CtrlK
BlogDocsLog inGet started
Tessl Logo

reviewing-msbuild-code

Reviews MSBuild code changes using a 24-dimension methodology. Activates for code review, PR review, pull request analysis, design review, architecture review, code quality assessment, or style check of MSBuild code. Covers backwards compatibility, ChangeWave discipline, performance, allocation awareness, test coverage, error message quality, logging, string comparison, API surface, target authoring, cross-platform correctness, code simplification, concurrency, naming, SDK integration, evaluation model integrity, correctness, dependency management, security, and build infrastructure.

64

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/reviewing-msbuild-code/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

52%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is admirably concise but over-delegates: it points to an `@expert-reviewer` agent for everything, leaving the skill itself without executable guidance, a sequenced workflow, or genuine bundle-file navigation.

Suggestions

Add a brief in-skill summary of the review workflow (e.g., the named waves and their validation checkpoints) instead of delegating the entire methodology to @expert-reviewer, so the skill is actionable without the external agent.

Provide at least one concrete, executable artifact in the body — a representative checklist line, command, or example — to raise actionability beyond a pointer.

Either bundle the methodology into actual reference files under references/ and link them with clear one-level-deep navigation, or document why the @expert-reviewer agent is the single source of truth, so progressive disclosure is intentional rather than absent.

DimensionReasoningScore

Conciseness

The body is three lean lines with no concept-padding or fluff ('Invoke `@expert-reviewer` for 24-dimension MSBuild code review'), where every token earns its place — the top 'lean and efficient' anchor.

3 / 3

Actionability

'Invoke `@expert-reviewer`' is a concrete instruction, but the skill delegates entirely to an external agent and supplies no in-skill code, commands, or specific examples, matching the 'some concrete guidance but incomplete; missing key details' anchor rather than the copy-paste-ready top anchor.

2 / 3

Workflow Clarity

The body only mentions that a '4-wave workflow' lives inside another agent and provides no sequenced steps or validation checkpoints in-skill, matching the 'steps unclear or missing; no sequence for multi-step tasks' bottom anchor.

1 / 3

Progressive Disclosure

No bundle files exist and the only reference is an inline `@expert-reviewer` agent invocation that is not a discoverable file, so organization is minimal and references are not clearly signaled — closest to the 'some structure but could be better organized' anchor.

2 / 3

Total

8

/

12

Passed

Description

100%

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: it states concrete capabilities, provides explicit activation triggers using natural review vocabulary, answers both what and when, and occupies a clear MSBuild niche unlikely to conflict with other skills.

DimensionReasoningScore

Specificity

It lists concrete actions ('Reviews MSBuild code changes') and enumerates many specific dimensions ('backwards compatibility, ChangeWave discipline, performance, allocation awareness, test coverage...'), matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

It answers both what ('Reviews MSBuild code changes using a 24-dimension methodology') and when ('Activates for code review, PR review...') with an explicit trigger clause, the top anchor.

3 / 3

Trigger Term Quality

Natural review vocabulary a user would actually say is well covered ('code review, PR review, pull request analysis, design review, architecture review, code quality assessment, or style check'), aligning with the 'good coverage of natural terms' anchor.

3 / 3

Distinctiveness Conflict Risk

Scoped tightly to MSBuild with distinct, domain-specific triggers, making it unlikely to fire for unrelated skills — matching the 'clear niche with distinct triggers' anchor.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
dotnet/msbuild
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.