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

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/skill-tdd/SKILL.md

Quality

Content

77%Weight 40%Scale 1-3

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

The body delivers an exceptionally clear, actionable TDD workflow with strong validation loops, but it is long and monolithic with heavy enforcement rhetoric that could be trimmed or offloaded to reference files.

Suggestions

Trim reinforcement sections (Iron Law, Common Rationalizations, Red Flags, Bottom Line) that repeat the same test-first message to improve token efficiency.

Move the rationalizations table, integration-with-octopus table, and extended examples into reference files linked one level deep from the overview.

Replace the ASCII cycle diagram with a compact numbered list to cut tokens without losing the workflow sequence.

Dimension	Reasoning	Score
Conciseness	Concrete examples are efficient, but the body is padded with reinforcement rhetoric ('MANDATORY COMPLIANCE', 'The Iron Law', 'Common Rationalizations', 'Red Flags', 'The Bottom Line') and an ASCII diagram that re-explain test-first discipline Claude already knows, falling short of lean.	2 / 3
Actionability	Provides fully executable TypeScript examples, concrete 'npm test' commands, and a real provider-detection orchestrate.sh block — copy-paste ready rather than pseudocode.	3 / 3
Workflow Clarity	The Red → Verify Red → Green → Verify Green → Refactor cycle is explicitly sequenced with mandatory validation checkpoints and outcome-to-action feedback tables, plus a completion checklist.	3 / 3
Progressive Disclosure	Headers organize the ~300-line body, but it is monolithic with no bundle references and content (rationalizations, integration tables, examples) that could be split is inline; not poor enough for a 1 yet not reference-structured for a 3.	2 / 3
	Total	10 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 answers both what and when with an explicit trigger, but its action list and trigger-term coverage are narrow and the phrasing risks overlapping with general coding skills.

Suggestions

Add more concrete actions beyond 'Build features' (e.g., 'write failing tests, drive implementation, refactor under green') to lift specificity.

Broaden trigger terms to include natural variations like 'implement', 'add feature', 'fix bug', and 'test coverage'.

Sharpen distinctiveness by foregrounding the test-first/TDD angle in the trigger clause rather than the generic 'build features'.

Dimension	Reasoning	Score
Specificity	Quotes 'Build features with tests-before-code rigor' name a single concrete action and domain rather than the multiple specific actions a score-3 anchor lists; it is not vague enough for a 1.	2 / 3
Completeness	'Build features with tests-before-code rigor' states the what and 'use for new features needing test coverage' gives an explicit 'use for' when-clause, clearly answering both.	3 / 3
Trigger Term Quality	'new features needing test coverage' and 'build features' are natural user phrases, but coverage is narrow and omits common variations like 'implement', 'add', or 'bugfix', so it is not a 3.	2 / 3
Distinctiveness Conflict Risk	The 'tests-before-code rigor' qualifier carves a niche, but the broad 'build features' / 'new features' phrasing could overlap with a general coding skill, so it is not clearly conflict-free enough for a 3.	2 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nyldn/claude-octopus
Path: .claude/skills/skill-tdd/SKILL.md
Commit: 9f39f0c

Reviewed: 11 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.