CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

item-management

Own concrete MSBuild ItemGroup and item-expression questions. USE FOR: Include, Remove, Update, item identity and metadata, transforms, filtering, batching, duplicate or overlapping items, and reviews that verify whether those operations are correct. Generated items stay in scope when the central defect is item identity, metadata, batching, duplicate declarations, or glob/Remove/Update semantics. For a generated artifact missing from compilation or output, wrong target timing/path, or FileWrites clean tracking without a broader item-semantics defect, use including-generated-files. The item operation may be broken, suspected, or already correct. Exclude property-only issues, general incrementality with no item question, broad reviews with no concrete item concern, and non-MSBuild systems.

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

93%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-built reference skill: lean, concrete, executable XML patterns with genuine MSBuild gotchas (cross-product batching, glob/Remove/Update semantics, FileWrites tracking) presented in cleanly sectioned form. The one weakness is the absence of an explicit review/verification sequence despite the description promising use for reviews that verify item operations.

Suggestions

Add a short "How to verify item operations" section giving an ordered check sequence (identity/metadata correctness, batching scope, Exclude/Remove semantics, FileWrites coverage) to support the review use case named in the description.

Fold the pitfall checks into that sequence as explicit validation steps (e.g., confirm no cross-group %() mixing before approving batching logic) so reviewers get a feedback loop rather than a catalog.

DimensionReasoningScore

Conciseness

The body is a lean pattern catalog: brief rule statements ("`Exclude` only works on `Include`", "`Update` does not add items") followed immediately by real XML snippets, with no padding or explanation of concepts Claude already knows. Set subtraction appears twice (Remove section and Exclude section) but each instance teaches a distinct pattern, so every section earns its place — matching the 5 anchor rather than 4.

5 / 5

Actionability

Every pattern ships as copy-paste-ready XML drawn from a real source ("from `Microsoft.Common.CurrentVersion.targets`"): Include/Remove/Update groups, target- and task-level batching, transforms, Exclude set subtraction, conditional inclusion, PrivateAssets, plus BAD/GOOD pitfall pairs. This fully covers the common cases per the 5 anchor.

5 / 5

Workflow Clarity

The Common Pitfalls section provides implicit checkpoints (cross-product batching BAD/GOOD pair, generated-files-in-source-tree, "Every file created during a target must be added to `@(FileWrites)`"), but there is no explicit sequence or verify step for the review workflow the description promises ("reviews that verify whether those operations are correct"). This sits at 4 — checkpoints present in reference form with minor gaps — rather than 5, which would require explicit validation steps.

4 / 5

Progressive Disclosure

The skill is a single self-contained file with no bundle directories; at ~160 lines of interdependent patterns, none of the content clearly belongs in a separate file, so no reference nesting is needed. Clear section headers (Include/Remove/Update, Batching, Transforms, Exclude, Pitfalls) make navigation easy, matching the 5 anchor's ease of navigation without requiring external references.

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.

An excellent description: it names the domain, enumerates concrete capabilities, provides an explicit USE FOR trigger clause, and actively disambiguates against a sibling skill and out-of-scope areas in third-person voice. The only gap is a few missing natural trigger terms (Exclude, .csproj/.proj).

Suggestions

Add "Exclude" to the USE FOR list since it is a core item operation covered in the skill body but absent from the description's trigger terms.

Mention project-file forms users naturally reference (e.g., ".csproj" or "project files") to round out trigger synonyms and file extensions.

DimensionReasoningScore

Specificity

The description lists multiple specific concrete operations — "Include, Remove, Update, item identity and metadata, transforms, filtering, batching, duplicate or overlapping items" — giving comprehensive coverage of the MSBuild item-operation domain in third-person voice. This matches the 5 anchor (multiple specific concrete actions, comprehensive) rather than 4, since no meaningful item operation is left out.

5 / 5

Completeness

Explicitly answers both questions: the "what" via "Own concrete MSBuild ItemGroup and item-expression questions" and the "when" via the explicit "USE FOR:" clause with concrete trigger phrases plus scope clarifications ("Generated items stay in scope when..."). Matches the 5 anchor exactly; clearly better than 4, whose "when" is only adequate.

5 / 5

Trigger Term Quality

Strong natural keyword coverage — "Include", "Remove", "Update", "metadata", "transforms", "batching", "duplicate or overlapping items", "glob" — which MSBuild users genuinely say. Falls short of the 5 anchor (comprehensive synonyms and file extensions) because notable natural terms are missing: "Exclude" (a core operation the skill covers) and project-file extensions like ".csproj"/".proj".

4 / 5

Distinctiveness Conflict Risk

Clear niche with explicit routing away from siblings and overlap zones: "use including-generated-files" for adjacent cases and "Exclude property-only issues, general incrementality with no item question, broad reviews with no concrete item concern, and non-MSBuild systems" — minimal conflict risk, matching the 5 anchor.

5 / 5

Total

19

/

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/skills

Path

plugins/dotnet-msbuild/skills/item-management/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.