CtrlK
BlogDocsLog inGet started
Tessl Logo

codebase-design

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

72

Quality

89%

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

SKILL.md
Quality
Evals
Security

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.

The body is lean, well-organized, and actionable for a conceptual design skill, with strong glossary discipline and concrete patterns. The main weakness is that the two "Going deeper" reference files are missing, leaving dead links.

Suggestions

Create the referenced DEEPENING.md and DESIGN-IT-TWICE.md files (or remove the "Going deeper" links) so the signaled navigation resolves to real content.

Ensure each code example is self-contained and runnable as written, or mark explicitly that snippets are illustrative patterns to adapt.

If the skill is purely conceptual, consider a short "How to apply this" checklist that sequences the principles into a concrete design pass.

DimensionReasoningScore

Conciseness

Lean and dense throughout — the glossary, principles, and code examples assume Claude's competence and add only the deep-module vocabulary it would not already share, with no padding of basic concepts.

5 / 5

Actionability

Provides concrete TypeScript examples, ASCII diagrams, the deletion test, and specific design questions, but the code is illustrative of patterns rather than copy-paste runnable as a unit, leaving minor gaps.

4 / 5

Workflow Clarity

A conceptual vocabulary skill rather than a sequenced procedure, but the principles and design questions are clearly organized and unambiguous; no destructive/batch workflow that would require validation checkpoints.

4 / 5

Progressive Disclosure

The body is well-structured and signals one-level-deep references (DEEPENING.md, DESIGN-IT-TWICE.md) under "Going deeper", but those referenced files do not exist in the bundle, so navigation is broken.

3 / 5

Total

16

/

20

Passed

Description

100%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 third-person, concrete, and answers both what and when with explicit, natural trigger phrases. It is comprehensive and clearly distinguishable from other skills.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — "design or improve a module's interface", "find deepening opportunities", "decide where a seam goes", "make code more testable or AI-navigable" — giving comprehensive coverage of the domain.

5 / 5

Completeness

Explicitly answers both what ("Shared vocabulary for designing deep modules") and when ("Use when the user wants to design or improve a module's interface, find deepening opportunities...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural phrases a user would actually say are present and varied ("design or improve a module's interface", "find deepening opportunities", "make code more testable", "AI-navigable"), with synonyms covering the design intent.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — deep-module design vocabulary — with distinct triggers and minimal overlap risk against other skills.

5 / 5

Total

20

/

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
coder/agent-tty
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.