CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

domain-model

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/domain-model/SKILL.md
SKILL.md
Quality
Evals
Security

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.

A tight, well-structured instructional body with excellent example phrasings and a precise ADR gate, wasted only by two dangling file references — CONTEXT-FORMAT.md and ADR-FORMAT.md are cited but missing from the skill bundle, so the documentation-update workflow has no format to follow. Compressing the directory trees would also tighten token efficiency.

Suggestions

Add the referenced CONTEXT-FORMAT.md and ADR-FORMAT.md files to the bundle (or inline the essential format skeletons) so the update-documentation steps are actually executable.

Replace or shrink the two ASCII directory trees — a short prose rule ('look for CONTEXT.md and docs/adr/ per context; a root CONTEXT-MAP.md signals multiple contexts') carries the same information in far fewer tokens.

Clarify the opaque '.svx' / 'Brain project' aside, which assumes project-specific context the skill never defines.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — directives like 'Ask the questions one at a time' and 'Don't batch these up' with no padding or explanation of concepts Claude already knows. Not a 5 because the two ASCII directory trees (~25 lines) could be compressed to a sentence or two while preserving the same convention information.

4 / 5

Actionability

Concrete example phrasings ('Your glossary defines cancellation as X, but you seem to mean Y — which is it?') and three explicit ADR criteria give real, executable interview guidance. However, the actual formats are delegated to [CONTEXT-FORMAT.md](./CONTEXT-FORMAT.md) and [ADR-FORMAT.md](./ADR-FORMAT.md), and neither file exists in the bundle, leaving key details of the documentation-update step missing. Not a 4 because those dangling references leave the guidance incomplete in practice.

3 / 5

Workflow Clarity

The session flow is clear and well-sequenced through rules: questions one at a time with feedback, explore the codebase instead when possible, call out glossary conflicts immediately, update CONTEXT.md inline as decisions land, and a three-part checklist gates ADR creation. Not a 5 because checkpoints are implicit (no guidance on wrapping up the session or confirming the shared understanding was reached); no validation cap applies since this is a conversational, non-destructive skill.

4 / 5

Progressive Disclosure

Section structure is sensible and the two references are clearly signaled inline and one level deep — but both referenced files (./CONTEXT-FORMAT.md, ./ADR-FORMAT.md) are absent from the bundle, so the navigation path breaks exactly where the detailed guidance should live. Not a 4 because dangling references are a real organization failure, not a minor gap; not a 2 because the inline content is concise and the structure itself is sound.

3 / 5

Total

14

/

20

Passed

Description

67%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 well-above-average description: third person, concrete three-part capability statement, named artifacts, and an explicit 'Use when...' clause. Main weakness is trigger phrasing that mirrors the capability statement instead of capturing the varied natural phrases users would actually utter.

Suggestions

Broaden the 'Use when' clause with natural trigger variations, e.g. 'Use when the user wants to challenge a design, review a plan against their architecture, or resolve ambiguity in domain terms'.

Mention the interactive interview mechanic ('asks hard questions one at a time') in the 'what' clause so the skill's core behavior is visible from the description alone.

DimensionReasoningScore

Specificity

The description lists several concrete actions — 'challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline' — with named artifacts. Not a 5 because coverage has minor gaps: it omits the interview/Q&A mechanic and codebase cross-checking that define the skill.

4 / 5

Completeness

Both are present: 'what' ('Grilling session that challenges... sharpens... updates documentation') and an explicit 'when' ('Use when user wants to stress-test a plan against their project's language and documented decisions'). Not a 5 because the 'when' clause largely restates the 'what' rather than offering distinct concrete trigger phrases; clearly above the 3 anchor where 'when' is only weakly implied.

4 / 5

Trigger Term Quality

Terms like 'stress-test a plan', 'domain model', and 'documented decisions' are relevant but lean jargon-heavy and miss natural variations users would say — 'challenge my design', 'review my architecture', 'glossary', 'ubiquitous language', 'ADR review'. Matches the anchor for some relevant keywords missing common synonyms; not a 4 because the natural-phrase coverage is thin.

3 / 5

Distinctiveness Conflict Risk

The pairing of 'domain model', 'terminology', 'CONTEXT.md, ADRs', and 'project's language' carves a clear DDD-flavored niche. Minor overlap remains with generic plan-review or design-critique skills, so it stops short of the 'minimal conflict risk' anchor.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 2 missing

Warning

Total

15

/

16

Passed

Repository

joelhooks/joelclaw

Path

skills/domain-model/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.