write-tests

Systematically add test coverage for all local code changes using specialized review and development agents. Add tests for uncommitted changes (including untracked files), or if everything is commited, then will cover latest commit.

Quality

42%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./plugins/tdd/skills/write-tests/SKILL.md

Quality

Content

35%

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

This skill provides a comprehensive orchestration workflow for test coverage but suffers from significant verbosity and redundancy, particularly with the agent templates repeating workflow content. The workflow structure is reasonable but lacks precise validation checkpoints and clear decision criteria for the simple vs. complex branching. The skill would benefit greatly from being trimmed down and having the agent templates moved to separate reference files.

Suggestions

Remove or consolidate the agent instruction templates into a separate reference file — they repeat 60%+ of the workflow steps and inflate the document significantly.

Add explicit validation gates: 'If baseline tests fail in step 3, STOP and fix before proceeding' and define clear exit criteria for the iteration loop.

Define what constitutes 'complex logic' vs 'simple change' with concrete examples (e.g., lines changed, number of functions modified) to make the branching decision unambiguous.

Remove the Context section ('After implementing new features...') — Claude already understands why test coverage matters. Start directly with the Goal or Workflow.

Dimension	Reasoning	Score
Conciseness	The skill is very verbose with significant redundancy. The agent instruction templates at the bottom largely repeat the workflow steps above. There's unnecessary context-setting ('After implementing new features or refactoring existing code, it's critical to ensure...'), and the entire document could be cut by 40-50% without losing actionable information. The templates repeat guidance like 'Read TDD skill' and 'Read README' multiple times.	1 / 3
Actionability	The skill provides a structured workflow with specific git commands and clear agent delegation patterns, but lacks executable code examples. Commands like 'run tests' and 'generate coverage report' remain vague without concrete tool-specific examples. The agent templates use placeholder variables ({FILE_PATH}, {TEST_COMMAND}) which is reasonable but the overall guidance is more procedural description than copy-paste ready instructions.	2 / 3
Workflow Clarity	The multi-step workflow is clearly sequenced with numbered steps and parallel execution noted, and there is an iteration loop (step 9). However, validation checkpoints are weak — there's no explicit 'stop if baseline tests fail' after step 3, and the feedback loop between steps 8-9 lacks clear exit criteria beyond 'all critical business logic is covered.' The branching between simple and complex flows adds complexity without clear decision criteria for what constitutes 'complex logic.'	2 / 3
Progressive Disclosure	The skill references external resources like 'sadd skill', 'TDD skill', and README.md but these references are not clearly signaled with file paths or links. The agent instruction templates could be split into separate files to reduce the monolithic nature of the document. No bundle files are provided, so the references to other skills are unverifiable and loosely structured.	2 / 3
	Total	7 / 12 Passed

Description

50%

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 communicates its core purpose—adding test coverage for local code changes—reasonably well, but lacks an explicit 'Use when...' clause and could be more specific about the concrete actions performed. It would benefit from more natural trigger terms users might say and clearer differentiation from other testing-related skills.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to add tests, write test coverage, cover untested code, or test recent changes.'

Include more natural trigger terms users would say, such as 'unit tests', 'write tests', 'test my code', 'missing test coverage', 'generate tests'.

List more specific concrete actions, e.g., 'Analyzes git diffs, identifies untested code paths, generates unit and integration tests, and validates test coverage improvements.'

Dimension	Reasoning	Score
Specificity	The description names the domain (test coverage) and some actions ('add test coverage', 'review', 'cover latest commit'), but doesn't list multiple concrete actions like generating unit tests, integration tests, or specific testing frameworks. It's more process-oriented than action-specific.	2 / 3
Completeness	The 'what' is reasonably clear (add test coverage for local code changes using agents), and there's an implicit 'when' (uncommitted changes or latest commit), but there's no explicit 'Use when...' clause with trigger guidance. Per the rubric, a missing explicit trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	Includes relevant terms like 'test coverage', 'uncommitted changes', 'untracked files', 'latest commit' which users might naturally say. However, it misses common variations like 'unit tests', 'write tests', 'missing tests', 'test my code', 'add tests' in a trigger-oriented way.	2 / 3
Distinctiveness Conflict Risk	The focus on adding test coverage for local/uncommitted changes is somewhat distinctive, but 'test coverage' could overlap with general testing skills, code review skills, or CI/CD skills. The mention of 'specialized review and development agents' adds some distinction but could still conflict with other agent-based skills.	2 / 3
	Total	8 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: NeoLabHQ/context-engineering-kit
Commit: 3711edf

Reviewed: 20 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.