CtrlK
BlogDocsLog inGet started
Tessl Logo

naming

Evaluate and improve names in code using naming as a design diagnostic. Use when the user asks to "name this", "rename", "review naming", "what should I call", struggles to name something, or when a code review surfaces vague or misleading names.

77

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, highly actionable skill body that keeps concrete examples inline while delegating detailed rules to a single well-signaled reference. Both review and design workflows are clearly sequenced with a checklist for verification.

DimensionReasoningScore

Conciseness

The body is dense and scannable — bullet lists, compact tables, and a checklist — with no padding or explanation of concepts Claude already knows. It is not a 2 because every table earns its place and there is no unnecessary explanation to tighten.

3 / 3

Actionability

Concrete before/after tables with specific code (processData → validateInvoiceLineItems), a copy-ready output format template, and a named checklist give fully executable guidance. It is not a 2 because the guidance is specific and copy-paste ready rather than pseudocode or abstract direction.

3 / 3

Workflow Clarity

Two clearly sequenced modes (Review Mode 1–3, Design Mode 1–5) with the naming checklist serving as an explicit verification step. It is not a 2 because the sequence and checking mechanism are explicit; no destructive/batch operations are present that would require additional validation checkpoints.

3 / 3

Progressive Disclosure

The body is an overview that signals one clearly-named, one-level-deep reference ("See references/principles.md for detailed rules and naming smells"), and that file exists. It is not a 2 because the reference is clearly signaled and content is appropriately split rather than inlined or nested multiple levels deep.

3 / 3

Total

12

/

12

Passed

Description

92%

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 description with explicit what/when structure and natural, quotable trigger terms. Its only weakness is slight overlap with general code-review skills via the broader review-oriented triggers.

Suggestions

Tighten the "when a code review surfaces vague or misleading names" trigger to emphasize naming-specific signals (e.g., vague or misleading *names*) so it is less likely to fire for general code review.

Lead the trigger list with the most naming-distinct phrases and consider scoping "review naming" to "review *code* naming" to reduce conflict with a generic /review skill.

DimensionReasoningScore

Specificity

"Evaluate and improve names in code using naming as a design diagnostic" names multiple concrete actions (evaluate, improve, use as a design diagnostic) rather than vague language. It is not a 2 because it goes beyond naming a domain and some actions to list specific concrete operations with a defined method.

3 / 3

Completeness

It explicitly answers both what ("Evaluate and improve names in code...") and when (an explicit "Use when the user asks to..." clause with multiple triggers). It is not a 2 because the when is explicit, not merely implied.

3 / 3

Trigger Term Quality

Quoted natural phrases users would actually say — "name this", "rename", "review naming", "what should I call" — plus "struggles to name something" give strong coverage of natural terms. It is not a 2 because it includes the common variations rather than only some relevant keywords.

3 / 3

Distinctiveness Conflict Risk

"Naming as a design diagnostic" is a clear niche, but triggers like "review naming" and "when a code review surfaces vague or misleading names" overlap with general code-review skills. It is not a 3 because the broader code-review triggers could fire for the wrong skill; it is not a 1 because the naming-specific triggers dominate.

2 / 3

Total

11

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
tslateman/duet
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.