CtrlK
BlogDocsLog inGet started
Tessl Logo

tdd-workflows-tdd-refactor

Use when working with tdd workflows tdd refactor

37

Quality

35%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/tdd-workflows-tdd-refactor/SKILL.md

The canonical home for this skill is tdd-workflows-tdd-refactor in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

45%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 well-structured with clear sections, a concrete code example, and genuine safety/validation checkpoints, but it is weighed down by inlined textbook material Claude already knows and a broken reference to a non-existent playbook file. The destructive-operation validation guidance is the strongest aspect.

Suggestions

Move the SOLID principles, code-smell catalog, and design-pattern enumerations into a separate reference file (and create the referenced resources/implementation-playbook.md or fix the path), keeping only actionable guidance in SKILL.md.

Trim the restated definitions (e.g., "Single Responsibility: One reason to change") that Claude already knows, retaining only skill-specific guidance like the test-safety workflow and recovery protocol.

Convert the abstract pattern lists into concrete, executable steps or a worked example showing the assessment→refactor→validate cycle end-to-end.

DimensionReasoningScore

Conciseness

The body extensively restates concepts Claude already knows — SOLID principle definitions, cataloged code smells, and enumerated GoF design patterns — across ~180 lines of padded reference material; it is noticeably verbose with several unnecessary explanation sections rather than severely padded prose.

2 / 5

Actionability

There is concrete guidance (a Task-tool subagent prompt and an executable before/after TypeScript example), but the bulk is abstract enumeration ("Apply Creational (Factory, Builder, Singleton)") without the specific steps to execute, leaving guidance incomplete.

3 / 5

Workflow Clarity

The numbered Core Process, "Run tests after each modification" checkpoint, Safety Checklist, and Recovery Protocol provide a clear sequence with explicit validation and a failure feedback loop; it falls short of 5 because the steps read as a reference catalog with minor gaps rather than one tight executable workflow.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent) yet line 24 points to resources/implementation-playbook.md which does not exist, and large catalog content (SOLID, patterns, smells) that belongs in separate reference files is inlined into SKILL.md.

2 / 5

Total

11

/

20

Passed

Description

25%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 essentially the skill name wrapped in a generic "Use when working with" clause, restating the domain tokens without concrete capabilities, natural trigger phrasings, or distinctiveness. It answers "when" only weakly and never answers "what".

Suggestions

Replace the generic "working with" verb with 2-4 concrete actions the skill performs (e.g., "Refactor code while keeping all tests green, applying design patterns and performance optimizations").

Add natural trigger phrasings users would actually say, such as "refactor", "clean up code", "improve test coverage", or "safe refactoring", instead of repeating the skill's name tokens.

State both what the skill does and when to use it explicitly, e.g. "Refactor code safely under a test harness. Use when the user asks to refactor, clean up, or restructure code without breaking tests."

DimensionReasoningScore

Specificity

The description names the domain ("tdd workflows tdd refactor") but provides no concrete actions, using only the generic verb "working with"; it is above the entirely-vague anchor (1) but offers minimal actionable specificity.

2 / 5

Completeness

It states a "when" ("Use when working with...") but no "what" — no capability is described — closely matching the anchor where only "when" is present without a real "what".

2 / 5

Trigger Term Quality

The trigger terms are the skill's own name tokens repeated ("tdd workflows tdd refactor") with no natural synonyms or phrasings a user would say, fitting the one-or-two-generic-keywords anchor rather than comprehensive coverage.

2 / 5

Distinctiveness Conflict Risk

The generic "working with tdd workflows tdd refactor" phrasing is broad and would overlap with general TDD or refactoring skills; it lacks a clearly distinct niche trigger, fitting the high-overlap-risk anchor.

2 / 5

Total

8

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-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.