testing

Apply Epicenter test-file conventions for setup, factories, Result assertions, type tests, naming, and pruning. Use when writing, reviewing, deleting, or reorganizing tests, especially `*.test.ts` files.

Quality

85%

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

80%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 well-structured conventions skill: lean, highly actionable, with an exemplary progressive-disclosure router to real reference files. The main weakness is workflow clarity — destructive tasks (test deletion/reorganization) have no validation or verification step in the body, which caps that dimension despite the otherwise crisp decision rules.

Suggestions

Add a verification step for the destructive path: after deleting or reorganizing tests, instruct to re-run `bun test` and confirm the suite passes and no behavioral coverage was lost (this would lift workflow_clarity above its cap).

Trim the caret-annotated "Pattern: {action} {outcome}" diagrams — the good-name examples already demonstrate the pattern, so the annotation block duplicates them.

In the test-deletion reference pointer, state the immediate safety check (e.g., confirm the test is redundant or covers dead code before removing) so the destructive action is gated even before the reference is loaded.

Dimension	Reasoning	Score
Conciseness	The body is dense rules-plus-examples with almost no explanation of concepts Claude already knows (no 'what is a test' padding); sections like Tests vs. Benchmarks and Test Naming are tight. Not a 5 because of minor trimmable material — the ASCII caret diagrams under "Pattern: {action} {outcome}" restate what the good examples already show, and the doc-comment template has some boilerplate lines.	4 / 5
Actionability	Copy-paste-ready code (the `expectOk`/`expectErr` import-and-usage block, JSDoc good example, section-header comment block) plus concrete decision criteria everywhere: exact file extensions, the `src/__benchmarks__/` location, numeric thresholds (~500 lines, 100+ lines, fewer than 3 tests), and a splitting table. Good/bad name pairs make the rule checkable.	5 / 5
Workflow Clarity	There is no multi-step sequence with checkpoints; the skill covers destructive operations ("deleting or pruning tests") and per the judging guidelines missing validation/verification steps in workflows involving destructive or batch operations caps workflow clarity at 3. Nothing tells the model to verify (e.g., re-run `bun test`, confirm no coverage loss) after pruning or reorganizing test files. It is not a 2 because the per-task decision rules (which extension, when to split, when not to) are themselves unambiguous.	3 / 5
Progressive Disclosure	The References section is a well-signaled one-level-deep router: each of the five on-demand loads pairs a specific trigger condition (negative type tests, setup architecture, hedged assertions, pruning) with a link, and all five linked files exist in references/ verbatim. The body keeps only core conventions inline and pushes deep detail out, matching the anchor-5 example.	5 / 5
	Total	17 / 20 Passed

Description

83%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 follows the good-example pattern closely: a concrete 'what' enumerating the convention areas, followed by an explicit 'Use when' clause with natural trigger terms including the file extension. Main gap is that the 'what' is one verb applied to topic categories rather than multiple distinct concrete actions, and a few natural synonyms (unit tests, test suite, bun test) are absent.

Dimension	Reasoning	Score
Specificity	"Apply Epicenter test-file conventions for setup, factories, Result assertions, type tests, naming, and pruning" lists six specific action areas matching the skill's coverage. Not a 5 because the actions are topic categories under one verb ('apply conventions for') rather than the distinct concrete verbs of the anchor-5 example ('extract text', 'fill forms', 'merge documents').	4 / 5
Completeness	Explicitly answers both: what ("Apply Epicenter test-file conventions for setup, factories, Result assertions, type tests, naming, and pruning") and when ("Use when writing, reviewing, deleting, or reorganizing tests, especially *.test.ts files") with concrete trigger phrases. Matches the anchor-5 example structure.	5 / 5
Trigger Term Quality	Natural phrases a user would say are present — "writing, reviewing, deleting, or reorganizing tests", "*.test.ts files" — plus the concrete library name 'wellcrafted'. Not a 5 because common synonyms like 'unit tests', 'test suite', 'bun test', or 'expect/it/test blocks' are missing.	4 / 5
Distinctiveness Conflict Risk	"Epicenter test-file conventions" carves a clear niche, and mentions of Result assertions/`wellcrafted` tie it to this repo's stack. Not a 5 because generic triggers like 'writing tests' or 'reviewing tests' could overlap with a general testing-conventions skill.	4 / 5
	Total	17 / 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: EpicenterHQ/epicenter
Path: .agents/skills/testing/SKILL.md
Commit: f9441c8

Reviewed: 3 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.