tdg-personal/agent-sort
Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.
84
84%
Does it follow best practices?
Impact
Pending
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 description that clearly communicates both what the skill does and when to use it, with a distinct niche that minimizes conflict risk. Its main weakness is reliance on domain-specific jargon (ECC, DAILY/LIBRARY buckets) that may not match natural user language, potentially reducing discoverability for users unfamiliar with the terminology.
Suggestions
Add natural-language trigger terms that users might actually say, such as 'optimize Claude skills', 'customize skill loading', 'reduce skill bundle', or 'configure which skills to load' to improve discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes.' This clearly describes the mechanism and the specific artifacts being processed. | 3 / 3 |
Completeness | Clearly answers both what ('Build an evidence-backed ECC install plan... by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets') and when ('Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle'). | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'ECC install plan', 'trimmed', 'DAILY vs LIBRARY buckets', but relies heavily on domain-specific jargon ('ECC', 'repo-aware review passes') that users may not naturally say. Missing common variations like 'optimize', 'configure', 'setup', or 'customize skills'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: ECC install planning with DAILY vs LIBRARY bucketing for a specific repo. The combination of 'ECC', 'install plan', and 'DAILY vs LIBRARY buckets' makes it 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, actionable skill that provides a clear methodology for classifying ECC components with repo evidence. Its strongest aspects are the concrete workflow steps, verification requirements, and specific output format. Minor weaknesses include some redundancy between sections and the opportunity to split detailed reference material into separate files for better progressive disclosure.
Suggestions
Consider extracting the evidence table format and parallel review pass details into a separate reference file to reduce the main skill's length
Trim the 'When to Use' section—several bullets overlap with the opening description and Classification Model section
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but has some redundancy—the 'When to Use' section overlaps with the opening line, and some sections (like Classification Model) restate what's already implied by the evidence table. The bullet lists are clean but could be tighter in places. | 2 / 3 |
Actionability | Provides concrete bash commands for evidence gathering, a specific text-based evidence table format, explicit file paths for outputs, clear classification criteria with examples, and a defined output format. The guidance is specific enough to execute without ambiguity. | 3 / 3 |
Workflow Clarity | The six-step core workflow is clearly sequenced with numbered steps, includes a verification step (step 6) with specific checks, and has explicit criteria for promotion/demotion decisions. The parallel review passes are well-defined with clear scope boundaries, and the handoff section provides error recovery paths. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections, but it's a fairly long monolithic document that could benefit from splitting the evidence table format, the library router template, and the parallel pass details into separate reference files. The handoff references to other skills are good, but the skill itself doesn't reference any supplementary docs. | 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 | |
Reviewed
Table of Contents