create-skill-test
Scaffolds eval.yaml evaluation specs for agent skills in the dotnet/skills repository. Use when creating skill tests, writing evaluation stimuli, defining graders and rubrics, sizing an eval for statistical power, or setting up test fixture files. Handles the Vally eval.yaml schema, fixture organization, and overfitting avoidance. Do not use for running or debugging existing evals (use improve-skill-quality) nor for skills authoring (use create-skill).
dotnet · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add dotnet/skills --skill create-skill-test技能说明
name: create-skill-test description: Scaffolds eval.yaml evaluation specs for agent skills in the dotnet/skills repository. Use when creating skill tests, writing evaluation stimuli, defining graders and rubrics, sizing an eval for statistical power, or setting up test fixture files. Handles the Vally eval.yaml schema, fixture organization, and overfitting avoidance. Do not use for running or debugging existing evals (use improve-skill-quality) nor for skills authoring (use create-skill).
Create Skill Test
Scaffold an evaluation spec (eval.yaml) for a skill or agent so it conforms to the Vally schema,
passes skill-validator check and check_eval_quality.py, is powerful enough to return a verdict,
and does not overfit to the skill's own wording.
When to Use
- Creating a new
eval.yamlfor a skill or agent - Adding stimuli to an existing eval
- Sizing an eval so the pass gate can actually be reached
- Setting up or repairing fixture files alongside an eval
- Reviewing whether rubric items and graders risk overfitting
When Not to Use
- Diagnosing a failing or regressed eval — use
improve-skill-quality - Modifying the skill-validator or the evaluation workflows
- Creating or editing
SKILL.mdfiles — usecreate-skill
Inputs
| Input | Required | Description |
|---|---|---|
| Skill or agent name | Yes | Must exist under plugins/<plugin>/skills/ or plugins/<plugin>/agents/ |
| Plugin name | Yes | e.g. dotnet-msbuild |
| Skill content | Yes | Read it — you cannot write non-overfitted rubric items without it |
| Failure modes to discriminate | Recommended | Each becomes one stimulus |
Workflow
Step 1: Locate the target and the test directory
tests/<plugin>/<skill-name>/eval.yaml # skills
tests/<plugin>/agent.<agent-name>/eval.yaml # agents (the agent. prefix disambiguates)
Verify the target exists at plugins/<plugin>/skills/<skill-name>/SKILL.md or
plugins/<plugin>/agents/<agent-name>.agent.md, and read it.
Agent evals sit outside the verdict flow. The canonical experiment declares
evals: tests/*/!(agent.*)/eval.yaml, so agent.* specs are excluded: no verdict is ever computed
for them, the stimulus floor does not apply, and ./eng/run-skill-evals.sh drops them even when you
name one explicitly (its --eval-filter is intersected with that glob). The distinct-stimulus
floor therefore applies to skill evals only. Author agent evals for the
scenario coverage and the deterministic graders, and run them as described in Step 10.
Be careful with a skill that sets disable-model-invocation: true. The model cannot invoke it,
so the skill is absent from the model-facing skilled arm and any direct eval compares two identical
arms. Answer-content graders do not create a difference between those arms. The honest coverage for
such skills is dependency-level — through the outcome evals of the skills that load them, and through
the plugin arm. For example, filter-syntax is covered by the filtered-command scenarios in
tests/dotnet-test/run-tests/eval.yaml.
Step 2: Write the spec skeleton
The spec is Vally format. Every eval in this repo uses stimuli: and graders:; scenarios: and
assertions: are a pre-Vally format that no longer loads.
name: <skill-name>
description: Evaluates the <plugin>/<skill-name> skill
type: capability
defaults:
timeout: 5m
runs: 1
stimuli:
- name: <what the agent must accomplish>
prompt: <natural developer request>
environment:
files:
- src: fixtures/<case>/Project.csproj
dest: Project.csproj
graders:
- type: output-matches
config:
pattern: (root cause|underlying issue)
- type: exit-success
- type: prompt
rubric:
- <outcome the agent should have reached>
defaults:replacesconfig:— it does not join it.configis a deprecated alias for the same block and vally throws on a spec declaring both. Some existing evals still open withconfig:; when you change settings, replace it with onedefaults:block. The failure is invisible otherwise: the job exits 0 with no verdicts and the PR comment blames "transient infrastructure".
Step 3: Size the eval for power before writing content
The gate gives each distinct stimulus one vote. Repeated runs for one stimulus collapse to one majority-direction vote and remain available as reliability evidence.
- Distinct stimuli ≥ 5, else the verdict is
underpowered— never a pass, never a regression. - p ≤ 0.05 on an exact one-sided sign test over discordant (non-tie) stimulus votes. Ties are not discarded; they hold the discordant count down.
| discordant stimulus votes | records that pass | p |
|---|---|---|
| ≤ 4 | none | ≥ 0.0625 |
| 5–7 | zero losses only (5W/0L) | 0.031 |
| 8 | one loss survivable (7W/1L) | 0.035 |
At exactly 5 stimuli, one tie is fatal because it leaves 4 discordant votes. At 6 stimuli one tie is survivable; at 7, up to two are. A loss is not. Five is an eligibility floor, not adequate power. For example, 80% power needs 8 discordant votes only for a true 90% conditional win rate; it needs 18 at 80%, 37 at 70%, and 158 at 60%. Size for the effect and tie rate you need to detect.
Use runs for reliability, not task breadth. Vally recommends 3 runs in CI and 5–10 nightly for
pass rate, pass@k, pass^k, and flakiness. Extra runs never clear the five-stimulus floor.
Do not set runs in dotnet-skills.experiment.yaml; experiment overrides overwrite every eval's
own value rather than defaulting it.
Step 4: Write stimuli
- Name describes what is tested, not how.
- Prompt is a natural developer request. Never mention the skill, the agent, or its vocabulary — cued prompts inflate the overfit score and bias the baseline.
- Each stimulus should discriminate a different property of the skill. Five stimuli covering one propert