tdd@0.1.0 • ronak • Registry • Tessl

The body is an unmodified skill template: a title and a single TODO line instructing no one to do nothing. It fails almost completely on actionability and workflow clarity — there are no steps, commands, or examples for executing TDD — and its neutral conciseness and progressive-disclosure scores only reflect that there is no content to pad or misorganize. The skill needs its full body written: a red-green-refactor workflow with concrete test commands and validation checkpoints.

Suggestions

Replace the TODO with a concrete red-green-refactor sequence, e.g. 1. Write a failing test for the next behavior, 2. Run the test suite to confirm it fails for the expected reason, 3. Implement the minimal change, 4. Re-run tests to green, 5. Refactor and re-run tests after each change.

Include executable examples of the actual commands (e.g. `pytest test_file.py -k new_test`, `npm test -- --watch=false`) so the guidance is copy-paste ready rather than abstract.

Add explicit validation checkpoints — 'only proceed when the new test fails for the right reason' and 'never leave the suite red after a refactor step' — to give the workflow error-recovery feedback loops.

Dimension	Reasoning	Score
Conciseness	The body ('# tdd' plus 'TODO: Add instructions for how the agent should execute this skill.') contains no padding or over-explanation of concepts Claude already knows, so it is far from the verbose anchors at 1–2. However, the one sentence present is a template placeholder that earns no place in a finished skill, so it cannot be the 'lean and efficient; every token earns its place' content of level 5 or the genuinely useful guidance of level 4 — it sits at the midpoint.	3 / 5
Actionability	There is no concrete guidance whatsoever — no commands, no code, no examples, not even a description of what to do; the only body text is a TODO. This matches the level-1 anchor 'Entirely vague or abstract; no concrete code or commands; only describes rather than instructs' — and the body does not even describe.	1 / 5
Workflow Clarity	TDD is inherently a multi-step process (write failing test, run it, implement, run again, refactor, verify), yet the body contains no steps or sequence at all. This matches the level-1 anchor 'Steps missing or incoherent; no sequence'; level 2 requires at least a rough sequence, which is absent.	1 / 5
Progressive Disclosure	No bundle files exist (no references/, scripts/, or assets/ directories) and no references are cited, so nothing is buried, nested, or misleadingly split — the file is trivially navigable because it is essentially empty. But the 'structure' is a single heading over a placeholder line, not the well-organized sections the simple-skill exception rewards with a 5, so it lands at the middle anchor: structure exists in name only and could be far better organized once real content exists.	3 / 5
	Total	8 / 20 Passed

Description

0%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.

The description field is an unfilled template stub: a lone '## What it does' heading with no content beneath it. It conveys no capabilities, no triggers, and no identity, scoring at the bottom of every dimension. It needs to be rewritten from scratch with concrete third-person actions and an explicit 'Use when...' clause.

Suggestions

State concrete third-person capabilities, e.g. 'Guides test-driven development: write a failing test first, implement the minimum code to pass it, then refactor while keeping tests green.'

Add an explicit trigger clause, e.g. 'Use when the user asks for TDD, red-green-refactor workflows, or wants tests written before implementation.'

Include natural trigger terms and synonyms users would actually say (e.g. 'test-driven development', 'TDD', 'write the test first', 'red-green-refactor') to make the skill discoverable and distinct from general testing or code-review skills.

Dimension	Reasoning	Score
Specificity	The description is literally only the placeholder header "## What it does" — it names no domain and no actions, matching the anchor 'Entirely vague; no concrete actions; pure abstract language'. It cannot score 2 because even 'Processes PDF files' names a domain, whereas this names nothing.	1 / 5
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered anywhere; the text is an empty section heading. This is the level-1 anchor ('Missing both what and when'); the guideline capping completeness at 3 for a missing 'Use when...' clause is irrelevant since even the 'what' is missing.	1 / 5
Trigger Term Quality	The text contains zero keywords of any kind — no natural phrases, no jargon, no file extensions — so nothing a user could say would surface this skill. This matches the level-1 anchor 'No natural keywords... or entirely generic language'; level 2 requires at least one or two generic keywords, which are absent.	1 / 5
Distinctiveness Conflict Risk	With no stated capabilities or triggers, the description provides nothing to distinguish this skill from any other and gives no basis for correct or incorrect triggering. It matches 'Entirely generic; would conflict with virtually any skill'; even the generic examples at levels 2–3 at least mention a domain like documents.	1 / 5
	Total	4 / 20 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
description_field	'description' is very short (16 chars), consider making it more detailed	Warning

	Total	15 / 16 Passed

Reviewed

5 hours ago

ronak/tdd

On this page