spec-miner
Use when understanding legacy or undocumented systems, creating documentation for existing code, or extracting specifications from implementations. Invoke for legacy analysis, code archaeology, undocumented features.
Overall
score
63%
Validation for skill structure
Discovery
N/ABased on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
Something went wrong
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has strong organizational structure with good progressive disclosure through its reference table, but lacks the concrete, executable guidance needed for high actionability. The workflow is present but missing validation checkpoints, and some content (role definition, knowledge reference) adds tokens without adding value Claude doesn't already have.
Suggestions
Add concrete Glob/Grep pattern examples directly in the skill (e.g., `Grep('TODO|FIXME|HACK', include='*.py')` for finding technical debt)
Include a brief inline EARS format example rather than only referencing external file (e.g., 'When [condition], the system shall [action]')
Add a validation checkpoint after the Trace step to verify data flow coverage before documenting
Remove or condense the 'Knowledge Reference' section as it lists concepts Claude already understands
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary framing ('senior software archaeologist with 10+ years of experience') and the 'Knowledge Reference' section lists concepts Claude already knows without adding value. | 2 / 3 |
Actionability | Provides a clear workflow and constraints but lacks concrete examples of Glob/Grep patterns, actual EARS format syntax, or executable commands. The guidance is directional rather than copy-paste ready. | 2 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced, but lacks validation checkpoints or feedback loops. No explicit verification step to confirm analysis completeness before documenting, and the 'Flag' step is vague. | 2 / 3 |
Progressive Disclosure | Excellent structure with a clear overview and well-organized reference table pointing to one-level-deep external files. The table format makes navigation easy and signals when to load each reference. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
68%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 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
body_examples | No examples detected (no code fences and no 'Example' wording) | Warning |
Total | 11 / 16 Passed | |
- 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.