skill-tdd

Build features with tests-before-code rigor — use for new features needing test coverage

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 ./.claude/skills/skill-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 body is highly actionable and the TDD cycle is sequenced with strong mandatory verification checkpoints and feedback tables. Its main weaknesses are repetition of the same enforcement message across several sections and a monolithic single-file structure with no progressive disclosure to separate references.

Suggestions

Collapse the overlapping enforcement sections (Iron Law, Common Rationalizations, Red Flags, Bottom Line) into one concise block to remove repeated padding.

Move the example walkthroughs and the Claude Octopus integration table into a separate reference file linked from the main body to add progressive disclosure.

Keep the adversarial-review bash block but trim the prose around it, since the script already carries the guidance.

Dimension	Reasoning	Score
Conciseness	The body restates the same enforcement message across 'MANDATORY COMPLIANCE', 'The Iron Law', 'Common Rationalizations', 'Red Flags', and 'The Bottom Line', adding padding without teaching Claude anything new; it avoids explaining known concepts, so it is 'mostly efficient but could be tightened' rather than fully lean.	2 / 3
Actionability	Provides fully executable TypeScript test and implementation snippets, concrete 'npm test path/to/test.test.ts' commands, and a copy-paste bash provider-dispatch block, matching 'fully executable code/commands; copy-paste ready'.	3 / 3
Workflow Clarity	The Red → Verify → Green → Verify → Refactor cycle is explicitly sequenced with mandatory verification checkpoints, outcome/feedback tables for each phase, and a completion checklist, matching 'clear sequence with explicit validation steps; feedback loops for error recovery'.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the skill is a single ~305-line monolithic file; it is well-sectioned but content that could be split (integration tables, examples) is inline, fitting 'some structure but content that should be separate is inline' rather than a 1 (poorly organized) or 3 (split across files).	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 cleanly answers both what and when with an explicit trigger, but its action vocabulary is narrow and the trigger terms miss the most common 'TDD'/'test-driven' phrasings a user would actually say. The generic 'Build features' opening leaves modest overlap risk with general coding skills.

Suggestions

Add the canonical trigger terms users actually say, e.g. 'test-driven development (TDD)' or 'write tests first', to raise trigger-term coverage.

List a second concrete action (e.g. 'write failing tests, then minimal implementation, then refactor') so specificity moves from one approach-action to multiple concrete actions.

Tighten the opening so the distinct TDD niche is stated up front rather than the generic 'Build features'.

Dimension	Reasoning	Score
Specificity	Quotes 'Build features with tests-before-code rigor' — it names the domain (features) and one approach-level action (tests-before-code), but does not list multiple concrete actions, matching the 'names domain and some actions, but not comprehensive' anchor rather than the multi-action score-3 example.	2 / 3
Completeness	'Build features with tests-before-code rigor' states what, and 'use for new features needing test coverage' is an explicit equivalent of a 'Use when...' trigger, so both what and when are answered explicitly.	3 / 3
Trigger Term Quality	Contains 'tests-before-code' and 'test coverage' but omits the most common natural phrasings ('TDD', 'test-driven development', 'write tests first'), fitting 'some relevant keywords but missing common variations' rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	The 'tests-before-code' / 'test coverage' qualifiers narrow it, but the generic 'Build features' opening could overlap with general feature-building skills, matching 'somewhat specific but could still overlap' rather than a fully distinct 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: nyldn/claude-octopus
Path: .claude/skills/skill-tdd/SKILL.md
Commit: 9f39f0c

Reviewed: 2 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.