CtrlK
BlogDocsLog inGet started
Tessl Logo

tdd-orchestrator

Master TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive test-driven development practices.

28

Quality

19%

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-orchestrator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

3%Scale 1-5

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

This skill is essentially a persona/role description rather than an actionable skill document. It exhaustively lists abstract capabilities, behavioral traits, and knowledge areas without providing any concrete, executable guidance for performing TDD orchestration. The content is severely bloated with information Claude already knows (TDD concepts, testing frameworks, methodologies) while lacking the specific steps, code examples, validation checkpoints, and tool usage instructions that would make it useful.

Suggestions

Replace the extensive capability/trait/knowledge lists with a concise, concrete workflow showing how to actually orchestrate a TDD cycle — include specific commands, code examples, and tool invocations.

Add explicit validation checkpoints to the workflow (e.g., 'Run tests to confirm red state before writing implementation', 'Verify all tests pass before refactoring') with concrete commands.

Move detailed reference material (framework-specific patterns, advanced techniques) into the referenced 'resources/implementation-playbook.md' bundle file and keep SKILL.md as a lean overview with actionable steps.

Replace the 'Example Interactions' section with actual input/output examples showing what Claude should produce when given a TDD orchestration request, including concrete code and test examples.

DimensionReasoningScore

Conciseness

Extremely verbose and padded. The vast majority of content is listing capabilities, behavioral traits, knowledge bases, and example interactions that Claude already knows or that provide no actionable guidance. The skill reads like a persona description or resume rather than a concise instruction set. Hundreds of tokens are spent on bullet-point lists of abstract concepts (e.g., 'TDD anti-pattern detection and prevention', 'TDD culture transformation and organizational change management') that teach Claude nothing new.

1 / 5

Actionability

The skill contains zero concrete code, commands, or executable steps. It is entirely abstract descriptions of capabilities and vague directives like 'Apply relevant best practices and validate outcomes.' There are no specific examples, no code snippets, no tool invocations, and no concrete workflows that Claude could follow to actually perform TDD orchestration.

1 / 5

Workflow Clarity

There is no clear multi-step workflow with sequenced steps or validation checkpoints. The 'Response Approach' section lists 8 high-level abstract phases ('Assess TDD readiness', 'Establish TDD discipline') but none have concrete steps, commands, or validation criteria. For a skill involving orchestration of complex multi-step processes, the complete absence of concrete workflows with checkpoints is a critical gap.

1 / 5

Progressive Disclosure

There is one reference to 'resources/implementation-playbook.md' but no bundle files are provided, so it's unclear if this reference is valid. The massive amount of content (capabilities lists, behavioral traits, knowledge base) is all inlined in a monolithic fashion with no meaningful structure for navigation. The content that is present would benefit enormously from being split into separate reference files rather than being listed as bullet points in the main skill.

2 / 5

Total

5

/

20

Passed

Description

36%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.

This description reads more like a title or tagline than a functional skill description. It relies heavily on buzzwords ('master orchestrator', 'comprehensive practices') without specifying concrete actions or providing any trigger guidance for when Claude should select this skill. The TDD domain is identifiable but the actual capabilities remain unclear.

Suggestions

Replace abstract terms like 'orchestrator' and 'comprehensive practices' with concrete actions such as 'writes failing tests, generates minimal implementation to pass tests, refactors code while maintaining passing tests'.

Add an explicit 'Use when...' clause with natural trigger phrases like 'Use when the user asks to write tests first, practice TDD, follow red-green-refactor, or develop code test-first'.

Clarify what 'multi-agent workflow coordination' means in practice — specify the concrete steps or agents involved to reduce ambiguity and overlap with other workflow-related skills.

DimensionReasoningScore

Specificity

Names the domain (TDD, red-green-refactor) but actions are vague and abstract. 'Orchestrator', 'coordination', and 'practices' are not concrete actions. No specific capabilities like 'writes failing tests', 'generates implementation code', or 'refactors to clean code' are mentioned.

2 / 5

Completeness

Has a vague 'what' (orchestrating TDD and multi-agent workflows) but no 'when' clause at all. There is no 'Use when...' guidance or equivalent trigger phrasing, which per the rubric should cap completeness at 3, and the weak 'what' brings it down further.

2 / 5

Trigger Term Quality

Includes some relevant keywords like 'TDD', 'red-green-refactor', and 'test-driven development', which users might naturally say. However, it misses common variations like 'unit tests', 'testing', 'write tests first', 'test coverage', or 'failing test'.

3 / 5

Distinctiveness Conflict Risk

The TDD and red-green-refactor focus provides some specificity, but 'multi-agent workflow coordination' is vague and could overlap with many orchestration or workflow skills. The 'comprehensive practices' language is generic and increases conflict risk.

3 / 5

Total

10

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

10

/

11

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.