domain-modeling

Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/domain-modeling/SKILL.md

Quality

Content

63%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.

Well-organized, lean instructional content with concrete example behaviors and a useful ADR checklist. Its main weakness is that both referenced format files are missing from the bundle, which undermines actionability and navigation.

Suggestions

Add the missing CONTEXT-FORMAT.md and ADR-FORMAT.md to the bundle (or inline minimal format templates) so the 'Use the format in...' instructions resolve to real content.

Tighten the opening paragraph by dropping the contrast with passive reading into a one-line boundary note, removing discursive framing that does not change what Claude does.

In the description's capability clause, enumerate one or two more concrete actions (e.g. 'record terms in a glossary, capture architectural decisions') to lift specificity beyond two high-level verbs.

Dimension	Reasoning	Score
Conciseness	The body is efficient and free of basic-concept padding, with mostly purposeful guardrails (e.g. the ADR criteria), but the discursive opening framing and a few explanatory asides could be trimmed, so it sits at 4 rather than 5.	4 / 5
Actionability	Each behavior is paired with concrete example dialogue ('Your glossary defines cancellation as X...'), but the actual record formats are deferred to [CONTEXT-FORMAT.md] and [ADR-FORMAT.md], neither of which exists in the bundle, leaving a key execution detail missing.	3 / 5
Workflow Clarity	The 'During the session' section sequences discrete behaviors under clear headings and the ADR section gives an explicit three-criterion checklist; no validation checkpoint is needed since this is a modeling discipline rather than a destructive/batch operation, so it stays at 4.	4 / 5
Progressive Disclosure	Section structure is clean and references are one level deep and clearly signaled, but both referenced files (CONTEXT-FORMAT.md, ADR-FORMAT.md) are absent from the bundle, so navigation leads to dead links rather than the promised detail.	3 / 5
	Total	14 / 20 Passed

Description

78%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, third-person description that cleanly answers both 'what' and 'when' with concrete domain-specific triggers. It is held back only by slightly abstract capability verbs and minor overlap risk on the ADR trigger.

Dimension	Reasoning	Score
Specificity	Names the domain ('domain model') with two concrete actions ('Build and sharpen'), but the verbs are high-level compared to anchor-4 examples that list several specific actions, and the deeper sub-actions live only in the body.	3 / 5
Completeness	Explicitly states what it does ('Build and sharpen a project's domain model') and when to use it via a concrete 'Use when...' clause with multiple trigger phrases, matching the anchor-5 example pattern.	5 / 5
Trigger Term Quality	Good coverage of natural terms ('domain terminology', 'ubiquitous language', 'architectural decision', 'domain model') with synonyms, though it omits common variations a user might say like 'glossary' or 'ADR'.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche with distinct triggers, but 'record an architectural decision' creates minor overlap risk with a hypothetical dedicated ADR skill, keeping it just below a 5.	4 / 5
	Total	16 / 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
relative_links	Relative link issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: coder/agent-tty
Path: .agents/skills/domain-modeling/SKILL.md
Commit: ebff2c2

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.