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.

Quality

100%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

100%

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

A well-structured, action-oriented skill body: concise, fully executable, with a clearly sequenced multi-phase workflow and an explicit stop-condition validation checkpoint. Bundle references are one level deep and the referenced script exists on disk.

Dimension	Reasoning	Score
Conciseness	Lean phase-structured body that assumes Claude's competence (no explanation of Rust, Criterion, or allocation concepts); every section earns its tokens with actionable detail rather than padding.	3 / 3
Actionability	Provides executable guidance throughout: concrete Glob patterns, the exact profile-modules script path, Read commands, a full patterns→techniques table, a hit-matrix format, and a copy-ready YAML output template.	3 / 3
Workflow Clarity	Seven phases are explicitly sequenced, with an explicit validation checkpoint in Phase 5 ('If zero survive, STOP: No valid optimization targets found.') and a strict exhaustive procedure in Phase 4 including a mandatory full hit matrix.	3 / 3
Progressive Disclosure	Well-organized into clear phases with one-level-deep, clearly signaled references to the real scripts/profile-modules bundle file and the sibling skill's db.yaml asset; no nested reference chains.	3 / 3
	Total	12 / 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 tight, third-person description that concretely states what it returns and when to invoke it, with domain-appropriate trigger terms and clear separation from a sibling skill. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('Finds a valid optimization target', 'Returns a filled target.yaml template') and enumerates specific output fields (pattern, technique, target, file, bench, fingerprint), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers what it does (finds and returns a target template) and when to use it ('Use before /lading-optimize-hunt or when selecting a new optimization target'), satisfying both halves with an explicit trigger.	3 / 3
Trigger Term Quality	Natural terms a user in this domain would say are present ('optimization target', 'lading', 'target.yaml', '/lading-optimize-hunt', 'selecting a new optimization target'), giving good coverage of trigger phrasings.	3 / 3
Distinctiveness Conflict Risk	Scoped to a clear niche (finding lading optimization targets) and explicitly distinguished from the sibling /lading-optimize-hunt skill, making wrong-skill triggering unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: DataDog/lading
Commit: 5761294

Reviewed: 8 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.