lading-optimize-hunt
Coordinates optimization attempts. Captures baselines, implements changes, invokes review, and records outcomes.
60
43%
Does it follow best practices?
Impact
88%
1.37xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/lading-optimize-hunt/SKILL.mdQuality
Discovery
9%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 description is too abstract and process-oriented, reading more like a workflow description than a skill description. It fails to specify what domain of optimization it covers, uses no natural trigger terms a user would say, and lacks any 'Use when...' guidance for skill selection.
Suggestions
Specify the domain of optimization (e.g., 'code performance optimization', 'database query optimization', 'build time optimization') to reduce ambiguity and conflict risk.
Add a 'Use when...' clause with natural trigger terms users would say, such as 'Use when the user asks to speed up code, improve performance, reduce latency, or optimize resource usage.'
Replace abstract process terms ('coordinates', 'invokes review', 'records outcomes') with concrete actions describing what the skill actually does, e.g., 'profiles code execution, identifies bottlenecks, refactors hot paths, and benchmarks improvements.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names some actions ('captures baselines', 'implements changes', 'invokes review', 'records outcomes') but they are generic process steps rather than concrete, domain-specific actions. It's unclear what kind of optimization or what specific operations are performed. | 2 / 3 |
Completeness | While there is a vague 'what' (coordinates optimization attempts), there is no 'when' clause or explicit trigger guidance. The description never specifies when Claude should select this skill, which per the rubric caps completeness at 2, and the 'what' is also weak enough to warrant a 1. | 1 / 3 |
Trigger Term Quality | The description lacks natural keywords a user would say. Terms like 'coordinates optimization attempts' and 'invokes review' are abstract process language, not terms users would naturally use when requesting help. There are no concrete trigger terms like 'performance', 'speed', 'benchmark', 'profiling', etc. | 1 / 3 |
Distinctiveness Conflict Risk | The term 'optimization' is extremely broad and could apply to code optimization, database optimization, image optimization, performance tuning, SEO, or countless other domains. Without specifying the domain or type of optimization, this would easily conflict with many other skills. | 1 / 3 |
Total | 5 / 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 coordination skill with strong actionability and workflow clarity. The phased approach with explicit validation checkpoints, cleanup steps, and clear handoff points makes it reliable for complex optimization workflows. Minor improvements could be made in conciseness by trimming the role clarification section, and progressive disclosure could benefit from verifiable bundle references.
Suggestions
Trim the 'Role: Coordinator and Recorder' section — the 'Hunt DOES / Hunt does NOT' lists largely restate what the phases already make clear, saving ~6 lines of context window.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but has some redundancy — the 'Hunt DOES / Hunt does NOT' section repeats information that's implicit in the workflow phases. The role clarification section could be tightened. However, the workflow phases themselves are lean and well-structured. | 2 / 3 |
Actionability | Provides fully executable bash commands, specific file paths, concrete variable assignments, and exact command-line invocations. Each phase has copy-paste ready commands with clear parameter substitution patterns. | 3 / 3 |
Workflow Clarity | Clear 6-phase sequential workflow with explicit validation checkpoints (ci/validate must pass before proceeding), cleanup of stale data before baselining, critical warnings about ordering, and clear error handling guidance (pre-existing bug documentation). The feedback loop for ci/validate failure is explicit. | 3 / 3 |
Progressive Disclosure | References external slash commands (/lading-preflight, /lading-optimize-find-target, /lading-optimize-review) and template files appropriately, but the bundle has no files provided to verify these references. The skill itself is somewhat long and could potentially split the baseline capture details into a referenced file, though the inline approach is defensible for a workflow document. | 2 / 3 |
Total | 10 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- DataDog/lading
- Commit
e98e305
- 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.