dotnet-inspect-query

Output formats, -D/-S discovery and selection, -Q query-capability discovery, value projection, @ categories, and output limits shared across commands.

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/query/SKILL.md

Quality

Content

65%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 concrete reference manual: executable commands are excellent, but the skill is a monolithic ~520-line inline catalog with no progressive disclosure into reference files and an implicit rather than explicit discover/select/project workflow.

Suggestions

Move the stable reference material — the category table (@Package/@Files/@Surface...), the -Q query-term semantics (license/depends/references/depends-transitive), and the --envelope route table — into one or two reference files, keeping SKILL.md as a short overview with well-signaled links.

Lead with an explicit numbered workflow (identify result space -> -D/-Q discover -> -S select -> --columns/--fields project -> -n/--rows limit) so the sequence currently spread across sections is a single checklist.

Trim 'currently'/'remains non-projectable' status sentences or consolidate them into a single 'Current limitations' section to cut time-sensitive tokens from the main flow.

Dimension	Reasoning	Score
Conciseness	Nearly every sentence is tool-specific information Claude cannot infer, but the body runs ~520 lines with dense caveat chains ('remains non-projectable', 'currently', exception-per-exception notes) and several time-sensitive version/format markers that could be trimmed or moved to a deprecation section.	3 / 5
Actionability	Dozens of copy-paste-ready bash invocations with concrete flags, arguments, and expected behaviors (e.g. 'dnx dotnet-inspect -y -- member JsonSerializer --platform System.Text.Json -D --tsv', '--where "tool=true"', '--where "depends starts-with Microsoft.Extensions."') cover the common discovery, selection, projection, and share cases.	5 / 5
Workflow Clarity	A discover-then-select-then-project sequence is stated ('Discover the shape first where available, then select and project', 'Discover first instead of guessing names'), but it is distributed across feature sections rather than presented as an ordered workflow, and error-recovery guidance (what to do when a section name does not exist or a count cannot be exact) is implicit.	3 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent), so the entire capability catalog — category tables, query-term reference, envelope route table — is inlined in one large SKILL.md. Section headers and tables give it real structure, but hundreds of lines of reference material that belong in separate files sit inline.	3 / 5
	Total	14 / 20 Passed

Description

51%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 precise capability inventory for the tool's shared query/output system, but written as internal flag shorthand: it lacks the domain keywords and explicit use-when triggers that let it fire on real requests.

Suggestions

Rewrite in natural domain language, e.g. 'Shapes and queries .NET inspection output: output formats, section discovery (-D) and selection (-S), query capabilities (-Q), value projection, and row limits shared across dotnet-inspect commands.'

Add an explicit trigger clause: 'Use when inspecting .NET packages, libraries, types, or members with dnx dotnet-inspect and the user needs tables, TSV/JSON output, section selection, or filtered queries.'

Include the plain-language synonyms users actually say — .NET, NuGet package, assembly, API surface — instead of only flag jargon like '-D/-S' and '@ categories'.

Dimension	Reasoning	Score
Specificity	It enumerates concrete capabilities ('Output formats, -D/-S discovery and selection, -Q query-capability discovery, value projection, @ categories, and output limits') — several specific items with minor gaps — though they are noun phrases rather than named actions.	4 / 5
Completeness	The 'what' is present and clear (the shared query/output surface across the tool's commands), but there is no 'Use when...' clause or equivalent trigger guidance, capping completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	The description is almost entirely CLI jargon ('-D/-S discovery', '-Q query-capability discovery', '@ categories'); it omits the natural terms a user or Claude would actually say — .NET, NuGet, package, assembly, inspect — so it would rarely match a natural-language request.	2 / 5
Distinctiveness Conflict Risk	The flag-level triggers are niche and unlikely to collide with unrelated skills, but the description never names the tool or domain (dotnet/.NET inspection), so its distinctiveness depends on the 'name' field rather than the description itself.	4 / 5
	Total	13 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (533 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: richlander/dotnet-inspect
Path: skills/query/SKILL.md
Commit: 71591ae

Reviewed: 3 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.