Tessl • The management layer for AI agent skills

The content is a strong, actionable workflow: concrete commands, explicit validation checkpoints with feedback loops, and well-organized sections. Its only weaknesses are minor — decorative ASCII banners, an undefined "BLOCKED" state, and output templates that consume tokens. This is a solid single-file skill.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence — no re-explanation of what TDD is — but the decorative ASCII banners and ~37 lines of output-format templates could be trimmed.	4 / 5
Actionability	Highly concrete: a copy-paste-ready test-runner detection script covering vitest/jest/playwright/mocha/npm, exact test commands with $TEST_CMD/$TEST_FILTER, and a commit command. Minor gaps: the "BLOCKED" state is never defined and the test example is a fill-in skeleton.	4 / 5
Workflow Clarity	The RED/GREEN/REFACTOR sequence is explicitly numbered with validation at every checkpoint ("Verify FAILS", "Verify PASSES", "Run ALL tests / Verify ALL PASS"), error-recovery directives ("fix before continuing"), a captured-output verification protocol, and a Rules checklist.	5 / 5
Progressive Disclosure	No bundle files exist and the single ~200-line file is well-organized into clear sections (When to Use, Workflow, Verification Protocol, Output, Anti-Rationalization, Rules). It exceeds the under-50-line simple-skill case, and the inline output templates and anti-rationalization table are minor organization gaps.	4 / 5
	Total	17 / 20 Passed

Description

32%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 has a clear, explicit 'Use when' trigger but completely omits what the skill does, and its scope is so broad that it would fire for almost any coding task. It also lacks the natural testing keywords (TDD, test-driven, write tests first) that users would most likely say. Rewriting it to state the skill's concrete actions and narrow the trigger would substantially improve it.

Suggestions

Add a 'what' clause stating the skill's concrete actions, e.g. "Implements features via strict test-driven development: write a failing test first, then minimal implementation, then refactor (RED/GREEN/REFACTOR cycles)."

Include natural trigger terms users would actually say, such as "TDD", "test-driven", "write tests first", or "regression test", so the skill triggers when users explicitly ask for test-first development.

Narrow the trigger to reduce conflict risk, e.g. "Use when correctness matters and the user wants test-driven development or a regression test to prove a bugfix" rather than "any feature or bugfix where correctness matters".

Dimension	Reasoning	Score
Specificity	The description names the domain ("implementing any feature or bugfix where correctness matters") but never states what the skill actually does — no concrete actions like writing failing tests or running RED/GREEN/REFACTOR cycles are mentioned.	2 / 5
Completeness	Only the 'when' is present ("Use when implementing any feature or bugfix where correctness matters") with no 'what' — the skill's actions are never described, matching the anchor for "only 'when' present without 'what'".	2 / 5
Trigger Term Quality	"implementing", "feature", "bugfix", and "correctness" are natural user terms, but the entire testing vocabulary ("TDD", "test-driven", "write tests first", "regression") is missing, so common variations and synonyms are absent.	3 / 5
Distinctiveness Conflict Risk	"any feature or bugfix where correctness matters" is very broad — nearly all coding work qualifies — creating high overlap risk with general coding, testing, and code-review skills.	2 / 5
	Total	9 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: fernandezbaptiste/specialist-agent
Path: skills/tdd/SKILL.md
Revision: cd716d9

Reviewed: 8 days ago

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.

tdd

Table of Contents

Is this your skill?