CtrlK
BlogDocsLog inGet started
Tessl Logo

ubiquitous-language

Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".

76

Quality

95%

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

88%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 strong, highly actionable single-file skill with a complete output template, opinionated rules, and clear re-run handling. Its only weaknesses are mild redundancy (the second example dialogue) and everything living inline in one ~93-line file with no separation of the template into a reference.

Suggestions

Drop the <example> dialogue block (lines 71-83) or the example dialogue inside the output template — one demonstration is enough and would tighten conciseness toward a 5.

If the skill grows, move the full output-file template into a references/ file (e.g. TEMPLATE.md) and keep SKILL.md as a lean overview, improving progressive disclosure.

State briefly what to do if the conversation contains no domain-relevant terms (e.g. say so rather than writing a sparse file) to close the last workflow gap.

DimensionReasoningScore

Conciseness

The body is largely lean and assumes Claude's competence, but the <example> dialogue (lines 71-83) duplicates the 'Example dialogue' already demonstrated inside the output template (lines 48-53), and a couple of Rules restate Process items. This matches the 4 anchor (minor instances that could be trimmed) rather than 5, where every token would earn its place.

4 / 5

Actionability

Guidance is fully executable for an instruction-only skill: an exact output filename, a complete copy-paste-ready output-file template (tables, relationships, example dialogue, flagged ambiguities), opinionated rules, and a concrete re-run procedure — matching the 5 anchor.

5 / 5

Workflow Clarity

A clear five-step sequence (scan, identify, propose, write, summarize) plus a dedicated Re-running section covering iteration and updates. The operation writes a single new file and is neither destructive nor batch, so the validation cap does not apply; the single purpose is unambiguous, matching the simple-skill exception for a 5.

5 / 5

Progressive Disclosure

No bundle files exist and the skill is self-contained with well-organized sections (Process, Output Format, Rules, Re-running), which fits good structure. However, at ~93 lines — above the under-50-line simple-skill exception — the full output template and the extra <example> dialogue are all inlined, matching the 4 anchor (minor organization gaps) rather than a 5.

4 / 5

Total

18

/

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.

An exemplary description: concrete third-person actions, a named artifact, an explicit 'Use when' clause with multiple natural trigger phrases, and a distinct DDD-focused niche. It mirrors the structure of the rubric's good overall examples.

DimensionReasoningScore

Specificity

The description lists four concrete actions in third person — 'Extract a DDD-style ubiquitous language glossary', 'flagging ambiguities', 'proposing canonical terms', and 'Saves to UBIQUITOUS_LANGUAGE.md' — which matches the 5 anchor for multiple specific concrete actions with comprehensive coverage.

5 / 5

Completeness

It explicitly answers both what (extract/flag/propose/save, including the output file) and when ('Use when user wants to define domain terms... or mentions "domain model" or "DDD"') with concrete trigger phrases, exactly matching the 5 anchor.

5 / 5

Trigger Term Quality

Natural user phrasings are comprehensively covered with synonyms: 'define domain terms', 'build a glossary', 'harden terminology', 'create a ubiquitous language', plus 'domain model' and 'DDD' — matching the 5 anchor's coverage of natural terms including synonyms.

5 / 5

Distinctiveness Conflict Risk

The DDD/ubiquitous-language glossary niche is distinct with specific trigger terms, so the risk of firing for an unrelated skill is minimal — a clear match for the 5 anchor.

5 / 5

Total

20

/

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
SnowingFox/ai-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.