test-driven-development

TDD: enforce RED-GREEN-REFACTOR, tests before code.

Quality

65%

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 ./skills/software-development/test-driven-development/SKILL.md

Quality

Content

70%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 highly actionable, well-sequenced TDD workflow with excellent validation checkpoints and feedback loops, undermined by noticeable verbosity from triplicated rationalization rebuttals and basic-concept padding. Consolidating the persuasive sections and externalizing Hermes integration would meaningfully improve token efficiency and progressive disclosure.

Suggestions

Merge the three overlapping rationalization sections ("Why Order Matters", "Common Rationalizations", "Red Flags") into a single concise section to remove duplication and recover tokens.

Move the Hermes Agent Integration details (delegate_task pattern, terminal-tool usage) into a separate reference file and link to it from the body, improving both conciseness and progressive disclosure.

Trim the basic-benefits list ("Finds bugs before commit", "Prevents regressions", "Documents behavior", "Enables refactoring") that restates knowledge Claude already has.

Dimension	Reasoning	Score
Conciseness	The rationalization-rebuttal content is duplicated across three sections ("Why Order Matters", the 11-row "Common Rationalizations" table, and "Red Flags"), and basic TDD benefits Claude already knows (sunk-cost fallacy, manual-testing limits, finds-bugs-before-commit) are spelled out, matching the noticeably-verbose score-2 anchor rather than the mostly-efficient score-3 anchor.	2 / 5
Actionability	Copy-paste-ready code contrasts (good/bad test, add function, retry_operation), concrete executable pytest commands, and a runnable delegate_task example cover the common cases, matching the fully-executable score-5 anchor.	5 / 5
Workflow Clarity	The RED-GREEN-REFACTOR cycle is a clearly sequenced multi-step process with MANDATORY "Verify RED" and "Verify GREEN" checkpoints, explicit error-recovery feedback loops ("Test fails? Fix the code, not the test", "If tests fail during refactor: Undo immediately"), and a final verification checklist, matching the score-5 anchor exactly.	5 / 5
Progressive Disclosure	Internal structure is good (clear section headers, well-ordered), but the skill is a single ~350-line monolith with no reference files at all, and Hermes-specific integration content (delegate_task usage) is inlined rather than split out, fitting the some-structure-but-inline score-3 anchor better than the well-split score-4 anchor.	3 / 5
	Total	15 / 20 Passed

Description

61%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 concise, distinctive description that clearly states what the skill enforces, but it omits any explicit "Use when..." trigger guidance and lacks synonym coverage. Adding a trigger clause and a few natural variants would raise both completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. "Use when writing new features, fixing bugs, refactoring, or making behavior changes," to satisfy the "when" half of completeness.

Add natural synonym trigger terms such as "test-driven", "write tests first", and "unit tests" to broaden trigger-term coverage toward the score-5 anchor.

Optionally list one or two more concrete cycle actions (write failing test, watch it fail, minimal code) to lift specificity from 3 toward 4.

Dimension	Reasoning	Score
Specificity	Names the domain (TDD) and 1-2 concrete actions ("enforce RED-GREEN-REFACTOR", "tests before code") but does not comprehensively enumerate the cycle's individual steps, matching the score-3 anchor rather than the several-actions score-4 anchor.	3 / 5
Completeness	Provides a clear "what" (enforce RED-GREEN-REFACTOR, tests before code) but no explicit "Use when..." clause or equivalent trigger guidance, so per the judging guidelines completeness is capped at 3.	3 / 5
Trigger Term Quality	Strong natural keywords ("TDD", "RED-GREEN-REFACTOR", "tests") that a developer would actually say, but missing common synonyms such as "test-driven", "write tests first", or "unit tests", so it falls just below the comprehensive score-5 anchor.	4 / 5
Distinctiveness Conflict Risk	The "TDD" / "RED-GREEN-REFACTOR" signature carves a clear niche with minimal conflict risk, though the lack of an explicit trigger clause and minor overlap with related debugging skills keeps it just below the score-5 anchor.	4 / 5
	Total	14 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: skills/software-development/test-driven-development/SKILL.md
Commit: 5292074

Reviewed: 1 day 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.