CD write-sglang-test
Guide for writing SGLang CI/UT tests. Covers CustomTestCase, CI registration, server fixtures, model selection, mock testing, and test placement. Always read test/README.md for the full CI layout, how to run tests, and extra tips. Use when creating new tests, adding CI test cases, writing unit tests, or when the user asks to add tests for SGLang features.
Guide for writing SGLang CI/UT tests.
As a process D 35/100 · Unfinished process — References files that are not bundled: ../kernel-organization/SKILL.md, ../ci-workflow-guide/SKILL.md, ../../rules/unit-test-admission.md
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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 ≈ 5142 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: ../kernel-organization/SKILL.md - warning
missing-refreference to a missing file: ../ci-workflow-guide/SKILL.md - warning
missing-refreference to a missing file: ../../rules/unit-test-admission.md - warning
missing-refreference to a missing file: scripts/ci/runner_configs.yml - note
edit-residuethe text marks something as outdated (lines 73, 323, 324, 389): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 35/100
- 0Tools and files. 4 referenced file(s) missing: ../kernel-organization/SKILL.md, ../ci-workflow-guide/SKILL.md, ../../rules/unit-test-admission.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 5 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 5142 tokens
- 85Steps. 40 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- low The response is described with custom markup (16 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 357: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 40 items
- +4Has examples (12 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.