generate-tests

Generate unit tests for a .NET service following the coverage-kit conventions. Use when the user asks to 'generate tests', 'backfill tests', 'characterize this service', or 'add tests for' a target after coverage-init has run. Operates in characterization mode (freeze current behavior for existing code) or spec mode (assert intended behavior for new/changed code), enforces the run-capture-fill loop, routes untestable units to the manifest cannot-test log, can fan the backfill out across a user-chosen number of parallel agents for large worklists (asking first, since more agents cost more tokens), and runs a single read-only suite critique before the baseline locks in (auditing cannot-test legitimacy, assertion/C1 depth, systematic gaps, and any frozen defect missing from the manifest latent_bugs backlog, never the C0/C1 numbers themselves).

Quality

90%

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

Quality

Content

81%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.

The content is highly actionable with a clear, well-validated multi-step workflow and concrete code/commands throughout. Its main weakness is verbosity — rules are repeated and cautionary asides pad the token budget without adding executable guidance.

Suggestions

Consolidate the repeated 'exit gate / not stopping on a number' statements into a single authoritative section; later references can link back instead of restating.

Move the parenthetical war-story asides ('as a real run did, roughly 87 false entries') into a brief 'past failures' reference or trim to one-line rationale, keeping the directive clean.

Consider extracting the verbose fan-out launch rules into a separate reference file so the main body stays a lean overview of the workflow.

Dimension	Reasoning	Score
Conciseness	The body is dense and directive, but several rules are restated multiple times (exit gate, 'not stopping on a number') and parenthetical war-story asides ('as a real run did, roughly 87 false entries') pad the text beyond what Claude needs to execute.	3 / 5
Actionability	Provides exact executable artifacts — script paths, the precise Workflow({ scriptPath, args }) call, a copy-paste YAML latent_bugs entry shape, and commands like `test -s coverage/backfill/worklist.json` — covering the common cases concretely.	5 / 5
Workflow Clarity	A clearly sequenced process (preflight → worklist → phasing → scaling → in-loop measure → exit gate → suite critique → promotion gate) with explicit validation checkpoints and feedback loops ('re-run until green', 'Never record a baseline off a red suite', critique loop until no clear-cut fixes remain).	5 / 5
Progressive Disclosure	Well-sectioned with clear headers and one-level-deep pointers to deeper material (MIGRATIONS.md, base rules, the workflow script), but no bundle files exist and some inlined war-story detail could be offloaded to a reference; structure is good with minor organization gaps.	4 / 5
	Total	17 / 20 Passed

Description

100%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 is specific, trigger-rich, and fully answers both what the skill does and when to use it, in third person. It is dense but every clause earns its place by naming a concrete capability or trigger.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — generate unit tests, characterization/spec modes, run-capture-fill loop, cannot-test routing, parallel agent fan-out, and a pre-baseline suite critique — giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both what ('Generate unit tests for a .NET service following the coverage-kit conventions') and when ('Use when the user asks to...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Quotes natural user utterances verbatim ('generate tests', 'backfill tests', 'characterize this service', 'add tests for'), which are exactly the phrases a user would say when they need this skill.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (.NET coverage-kit test backfill, gated on coverage-init having run) with distinct triggers, minimizing overlap with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: livlign/claude-skills
Path: plugins/dotnet-coverage-kit/skills/generate-tests/SKILL.md
Commit: c8bcd3d

Reviewed: 2 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.