CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

domain-modeling

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

Quality

74%

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 ./.agents/skills/domain-modeling/SKILL.md

The canonical home for this skill is domain-modeling in mattpocock/skills

SKILL.md
Quality
Evals
Security

Quality

Content

67%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-organized, lean, instruction-only skill whose session guidance is unusually concrete for its genre. Its one serious defect is that both of its external reference files are missing from the bundle, which both dead-ends navigation and leaves glossary and ADR formats unspecified.

Suggestions

Add the referenced GLOSSARY-FORMAT.md and ADR-FORMAT.md to the bundle, or inline minimal entry templates if the formats are short enough to stay within token budget.

Define what counts as a term being "resolved" (e.g., the user confirms a definition) so the update-inline step has an explicit trigger.

Trim the parenthetical contrasting with merely reading GLOSSARY.md and compress the multi-context directory tree to a short rule, since both restate scope already in the frontmatter.

DimensionReasoningScore

Conciseness

The body is lean, assumes Claude's competence (never explains what a glossary or ADR is), and gives concrete rules like "Create files lazily: only when you have something to write". Minor over-explanation remains: the parenthetical distinguishing active from merely reading GLOSSARY.md repeats frontmatter scope, and the second directory tree could be compressed. Not level 5 because those tokens could be trimmed; not level 3 because no padding or known-concept explanation exists.

4 / 5

Actionability

Concrete, copy-ready guidance throughout: example challenge dialogues ("Your glossary defines 'cancellation' as X, but you seem to mean Y"), a three-condition numbered test for when to offer an ADR, and explicit file-layout rules. It falls short of level 5 because entry formats are delegated to GLOSSARY-FORMAT.md and ADR-FORMAT.md, which are absent from the bundle, leaving a key execution detail missing.

4 / 5

Workflow Clarity

Session behaviors are each paired with a clear trigger (conflicting term, vague term, relationship discussion, code statement), and "Cross-reference with code" functions as a validation checkpoint. It is not level 5 because "when a term is resolved" lacks a criterion for recognizing resolution, and there is no verify step before writing an ADR or glossary entry; not level 3 because sequencing and checkpoints are mostly explicit.

4 / 5

Progressive Disclosure

Both external references — [GLOSSARY-FORMAT.md](./GLOSSARY-FORMAT.md) and [ADR-FORMAT.md](./ADR-FORMAT.md) — are well-signaled, one-level-deep links, but neither file exists anywhere in the bundle. The split is not actually realized: the format content is neither inlined nor in the referenced files, so navigation dead-ends. This sits between the broken-structure anchors of level 2 and the partial-structure level 3, noticeably below the midpoint.

2 / 5

Total

14

/

20

Passed

Description

70%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 solid description with an explicit, concrete trigger clause and a distinct niche built around two well-known artifacts. Its main weakness is an abstract, one-clause statement of what the skill actually does, which limits specificity and keeps completeness just below top marks.

Suggestions

Enumerate the concrete actions in the 'what' clause, e.g. "Challenge vague terms against the glossary, capture resolved definitions in GLOSSARY.md, and record trade-offs as ADRs".

Add natural trigger synonyms such as "glossary", "decision record", or "domain vocabulary" to broaden when-matching.

DimensionReasoningScore

Specificity

"Build and sharpen a project's domain model" is a single abstract action, though the artifacts "GLOSSARY.md" and "ADR" add concreteness. It never names the concrete actions the skill performs (challenge terms, capture entries, draft ADRs), so it matches 'names domain and 1-2 concrete actions' rather than the 'several specific actions' of level 4 or the purely generic level 2.

3 / 5

Completeness

It has an explicit "Use when..." clause with three concrete trigger conditions and a stated what ("Build and sharpen a project's domain model"). The 'what' is a single abstract clause rather than the multiple concrete actions of the level-5 anchor, so level 4 fits best.

4 / 5

Trigger Term Quality

Triggers like "codebase terminology", "GLOSSARY.md", and "ADR" are natural phrases a user working on domain language would say. Common synonyms such as "glossary" (unqualified), "decision record", "domain vocabulary", or "naming" are missing, keeping it below level 5.

4 / 5

Distinctiveness Conflict Risk

GLOSSARY.md and ADR are distinct artifacts giving the skill a clear niche with minimal conflict risk. "Discussing codebase terminology" is somewhat broad and could overlap with documentation or code-review skills, a minor overlap consistent with level 4 rather than 5.

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

withcoral/coral

Path

.agents/skills/domain-modeling/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.