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. Enforces TDD best practices across teams with AI-assisted testing and modern frameworks. Use PROACTIVELY for TDD implementation and governance.

45

Quality

47%

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

20%

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

The body is a verbose persona profile that restates widely-known TDD concepts without executable guidance, concrete examples, or validation checkpoints, and keeps all content inline with no progressive disclosure. It is organized into clear sections but adds little that Claude does not already know.

Suggestions

Replace the capability/behavior/knowledge lists with a short, lean overview plus a concrete red-green-refactor workflow (e.g., write failing test -> run -> implement -> run -> refactor -> run) with explicit validation commands at each step.

Add actionable, copy-paste-ready guidance: example test skeletons, framework-specific commands, and a worked example of orchestrating a multi-agent TDD flow rather than abstract platitudes.

Move the long capability and knowledge-base catalogs into separate reference files (e.g., CAPABILITIES.md, REFERENCES.md) and link to them one level deep from a concise SKILL.md, so the main file assumes Claude's competence and earns its tokens.

DimensionReasoningScore

Conciseness

Roughly 190 lines of capability, behavioral-trait, and knowledge-base lists restate TDD concepts Claude already knows and are padded with buzzwords ('Elite TDD orchestrator', 'comprehensive', 'unwavering test-first discipline'), matching the verbose/padded score-1 anchor; it is not a 2 because almost no token earns its place over Claude's existing knowledge.

1 / 3

Actionability

The Instructions section is generic boilerplate ('Clarify goals, constraints, and required inputs', 'Apply relevant best practices') and the Response Approach is abstract; there is no executable code, command, or concrete example, so it describes a persona rather than instructing.

1 / 3

Workflow Clarity

The 8-step Response Approach provides a visible sequence, but the steps are abstract ('Assess TDD readiness', 'Establish TDD discipline') with no validation checkpoints or feedback loops, fitting the steps-listed-but-validation-gaps anchor; not a 1 because a numbered sequence is present.

2 / 3

Progressive Disclosure

No bundle files exist and the body is a single monolithic ~190-line document with section headers; the capability and knowledge-base lists are content that should live in separate references but is inline, matching the some-structure-but-should-be-split anchor rather than a 1 because headers give reasonable organization.

2 / 3

Total

6

/

12

Passed

Description

75%

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 reasonably strong description: it answers both what and when with an explicit trigger and occupies a clear TDD niche, though its action list is somewhat abstract and its trigger-term coverage could be broader. Third-person voice is maintained throughout.

DimensionReasoningScore

Specificity

Names the TDD domain plus some actions ('Enforces TDD best practices', 'multi-agent workflow coordination', 'red-green-refactor discipline'), but these are abstract rather than the concrete, multi-action listing of a score-3 example.

2 / 3

Completeness

It states what the skill does (TDD orchestration, cycle discipline) and gives an explicit when-trigger ('Use PROACTIVELY for TDD implementation and governance'), satisfying both halves; not below 3 because an explicit trigger clause is present, and not below 2 by the missing-trigger cap.

3 / 3

Trigger Term Quality

'TDD', 'test-driven development', and 'red-green-refactor' are natural terms, but coverage is narrow and omits common variations a user would actually say such as 'testing', 'unit tests', or 'writing tests'.

2 / 3

Distinctiveness Conflict Risk

TDD / red-green-refactor / multi-agent workflow coordination is a clear niche with distinct triggers unlikely to fire for unrelated skills, and the description uses third-person voice.

3 / 3

Total

10

/

12

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

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.