tdd-red-green-refactor

Enforces a disciplined Red-Green-Refactor (TDD) workflow in TypeScript/Node.js. Use this whenever creating new features, fixing bugs, or migrating logic to ensure high-quality, verifiable implementations.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/tdd/SKILL.md

Quality

Content

77%

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

The content is a strong, actionable TDD workflow: executable code, clear sequencing, and explicit validation feedback loops. Its main weaknesses are minor verbosity in framing language and the absence of any progressive-disclosure structure, though the skill is largely self-contained.

Suggestions

Trim mission-statement and metaphorical flourishes (e.g. the opening 'structural framework' sentence, 'Proof of Work', 'playing in the mud') to improve token efficiency.

Consider moving the worked example or the 'Core Operational Rules' into a referenced file (e.g. EXAMPLES.md) to add one-level-deep progressive disclosure and keep the main body as a lean overview.

Optionally add a brief validation checklist at the end of the cycle to reinforce the feedback loop as a scannable artifact.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and does not over-explain TDD or TypeScript, but includes unnecessary flourishes such as the opening 'This skill implements a structural framework for AI-assisted programming' line, the 'Proof of Work for the developer' phrase, and the 'playing in the mud with low-quality code' metaphor that could be trimmed, matching the score-2 anchor of 'mostly efficient but could be tightened'.	2 / 3
Actionability	Provides fully executable, copy-paste-ready TypeScript/Vitest code across all three phases (a failing test, a minimal implementation, and a typed refactor), plus concrete numbered steps, matching the score-3 anchor for executable, specific examples.	3 / 3
Workflow Clarity	The Red→Green→Refactor cycle is explicitly sequenced with validation checkpoints ('Execute & Fail', 'Run Tests') and an explicit feedback loop ('Rerun the tests after every change. If they turn Red, revert the change immediately'), matching the score-3 anchor for clear sequence with error-recovery loops.	3 / 3
Progressive Disclosure	The body is well-organized into clear sections (Three-Phase Cycle, Core Operational Rules, Example Workflow), but it is a single ~85-line self-contained file with no external references or navigation; it exceeds the under-50-line simple-skill threshold, so in-file structure alone lands at the score-2 anchor rather than a 3.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 well-formed: third-person, with an explicit 'Use this whenever' trigger that satisfies completeness. It is held back from the top tier by broad trigger scenarios and a lack of multiple distinct concrete capability statements.

Suggestions

Replace generic trigger scenarios with capability-focused phrasing, e.g. 'Write failing tests first, implement minimal code to pass, then refactor — for new features, bug fixes, and logic migrations.'

Add common natural trigger terms users would say, such as 'writing tests', 'unit testing', 'test coverage', and 'refactoring code', to improve trigger-term coverage.

Tighten distinctiveness by anchoring triggers to the TDD cycle itself (e.g. 'Use when writing code test-first') rather than to broad scenarios like 'fixing bugs'.

Dimension	Reasoning	Score
Specificity	Names the domain ('Red-Green-Refactor (TDD) workflow in TypeScript/Node.js') and the action 'Enforces', but does not list multiple distinct concrete capabilities — instead it enumerates trigger scenarios ('creating new features, fixing bugs, or migrating logic'), matching the score-2 anchor rather than the multi-action score-3 example.	2 / 3
Completeness	Clearly answers both what ('Enforces a disciplined Red-Green-Refactor (TDD) workflow') and when with an explicit trigger clause ('Use this whenever creating new features, fixing bugs, or migrating logic'), satisfying the score-3 anchor and the guideline that an explicit 'Use when' clause keeps completeness uncapped.	3 / 3
Trigger Term Quality	Includes natural trigger phrases ('creating new features, fixing bugs, or migrating logic') plus 'TDD' and 'TypeScript/Node.js', but misses common variations a user might say such as 'writing tests', 'unit tests', 'refactoring', or 'test coverage', so coverage is partial rather than comprehensive.	2 / 3
Distinctiveness Conflict Risk	The TDD/TypeScript/Node.js niche is reasonably distinct, but the trigger scenarios ('creating new features, fixing bugs') are generic enough to overlap with general coding skills, so it is 'somewhat specific but could still overlap' rather than a clearly non-conflicting niche.	2 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: google-labs-code/stitch-sdk
Path: .agents/skills/tdd/SKILL.md
Commit: 575a9fb

Reviewed: 22 minutes ago

Table of Contents

Discovery Implementation Validation

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.