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.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Quality

Content

78%Weight 40%Scale 1-5

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

The body is well-structured and actionable, with executable exploration patterns, an explicit validation checkpoint, and clean one-level-deep references to real bundle files. Minor gains are available from removing the inline EARS duplication and tightening a few high-level workflow steps.

Suggestions

Remove the inline EARS quick-reference table or reduce it to a one-line pointer, since the full reference already lives in references/ears-format.md — this trims duplicate tokens.

Either weave the 'Arch Hat / QA Hat' perspectives into the workflow steps or drop the Role Definition section, so every introduced concept earns its place.

Add a concrete sub-step or example command under 'Trace' (e.g., a Grep pattern for following a request path) to match the actionability of the Explore step.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with tables and tight bullets, but the inline EARS quick-reference table partially duplicates references/ears-format.md, and the 'Arch Hat / QA Hat' roles are introduced without being used in the workflow, so a few tokens could be trimmed.	4 / 5
Actionability	Provides concrete, executable Glob/Grep patterns, a copy-paste EARS pattern table, and a concrete output template; however some workflow steps ('Trace - Follow data flows and request paths') remain high-level rather than executable.	4 / 5
Workflow Clarity	A clear five-step sequence (Scope, Explore, Trace, Document, Flag) with an explicit validation checkpoint in Explore ('Confirm sufficient file coverage before proceeding... continue exploration before writing documentation'); later steps lack checkpoints, leaving minor validation gaps.	4 / 5
Progressive Disclosure	Clear overview body with a well-signaled Reference Guide table mapping each real bundle file (analysis-process.md, ears-format.md, specification-template.md, analysis-checklist.md) to a load-when trigger; references are one level deep and content is appropriately split.	5 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is exemplary: third-person voice, concrete actions, explicit 'Use when' guidance, and a rich set of natural trigger phrases. It answers what, when, and how-to-invoke clearly with no padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('map code dependencies, generate API documentation from source, identify undocumented business logic, figure out what code does, or create architecture documentation from implementation'), giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Clearly answers both what ('extracts specifications from existing codebases' plus concrete actions) and when ('Use when working with legacy or undocumented systems, inherited projects, or old codebases with no documentation') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Explicit 'Trigger phrases' cover natural terms and synonyms users would say ('reverse engineer, old codebase, no docs, figure out how this works, inherited project, legacy analysis, code archaeology'), with strong common-variation coverage.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (reverse-engineering specs from existing/legacy code) with distinct triggers that are unlikely to fire for unrelated skills; conflict risk is minimal.	5 / 5
	Total	20 / 20 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: Jeffallan/claude-skills
Path: skills/spec-miner/SKILL.md
Commit: 882ef55

Reviewed: 3 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.