BC unit-tests
Use when writing, reviewing, speeding up, or fixing a flaky `bun test` unit test in any package (core, cli, server, ai, codemode, util, client, sdk, plugin, http-recorder, merman, app src and test-browser, desktop, gui-extensions, ui, session-ui, latex, ...), except OpenTUI renderer tests (see tui-tests). Also use when a test "timed out after 5000ms" on Windows CI, fails only on Windows, when the unit job is slow, when adding cli subprocess or service tests, or when adding a package's test task to turbo.json. Covers controlling time instead of sleeping, per-test timeouts, process and git spawn cost on Windows, Windows-only failures, temp dirs and process state, leaks between files, and reading CI timeouts.
A skill for debugging unit tests in bun test: helps accelerate, fix, and handle flaky tests across any package in the project. Promises solutions for Windows timeouts, inter-file leaks, process and git spawn issues. The files contain 5375 instruction tokens with no critical errors, graded B with quality_score 74 and process_score 55. That means: basic logic is there, but process coverage is incomplete. In practice, you get a working guide for typical cases (sleep vs time control, per-test timeout, Windows CI failures), but edge cases require improvisation. Supports all major AI platforms without restrictions. Install if your project regularly breaks tests on Windows or you need a bun test reference—otherwise too narrow.
Use when writing, reviewing, speeding up, or fixing a flaky bun test unit test in any package (core, cli, server, ai, codemode, util, client, sdk, plugin…
As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions
The same skill appears in 1 more place: opencode
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5447 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 55/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, git) that frontmatter does not declare
- 70Execution cost. Instruction body is 5447 tokens
- 100Steps. 84 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 715: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 84 items
- +4Has examples (0 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.