'when' in terms that distinguish it from the base NuGet.org inspection skill (e.g. "for private, local, or authenticated feeds rather than NuGet.org") to reduce the residual conflict risk with that closely related skill.

Dimension	Reasoning	Score
Specificity	In third-person voice it enumerates multiple concrete actions — "Inspect packages from private or folder NuGet feeds", "using explicit sources, mapping and noninteractive authentication", "preserve source authority and distinguish failures from package absence" — comprehensively covering inspection, source selection, mapping, authentication, and failure discrimination. It is not 4 because the action coverage has no notable gaps rather than 'minor gaps'.	5 / 5
Completeness	The 'what' is clear and concrete, but the description contains no "Use when..." clause or equivalent explicit trigger guidance (the body's "Use this skill when package evidence lives outside NuGet.org" is outside the description field), which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	"private or folder NuGet feeds" and "noninteractive authentication" are natural trigger phrases, but the description misses common synonyms a user would say such as "Azure Artifacts", "GitHub Packages", "local feed", or "authenticated feed" — good coverage with a few natural terms missing, not comprehensive.	4 / 5
Distinctiveness Conflict Risk	The private/folder-feed niche with source mapping and noninteractive authentication is mostly distinct from generic package-inspection skills, with only minor overlap risk against a closely related base NuGet.org inspection skill; it is not 5 because without an explicit 'when' clause it relies on the reader to disambiguate from that sibling skill.	4 / 5
	Total	16 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: richlander/dotnet-inspect
Path: skills/private-feeds/SKILL.md
Revision: e58afa8

Reviewed: 9 days ago

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.

dotnet-inspect-private-feeds

Table of Contents

Is this your skill?