CtrlK
BlogDocsLog inGet started
Tessl Logo

codebase-design

Vocabulary for designing deep modules. Trigger: improve a module interface, place a seam, make code more testable.

64

Quality

76%

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 ./ywai/skills/codebase-design/SKILL.md

The canonical home for this skill is codebase-design in mattpocock/skills

SKILL.md
Quality
Evals
Security

Quality

Content

68%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.

The body is a well-structured conceptual vocabulary skill: lean definitions, concrete principles, and executable testability patterns. Its main weaknesses are the absence of an explicit application workflow with validation checkpoints and two "Going deeper" references that point to files not included in the bundle.

Suggestions

Add the referenced DEEPENING.md and DESIGN-IT-TWICE.md files to the bundle (under references/) so the "Going deeper" links resolve, or remove the links until the files exist.

Provide a short sequenced application workflow with a validation checkpoint (e.g. design interface → run the deletion test → verify one-adapter-vs-two rule → confirm test surface matches interface) to raise workflow clarity above 3.

Trim the ASCII deep/shallow diagrams or collapse them into a single comparison to recover tokens without losing the depth intuition.

DimensionReasoningScore

Conciseness

The glossary uses tight, purposeful definitions and avoids explaining basics Claude already knows, but the ASCII diagrams and repeated "Avoid" annotations add some tokens that could be trimmed; anchor 4 rather than 5.

4 / 5

Actionability

Provides concrete, executable guidance — the deletion test, specific design questions, and runnable TypeScript patterns for testability — with only minor gaps in coverage, matching anchor 4; not 5 because the patterns are illustrative rather than covering the common end-to-end cases.

4 / 5

Workflow Clarity

Content is organized into sections (deep vs shallow → design questions → principles → testability) but there is no sequenced multi-step workflow with validation checkpoints, matching anchor 3; it is not a destructive/batch skill so the cap-at-3 rule is met rather than violated.

3 / 5

Progressive Disclosure

Good section structure with clearly signaled one-level-deep references in "Going deeper" (DEEPENING.md, DESIGN-IT-TWICE.md), fitting anchor 4; not 5 because those referenced files are not present in the bundle, leaving the navigation partially dangling.

4 / 5

Total

15

/

20

Passed

Description

83%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.

The description is concise, third-person, and explicitly pairs a clear "what" with a concrete "Trigger:" clause, satisfying completeness well. Specificity and trigger quality are strong but stop short of fully comprehensive, and a few triggers overlap with adjacent refactoring/testing skills.

Suggestions

Broaden trigger coverage with natural synonyms users might say, e.g. "refactor an interface", "reduce a module's surface area", or "introduce a seam for testing".

Sharpen the "what" beyond "Vocabulary for designing deep modules" with one more concrete verb (e.g. "Apply a vocabulary for designing deep modules…") to reduce overlap with generic refactoring guidance.

DimensionReasoningScore

Specificity

Lists several concrete actions ("improve a module interface, place a seam, make code more testable") and names the domain, matching anchor 4; not a 5 because the actions are abstract design activities rather than comprehensive concrete operations.

4 / 5

Completeness

Explicitly answers "what" ("Vocabulary for designing deep modules") and "when" via an explicit "Trigger:" clause with concrete trigger phrases, matching anchor 5; the explicit trigger guidance means it is not capped at 3.

5 / 5

Trigger Term Quality

Includes natural phrases a developer would say ("improve a module interface", "make code more testable") alongside the jargon term "place a seam"; good coverage but a few synonyms/common variations are missing, so anchor 4 fits better than 5.

4 / 5

Distinctiveness Conflict Risk

Has a clear niche (deep modules, seams) with distinct triggers, but phrases like "make code more testable" overlap with refactoring/testing skills, fitting anchor 4 (mostly distinct, minor overlap) rather than 5.

4 / 5

Total

17

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 missing

Warning

Total

15

/

16

Passed

Repository
YoizenSA/dev-ai-workflow
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.