domain-modeling

Build the project's shared language and bounded contexts before writing code, so names stay consistent and the agent stops paraphrasing domain concepts. Produces a CONTEXT.md glossary and decision records. Use at the start of a project or feature, or when the codebase and the people describing it speak different languages.

Quality

83%

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.

A well-structured, mostly lean instruction-only skill with a clear four-step method and concrete outputs. It could be sharpened by trimming the motivational intro, adding worked examples of a glossary line and a decision record, and inserting an explicit validation checkpoint.

Suggestions

Trim the opening motivational paragraph ('Most misbuilds start as a language gap...') to a single line, keeping the Method as the lead, to improve token efficiency.

Add one worked example of a CONTEXT.md line and one filled-in decision record so the output format is copy-paste ready rather than only described.

Insert an explicit validation checkpoint in the workflow (e.g. 'Review the glossary with the user and confirm term boundaries before writing decision records') to close the validation gap.

Dimension	Reasoning	Score
Conciseness	The Method, Outputs, and Guardrails sections are tight and assume Claude's competence, but the opening paragraph ('Most misbuilds start as a language gap...') is motivational framing that could be trimmed. Not 5 due to that padding; not 3 because the bulk is efficient with no over-explanation of basic concepts.	4 / 5
Actionability	Concrete, specific guidance throughout ('list the nouns and verbs that carry domain meaning', 'one-line definition in the project's own language', 'docs/decisions/NNNN-slug.md', 'number from the highest existing record so two records never collide'). Not 5 because there are no worked examples of a glossary line or a decision record to make it copy-paste ready; not 3 because the guidance is concrete and executable, not pseudocode-level.	4 / 5
Workflow Clarity	The four Method steps (Harvest, Pin, Draw boundaries, Record) are clearly sequenced with embedded decision checkpoints ('If two terms blur together, force the distinction or collapse them'). Not 5 because there is no explicit review/validation checkpoint (e.g. confirm the glossary with the user); not 3 because the sequence is clear with implicit checkpoints and the skill is not destructive/batch so the cap does not apply.	4 / 5
Progressive Disclosure	No bundle files exist, so the skill is self-contained; the body is well-sectioned (Method, Outputs, Guardrails, Where it fits) at roughly 50 lines with no nested references and easy navigation. The simple-skill exception applies: well-organized sections with no need for external references score 5.	5 / 5
	Total	17 / 20 Passed

Description

87%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, specific description that clearly states both what the skill does and when to use it, with a distinct domain-modeling niche and concrete trigger guidance. Minor room to add common synonyms and tighten the abstract 'build shared language' phrasing.

Dimension	Reasoning	Score
Specificity	Names the domain ('shared language and bounded contexts') and lists several concrete actions (build the language, draw contexts, produce a CONTEXT.md glossary, produce decision records), with only minor abstraction gaps. Not 5 because 'build shared language' is somewhat abstract rather than a fully concrete action; not 3 because it lists more than 1-2 specific actions.	4 / 5
Completeness	It explicitly answers both 'what' (build shared language and bounded contexts; produces a CONTEXT.md glossary and decision records) and 'when' ('Use at the start of a project or feature, or when the codebase and the people describing it speak different languages') with concrete trigger phrases, in third-person imperative voice.	5 / 5
Trigger Term Quality	The 'Use at the start of a project or feature, or when the codebase and the people describing it speak different languages' clause gives good natural trigger phrases a user would say. Not 5 because common synonyms like 'ubiquitous language', 'terminology', or 'glossary' are missing; not 3 because coverage is clearly better than a single generic keyword.	4 / 5
Distinctiveness Conflict Risk	It occupies a clear domain-modeling / ubiquitous-language niche with distinct triggers (bounded contexts, CONTEXT.md glossary, decision records) and minimal overlap risk with other skills.	5 / 5
	Total	18 / 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: rohitg00/pro-workflow
Path: skills/domain-modeling/SKILL.md
Commit: 7f7209d

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.