aot-guru
Specialized Native AOT, trimming, and optimization expert for morphir-dotnet. Expert in single-file trimmed executables, AOT compilation, size optimization, and guiding toward AOT-compatible features. Use when troubleshooting compilation, diagnosing trimming issues, optimizing binary size, implementing reflection workarounds, or maintaining best practices. Triggers include "AOT", "Native AOT", "trimming", "single-file", "size optimization", "reflection error", "IL2026", "IL3050", "PublishAot", "PublishTrimmed", "source generator", "Myriad".
56
63%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/aot-guru/SKILL.mdQuality
Discovery
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.
This is a strong skill description that clearly defines its niche (Native AOT and trimming for morphir-dotnet), lists concrete actions, and provides explicit trigger guidance with both a 'Use when' clause and a comprehensive list of trigger terms. The description is well-structured, uses third person voice, and would be easily distinguishable from other skills in a large skill library.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and domains: 'single-file trimmed executables, AOT compilation, size optimization, guiding toward AOT-compatible features, troubleshooting compilation, diagnosing trimming issues, implementing reflection workarounds.' | 3 / 3 |
Completeness | Clearly answers both 'what' (AOT compilation, trimming, size optimization, reflection workarounds for morphir-dotnet) and 'when' with an explicit 'Use when...' clause listing specific trigger scenarios, plus an additional 'Triggers include' list. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say, including both high-level terms ('AOT', 'trimming', 'size optimization') and specific technical terms users would search for ('IL2026', 'IL3050', 'PublishAot', 'PublishTrimmed', 'source generator', 'Myriad'). | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the narrow niche of 'morphir-dotnet' combined with Native AOT/trimming specialization. The specific error codes (IL2026, IL3050) and tool names (Myriad) make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is extremely comprehensive in coverage but severely undermines its utility through massive verbosity and poor content organization. The same configuration blocks and size targets are repeated multiple times, entire BDD test suites and Gherkin features are inlined rather than referenced, and organizational process content (quarterly reviews, metrics tracking) dilutes the actionable technical guidance. The core technical content (reflection workarounds, decision trees, trimming diagnostics) is solid but buried in a document that would consume enormous context window space.
Suggestions
Reduce the document to ~150 lines by extracting BDD testing details, issue templates, Gherkin features, and interaction patterns into separate referenced files, keeping only a concise overview with links.
Remove all repeated XML configuration blocks - define the canonical configuration once and reference it, rather than showing nearly identical PropertyGroup blocks 3+ times.
Remove organizational/process content (quarterly reviews, metrics tracking, knowledge base self-improvement) that describes team processes rather than providing actionable technical guidance for Claude.
Ensure referenced files (templates/aot-issue-report.md, diagnostic scripts, docs/contributing/aot-trimming-guide.md) are included as bundle files, or remove references to non-existent resources.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~600+ lines. Massive amounts of content Claude already knows (what AOT is, what trimming does, basic .NET concepts). Extensive repetition of XML configuration blocks (the same PropertyGroup appears 3+ times), size targets repeated multiple times, and lengthy sections on interaction patterns, quarterly reviews, and metrics tracking that are organizational process rather than actionable skill content. | 1 / 3 |
Actionability | Contains concrete XML configurations, bash commands, and some code examples (source generators, Myriad patterns) that are executable. However, many code examples are incomplete (e.g., F# parseConfig with '...', Myriad generator attributes that may not exist as shown), diagnostic scripts are referenced but only show usage comments without implementation, and some patterns are more illustrative than copy-paste ready. | 2 / 3 |
Workflow Clarity | The phased roadmap (Phase 1-4) provides a clear sequence, and the decision trees for error diagnosis are well-structured. However, the primary workflows for building and testing lack explicit validation checkpoints - for example, the 'Single-File Trimmed Executable Production' section lists steps but doesn't include verify/retry loops. The testing section has good detail but the core build workflow is missing feedback loops for destructive operations. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no bundle files to support it. Content that should be in separate files (BDD test details, issue templates, decision trees, Myriad guide, size optimization reference) is all inlined. References to external files like 'templates/aot-issue-report.md' and diagnostic scripts exist but no bundle files are provided, and the skill itself contains hundreds of lines that should be split across referenced documents. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (1034 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- finos/morphir-dotnet
- Commit
7c0c06d
- 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.