CtrlK
BlogDocsLog inGet started
Tessl Logo

tdd-workflows-tdd-refactor

Use when working with tdd workflows tdd refactor

48

Quality

51%

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/tdd-workflows-tdd-refactor/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

The content is well-structured with a clear process, safety checklist, and recovery protocol, and includes a concrete invocation prompt and example. Its main weakness is verbosity from cataloging concepts Claude already knows, with everything inlined in a single file rather than split across references.

Suggestions

Cut the explanatory catalogs of widely-known concepts (SOLID principle definitions, code-smell and design-pattern enumerations) down to the non-obvious guidance Claude would not already supply.

Move the long pattern/smell catalogs into reference files (e.g. references/patterns.md, references/code-smells.md) and link to them one level deep so SKILL.md stays a lean overview.

Keep the Task-tool prompt and before/after example as the actionable core and trim the surrounding boilerplate ('Use this skill when / Do not use this skill when' generic template).

DimensionReasoningScore

Conciseness

The body is padded with well-known material Claude already knows (SOLID definitions, code-smell lists, design-pattern categories), but it also contains lean actionable elements like the Task-tool prompt and example, fitting 'mostly efficient but includes some unnecessary explanation'; not a 1 because the actionable core is genuinely lean.

2 / 3

Actionability

It provides a concrete Task-tool invocation with a copy-paste prompt template and a worked before/after TypeScript example, but large portions are conceptual catalogs ('Apply Behavioral (Strategy, Observer, Command)') that describe rather than instruct, so it is not fully copy-paste ready throughout.

2 / 3

Workflow Clarity

The numbered Core Process (Pre-Assessment through Safety Verification) plus a Safety Checklist and a Recovery Protocol with an explicit feedback loop (tests fail -> revert -> apply smaller changes) provides a clear sequence with validation checkpoints and error recovery.

3 / 3

Progressive Disclosure

No bundle files exist (references/scripts/assets absent) and all content is inline in one monolithic file; pattern catalogs that should be split out are inline with no external references, matching 'content that should be separate is inline'; not a 1 because sections are at least organized.

2 / 3

Total

9

/

12

Passed

Description

40%

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 essentially a bare trigger clause with no statement of capabilities, using unnatural duplicated tokens rather than natural language. It answers 'when' but not 'what', and is not clearly distinguishable from generic TDD skills.

Suggestions

Rewrite as a third-person capability statement plus a 'Use when...' trigger, e.g. 'Refactors code safely under a green-test safety net using TDD. Use when the user asks to refactor, clean up, or restructure code while keeping tests passing.'

Replace the duplicated token phrase 'tdd workflows tdd refactor' with natural trigger terms a user would actually say (refactor, clean up code, improve design, keep tests green).

Add concrete actions so the 'what' is explicit (apply design patterns, eliminate code smells, optimize performance) rather than only stating when to use the skill.

DimensionReasoningScore

Specificity

The description is only a trigger clause ("Use when working with tdd workflows tdd refactor") and names no concrete actions or capabilities, matching the anchor 'Vague or no actions; abstract language.'

1 / 3

Completeness

It has an explicit 'when' trigger but entirely lacks a 'what does this do' statement; per guideline a missing what caps completeness, keeping it at 2 rather than 3 and above 1 because the when is explicit.

2 / 3

Trigger Term Quality

It references the relevant domain (tdd, refactor) but as unnatural token salad ('tdd workflows tdd refactor') rather than phrases a user would actually say; below 3 because coverage of natural terms is poor, above 1 because some relevant keywords are present.

2 / 3

Distinctiveness Conflict Risk

'tdd workflows tdd refactor' is somewhat specific to its niche but the generic, mangled phrasing could overlap with other TDD/refactoring skills, fitting 'Somewhat specific but could still overlap.'

2 / 3

Total

7

/

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
rmyndharis/antigravity-skills
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.