CtrlK
BlogDocsLog inGet started
Tessl Logo

spec-miner

Reverse-engineering specialist that extracts specifications from existing codebases. Use when working with legacy or undocumented systems, inherited projects, or old codebases with no documentation. Invoke to map code dependencies, generate API documentation from source, identify undocumented business logic, figure out what code does, or create architecture documentation from implementation. Trigger phrases: reverse engineer, old codebase, no docs, no documentation, figure out how this works, inherited project, legacy analysis, code archaeology, undocumented features.

72

Quality

88%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

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 skill with strong actionability through concrete Grep/Glob patterns and the EARS format table. The workflow is clearly sequenced with an appropriate validation checkpoint. Main weaknesses are minor verbosity in framing sections and unverifiable external references due to missing bundle files.

Suggestions

Trim the 'When to Use This Skill' section — it largely duplicates the skill description and consumes tokens without adding actionable guidance.

Remove or condense obvious constraints like 'Use Read, Grep, Glob extensively' which Claude can infer from the workflow itself.

DimensionReasoningScore

Conciseness

Generally efficient but includes some unnecessary framing (e.g., 'Role Definition' with hat metaphors, 'When to Use This Skill' section largely restates the description). The EARS table and exploration patterns earn their place, but the constraints section has some obvious items Claude already knows (like 'use Read, Grep, Glob extensively').

2 / 3

Actionability

Provides concrete, executable Glob/Grep patterns, a clear EARS format table with specific examples, explicit output file path conventions, and a structured specification template outline. The exploration patterns are copy-paste ready and the EARS examples are immediately usable.

3 / 3

Workflow Clarity

The 5-step core workflow is clearly sequenced with an explicit validation checkpoint after the Explore step that includes specific criteria for proceeding. The workflow covers the full lifecycle from scoping through documentation, with a clear feedback loop requiring sufficient file coverage before advancing.

3 / 3

Progressive Disclosure

References four separate files (ears-format.md, analysis-process.md, specification-template.md, analysis-checklist.md) with a clear reference table indicating when to load each. However, no bundle files were provided, so we cannot verify these references exist. The SKILL.md itself includes a good amount of inline content (EARS table, exploration patterns) that balances the overview well, but the missing bundle files prevent a score of 3.

2 / 3

Total

10

/

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.

This is a strong skill description that clearly defines its niche in reverse-engineering and legacy code analysis. It provides specific concrete actions, comprehensive trigger terms that users would naturally use, and explicitly addresses both what the skill does and when to invoke it. The description uses proper third-person voice and is well-structured without unnecessary verbosity.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: map code dependencies, generate API documentation from source, identify undocumented business logic, create architecture documentation from implementation.

3 / 3

Completeness

Clearly answers both 'what' (extracts specifications, maps dependencies, generates API docs, identifies business logic, creates architecture docs) and 'when' (legacy/undocumented systems, inherited projects, old codebases with no documentation) with explicit trigger phrases.

3 / 3

Trigger Term Quality

Excellent coverage of natural terms users would say: 'reverse engineer', 'old codebase', 'no docs', 'figure out how this works', 'inherited project', 'legacy analysis', 'code archaeology', 'undocumented features'. These are highly natural phrases a user would actually type.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche around reverse-engineering undocumented/legacy codebases. The trigger terms are highly specific to this use case and unlikely to conflict with general code analysis or documentation generation skills.

3 / 3

Total

12

/

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

10

/

11

Passed

Repository
Jeffallan/claude-skills
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.