CtrlK
BlogDocsLog inGet started
Tessl Logo

he-tdd

Build behavior-safe code changes with TDD and RED/GREEN evidence. Use when he-plan or he-work requires TDD for a concrete behavior target.

56

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./Plugins/harness-engineering/fixtures/budget-archive/2026-04-21/deferred-store/skills/team_automation/he-tdd/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%Scale 1-3

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

This skill is well-structured as a progressive disclosure entrypoint with excellent reference organization and clear 'Read when' annotations. However, it lacks concrete, executable examples (no sample test code, no framework-specific commands) and the workflow steps need explicit validation checkpoints between RED and GREEN phases to match the skill's own stated constraint of 'do not skip RED verification.'

Suggestions

Add a concrete executable example showing a minimal RED test followed by a GREEN fix, even if brief, to demonstrate the expected workflow pattern with actual code.

Insert explicit validation checkpoints between procedure steps—e.g., after step 3, verify RED output before proceeding to GREEN, with a sample expected output format.

Remove or consolidate the duplicated Subagent Routing section since it largely repeats the reference already linked in Full Context, and trim the Philosophy and preamble sections to save tokens.

DimensionReasoningScore

Conciseness

The skill is moderately efficient but includes some unnecessary sections like the 'Progressive Disclosure Entry' preamble explaining its own structure, the Philosophy section, and the Examples section which just shows natural language prompts rather than actionable examples. The Subagent Routing section duplicates a reference link already listed in Full Context.

2 / 3

Actionability

The procedure provides a clear sequence but remains at a high level of abstraction—there are no concrete code examples, specific test commands, or executable snippets beyond the validation bash command. The guidance describes what to do conceptually ('produce a failing test first') without showing how (no sample test code, no framework-specific commands).

2 / 3

Workflow Clarity

The 5-step procedure outlines a reasonable sequence and the validation section provides a concrete gate command with a 'fail fast' instruction. However, there are no explicit validation checkpoints between steps (e.g., confirming RED before proceeding to GREEN), and the feedback loop for error recovery is only implicit in 'repeat in vertical slices.'

2 / 3

Progressive Disclosure

The skill excels at progressive disclosure with a concise entrypoint and well-signaled one-level-deep references, each annotated with 'Read when:' conditions that clearly indicate when to load each reference. The Full Context section is well-organized with topical links to preserved guides, mocking, interface design, refactoring, etc.

3 / 3

Total

9

/

12

Passed

Description

75%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 has a clear niche and explicitly addresses both what the skill does and when to use it, which is a strength. However, it relies on internal/custom terminology ('he-plan', 'he-work') that reduces trigger term quality for natural user queries, and the capability description could be more specific about the concrete actions performed during the TDD workflow.

Suggestions

Replace or supplement 'he-plan' and 'he-work' with natural language terms users might say, such as 'test-driven development', 'write failing tests first', 'red-green-refactor cycle'.

List more specific concrete actions, e.g., 'Writes failing tests, implements minimal code to pass, captures RED/GREEN console output as evidence, and refactors safely.'

DimensionReasoningScore

Specificity

Names the domain (TDD, code changes) and mentions some actions ('build behavior-safe code changes', 'RED/GREEN evidence'), but doesn't list multiple concrete actions like writing tests, running tests, refactoring, or verifying test output.

2 / 3

Completeness

Clearly answers both 'what' (build behavior-safe code changes with TDD and RED/GREEN evidence) and 'when' (when he-plan or he-work requires TDD for a concrete behavior target), with an explicit 'Use when' clause.

3 / 3

Trigger Term Quality

Includes relevant terms like 'TDD', 'RED/GREEN', and 'behavior-safe', but uses non-standard references ('he-plan', 'he-work') that users would not naturally say. Missing common variations like 'test-driven development', 'unit tests', 'failing test', 'green test'.

2 / 3

Distinctiveness Conflict Risk

The focus on TDD with RED/GREEN evidence and the specific trigger conditions ('he-plan or he-work requires TDD for a concrete behavior target') create a clear niche that is unlikely to conflict with general coding or testing skills.

3 / 3

Total

10

/

12

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

9

/

11

Passed

Repository
jscraik/Agent-Skills
Reviewed

Table of Contents

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.