write-tests

Add missing test coverage for your local code changes by generating new test files (covers uncommitted and untracked changes, or the latest commit if everything is committed). Use when you want write tests for new logic or increase test coverage.

Quality

66%

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 ./plugins/tdd/skills/write-tests/SKILL.md

Quality

Content

63%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 detailed, actionable workflow with strong verification loops, but it suffers from triple-repeated guidance, inlined templates that belong in reference files, and numbering inconsistencies across the two flows.

Suggestions

Move the Coverage Review and Developer Agent templates into separate reference files under ./references/ and link to them, cutting the main body substantially.

Re-number the complex flow as a self-contained 1-N sequence and fix "Return to step 5" to point at the test-writing step.

Drop the Context/Goal sections and de-duplicate the test-quality checklist so the writing guidance appears once.

Dimension	Reasoning	Score
Conciseness	The test-writing guidance is repeated three times (simple flow, the per-agent provisions in steps 6-8, and the full templates), and the Context/Goal sections restate that tests matter for new logic, which Claude already knows.	3 / 5
Actionability	Provides concrete commands ("git status -u", "git show --name-status"), named agents ("review:test-coverage-reviewer", "developer"), and ready-to-fill templates, though reliance on possibly-absent skills (TDD, sadd) leaves minor gaps.	4 / 5
Workflow Clarity	Sequenced into Preparation/Analysis/Test-Writing with explicit verification and iteration loops (steps 8-10), but the simple-flow numbering (1-7) then complex-flow restarting at 6-10 and "Return to step 5" (which points back to Analysis) introduce sequencing confusion.	4 / 5
Progressive Disclosure	No bundle files exist and the full agent-instruction templates are inlined in SKILL.md when they clearly belong in separate reference files; section headers provide some structure but content that should be split is inline.	3 / 5
	Total	14 / 20 Passed

Description

70%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 clear, mostly well-scoped description that answers both what and when with natural trigger terms. It is held back by naming only one core action and slightly thin synonym coverage.

Suggestions

List a second concrete action (e.g., "identifies untested logic via coverage analysis") to lift specificity toward 5.

Add common synonyms such as "unit tests" or "testing" to broaden trigger-term coverage.

Tighten the trigger clause to name the situations more concretely (e.g., "Use when the user asks to add tests for recent changes or bump coverage").

Dimension	Reasoning	Score
Specificity	Names one concrete action ("generating new test files") plus scoping detail (uncommitted/untracked or latest commit), but does not list multiple distinct actions to reach comprehensive coverage.	3 / 5
Completeness	Explicitly answers both "what" (add missing test coverage by generating new test files) and "when" ("Use when you want write tests for new logic or increase test coverage"), though the trigger phrasing could be more specific.	4 / 5
Trigger Term Quality	Includes natural phrases users would say ("write tests", "test coverage", "increase test coverage") but misses common synonyms like "unit tests" or "testing".	4 / 5
Distinctiveness Conflict Risk	The "local code changes" / uncommitted-or-latest-commit scoping carves a distinct niche with minimal conflict risk, though it could still overlap with a general TDD skill.	4 / 5
	Total	15 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: NeoLabHQ/context-engineering-kit
Path: plugins/tdd/skills/write-tests/SKILL.md
Commit: 8539779

Reviewed: 5 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.