test-driven-development

Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first

Quality

86%

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

Quality

Content

88%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.

A well-structured TDD workflow with executable code examples, clear phase sequencing, and explicit validation checkpoints plus an error-recovery feedback loop. The main weaknesses are mild verbosity in the subagent evaluation criteria and the use of non-standard custom tags that slightly disrupt clean markdown organization.

Suggestions

Tighten the subagent evaluation bullets in the <required> block into more concise criteria to reduce token overhead while preserving the actionable checks.

Replace custom tags (<required>, <good-example>, <system-reminder>) with standard markdown headings or blockquotes so the structure is cleaner and more navigable.

Consider moving the detailed test-quality heuristics into a separate reference file referenced one level deep, keeping SKILL.md as a tighter overview of the RED/GREEN/REFACTOR loop.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with annotated good/bad examples and direct commands, but the multi-bullet subagent evaluation criteria and embedded custom tags add mild over-explanation that could be trimmed, fitting 'efficient; minor instances of over-explanation' rather than the fully lean 5.	4 / 5
Actionability	Provides copy-paste ready TypeScript code for both RED and GREEN phases, concrete shell commands ('npm test path/to/test.test.ts'), and paired good/bad examples covering the common retry case, matching the 'fully executable; copy-paste ready' anchor.	5 / 5
Workflow Clarity	The RED/GREEN/REFACTOR sequence is explicitly numbered with validation checkpoints ('Verify the test fails', 'Verify the test now passes', 'Verify tests still pass') and a feedback loop ('If you go through three loops without making progress, switch to...'), matching the top anchor with explicit validation and error-recovery guidance.	5 / 5
Progressive Disclosure	Content is well-organized into clearly labeled RED/GREEN/REFACTOR sections with a single one-level reference to another skill, but no bundle files exist to split detail into and the custom <required>/<system-reminder> tags introduce minor organization gaps, placing it just below the ideally-structured 5.	4 / 5
	Total	18 / 20 Passed

Description

83%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.

A strong description that clearly states both the TDD methodology (what) and a concrete triggering context (when), with concrete actions and natural trigger terms. The main weakness is the breadth of 'any feature or bugfix', which slightly raises overlap risk with general coding skills.

Dimension	Reasoning	Score
Specificity	Names the TDD domain and lists several concrete actions ('write the test first, watch it fail, write minimal code to pass') with only minor coverage gaps (no mention of refactor/verify steps), fitting the 'several specific actions' anchor rather than the fully comprehensive 5.	4 / 5
Completeness	Explicitly answers both what ('write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first') and when ('Use when implementing any feature or bugfix, before writing implementation code') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural terms a user would say ('implementing any feature or bugfix', 'before writing implementation code') with good coverage, but misses common synonyms like 'fix', 'change', or 'new functionality', placing it just below the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	The test-first methodology is a distinct niche with clear triggers, but 'any feature or bugfix' is broad enough to risk minor overlap with general coding skills, so it sits at 'mostly distinct' rather than the minimal-conflict 5.	4 / 5
	Total	17 / 20 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: microsoft/FluidFramework
Path: .agency/plugins/nori/skills/test-driven-development/SKILL.md
Commit: f02e424

Reviewed: 3 days 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.