CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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.

A well-structured, action-oriented body: a clear five-step workflow with an explicit exploration checkpoint, concrete tool patterns, and a clean reference table pointing to a verified one-level-deep bundle. The main improvement opportunities are removing the EARS table duplication with the reference file and adding concrete technique to the Trace step.

DimensionReasoningScore

Conciseness

The body is largely efficient — the workflow, constraints, and exploration patterns carry no filler and assume competence — but the EARS quick-reference table duplicates content already in 'references/ears-format.md', and 'When to Use This Skill' restates the frontmatter description. This matches the level-4 anchor ('efficient; minor instances that could be trimmed') rather than level 5, where every token would earn its place with no duplicated material.

4 / 5

Actionability

Concrete, usable guidance is present: executable-style tool calls ('Glob(\'**/*.py\', exclude=[\'**/test*\', ...\'])', 'Grep(\'TODO|FIXME|HACK|XXX\', include=\'*.py\')'), a specific output path ('specs/{project_name}_reverse_spec.md') with a 7-section template, and filled-in EARS examples. It falls short of the level-5 anchor because the 'Trace' and 'Flag' steps remain high-level ('Follow data flows and request paths') without concrete technique, leaving minor gaps.

4 / 5

Workflow Clarity

The five-step Core Workflow (Scope → Explore → Trace → Document → Flag) is clearly sequenced and includes an explicit validation checkpoint with a feedback loop ('Confirm sufficient file coverage... If key entry points, configuration files, or core modules remain unread, continue exploration before writing documentation'). It is not level 5 because only the Explore step has an explicit checkpoint — Trace and Document lack verification steps, fitting the level-4 anchor ('clear sequence with most checkpoints present; minor validation gaps').

4 / 5

Progressive Disclosure

The body is a well-sectioned overview with a clearly signaled, one-level-deep reference table giving topic, path, and 'Load When' conditions, and all four referenced files (references/analysis-process.md, ears-format.md, specification-template.md, analysis-checklist.md) exist in the bundle. The EARS summary is inlined appropriately with a pointer to the full reference, matching the level-5 anchor (clear overview, well-signaled references, easy navigation).

5 / 5

Total

17

/

20

Passed

Description

96%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.

A strong description that clearly and explicitly states both capabilities and usage conditions, with an unusually thorough list of natural trigger phrases including synonyms. The only weakness is that a couple of the broader trigger phrases could invite overlap with general code-understanding skills.

DimensionReasoningScore

Specificity

The description 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' — on top of the headline 'extracts specifications from existing codebases', giving comprehensive coverage of the skill's capabilities. It matches the level-5 anchor (multiple specific concrete actions) rather than level 4, since no meaningful capability in this niche is left unstated.

5 / 5

Completeness

It explicitly answers 'what' ('Reverse-engineering specialist that extracts specifications from existing codebases' plus the 'Invoke to...' action list) and 'when' ('Use when working with legacy or undocumented systems, inherited projects, or old codebases with no documentation') with concrete trigger phrases. Both elements are explicit and concrete, matching the level-5 anchor exactly; level 4 would require the 'when' clause to be less specific than it is.

5 / 5

Trigger Term Quality

The explicit 'Trigger phrases:' list — 'reverse engineer, old codebase, no docs, no documentation, figure out how this works, inherited project, legacy analysis, code archaeology, undocumented features' — covers natural user phrasings including synonym pairs ('no docs' / 'no documentation', 'old codebase' / 'legacy analysis'). This is comprehensive natural-term coverage per the level-5 anchor; level 4 ('a few natural terms missing') would understate the synonym and colloquial coverage present here.

5 / 5

Distinctiveness Conflict Risk

The niche (extracting specifications from existing/legacy code) is clear with mostly distinct triggers, but phrases like 'figure out how this works' and 'figure out what code does' are broad enough to overlap with general code-comprehension or onboarding skills. This fits the level-4 anchor ('mostly distinct; minor overlap risk with closely related skills') rather than level 5, whose example has tightly scoped triggers with minimal conflict risk.

4 / 5

Total

19

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

Jeffallan/claude-skills

Path

skills/spec-miner/SKILL.md

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.