lexicon

Enforce one term, one meaning across code, docs, UI, API, and commits. Use when the user says "we call this three different things", "align our terminology", "build a glossary", "what do we actually mean by X", or when a review surfaces the same concept under multiple names.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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 with a concrete failure-mode taxonomy, a filled term-record example, a sequenced workflow, and an output template, all supported by a real one-level reference. It is held back from a perfect score only by a few trimmable explanatory sentences and the absence of a concrete validation loop and grep command.

Suggestions

Add a concrete CI grep snippet (e.g. a sample ripgrep/grep command matching deprecated variants) to make the Enforce step copy-paste ready.

Insert an explicit validate-fix-retry checkpoint in the workflow, e.g. after Enforce run the grep check and iterate until no deprecated variants remain.

Tighten the Overview's /ia contrast and the "collisions are most expensive" paragraph to the minimum needed to set scope and priorities.

Dimension	Reasoning	Score
Conciseness	The body is lean and defers Z39.19 detail to references, but a few explanatory sentences (the /ia contrast and the "collisions are most expensive" flourish) go slightly beyond minimal; it fits efficient-with-minor-trims rather than every-token-earns-its-place.	4 / 5
Actionability	Copy-paste-ready term-record and output-format templates plus concrete placement guidance (GLOSSARY.md at repo root, grep check in CI) are actionable, but the CI grep check is named abstractly without a concrete command, leaving a minor gap.	4 / 5
Workflow Clarity	The five-step Extract-to-Enforce sequence is clear with a citation gate in Judge and CI-grep enforcement as an ongoing feedback loop, but there is no explicit validate-then-fix-then-retry loop in the numbered steps.	4 / 5
Progressive Disclosure	The real references/controlled-vocabulary.md is signaled one level deep ("See references/controlled-vocabulary.md for the full vocabulary types and term-record schema"), with the core workflow inline and detail split to the reference, giving clear navigation.	5 / 5
	Total	17 / 20 Passed

Description

95%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 strong: it states the capability, enumerates the surfaces it spans, and supplies multiple concrete natural-language triggers. It is distinguishable from neighboring skills and answers both what and when explicitly.

Dimension	Reasoning	Score
Specificity	"Enforce one term, one meaning across code, docs, UI, API, and commits" names the domain and one core action applied comprehensively across five concrete surfaces; it is not a 5 because it is one action across surfaces rather than multiple distinct actions.	4 / 5
Completeness	A clear "what" clause is followed by an explicit "Use when the user says..." with concrete trigger phrases, answering both what and when explicitly.	5 / 5
Trigger Term Quality	Five natural user phrasings ("we call this three different things", "align our terminology", "build a glossary", "what do we actually mean by X") plus synonym coverage match the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	A clear niche (cross-surface term consistency) with distinct triggers and explicit contrast against /naming and /ia gives minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tslateman/duet
Path: skills/lexicon/SKILL.md
Commit: 504b3b1

Reviewed: 1 day 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.