lading-optimize-find-target
Finds a valid optimization target in lading. Returns a filled target.yaml template with pattern, technique, target, file, bench, and fingerprint. Use before /lading-optimize-hunt or when selecting a new optimization target.
67
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
85%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 well-structured skill description that clearly communicates what the skill does and when to use it, with specific output details (target.yaml fields). Its main weakness is that the trigger terms are highly technical and project-specific, which could make it harder for users unfamiliar with the exact terminology to trigger it naturally. However, given the specialized nature of the skill, this is somewhat expected.
Suggestions
Consider adding more natural language trigger terms such as 'find optimization opportunity', 'pick a target to optimize', or 'benchmark target selection' to improve discoverability for users who may not know the exact jargon.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: finding a valid optimization target, returning a filled target.yaml template, and specifies the template fields (pattern, technique, target, file, bench, fingerprint). | 3 / 3 |
Completeness | Clearly answers both 'what' (finds optimization target, returns filled target.yaml template with specific fields) and 'when' (use before /lading-optimize-hunt or when selecting a new optimization target) with explicit triggers. | 3 / 3 |
Trigger Term Quality | Includes domain-specific terms like 'lading', 'optimization target', 'target.yaml', but these are technical/project-specific jargon rather than natural keywords a user would say. Missing common variations or more natural phrasing. | 2 / 3 |
Distinctiveness Conflict Risk | Highly specific to the 'lading' domain with distinct triggers like 'target.yaml', '/lading-optimize-hunt', and 'optimization target'. Very unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill that provides a clear 7-phase workflow for finding optimization targets in a specific codebase. Its strengths are the concrete patterns table, explicit ranking criteria, and precise output format. The main weakness is its length — at ~120 lines of substantive content, some sections could be tightened or split into referenced files, though the domain-specific nature of the content justifies much of the verbosity.
Suggestions
Consider extracting the Known Patterns table into a separate referenced file (e.g., patterns.md) to reduce the main skill's token footprint and make patterns independently maintainable.
Tighten Phase 3 by removing the explanatory bullets about what to extract — a concise instruction like 'Extract technique, measurements, lessons, and covered targets from each entry' would suffice.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly efficient and avoids explaining basic concepts, but the Known Patterns table and the detailed multi-phase structure add significant length. Some phases (e.g., Phase 3's explanation of what to extract from history) could be tightened. However, most content is domain-specific and not something Claude would inherently know. | 2 / 3 |
Actionability | The skill provides concrete, executable guidance throughout: specific glob patterns, exact script paths, a complete patterns table with before/after techniques, explicit filtering and ranking criteria, and a precise YAML output template. Every phase has clear, specific instructions. | 3 / 3 |
Workflow Clarity | The 7-phase workflow is clearly sequenced with explicit dependencies between phases. Phase 4 has a mandatory 3-step procedure with a required hit matrix. Phase 5 provides explicit filtering criteria with a stop condition. Phase 6 has clear ranking rules with tiebreakers. The workflow handles the 'zero results' edge case explicitly. | 3 / 3 |
Progressive Disclosure | The skill references external files appropriately (db.yaml, profile-modules script, fingerprint configs) but the SKILL.md itself is a long monolithic document. The Known Patterns table and detailed phase descriptions could potentially be split into referenced assets. However, for a skill of this complexity, keeping it in one file is defensible. | 2 / 3 |
Total | 10 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- DataDog/lading
- Commit
7a050d9
- 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.