SkillAgentSearch skills...

create-skill-test

Scaffolds eval.yaml evaluation specs for skills, custom agents, and redistributable gh-aw workflow packages in the dotnet/skills repository

Install / Use

npx skills add dotnet/skills --skill create-skill-test

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

96/100

Category

Automation

Supported Platforms

Universal

Our assessment of create-skill-test

create-skill-test scores 96/100 on our quality scale, 227th of 2,790 Automation skills we index (top 9%).

Its SKILL.md is 17 KB long, well organised into 17 sections with 9 code examples: a thorough specification that gives an agent plenty to work with.

With 5,471 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
30/30
Structure
20/20
Description
15/15
Adoption
16/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so create-skill-test is actively maintained.
  • Our last check on 2026-11-15 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-09-27. Automated pattern scan on 2026-09-27. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

create-skill-test compared with similar skills

All 4 of these similar skills score higher than create-skill-test; compare them before choosing.

SkillScoreStarsUpdatedFormat
create-skill-test (this skill)by dotnet965.5k53d agoSKILL.md
Agent-Reachby Panniantong100112.3k8d agoCLAUDE.md
rufloby ruvnet10081.9ktodayCLAUDE.md
Claude-Code-Game-Studiosby Donchitos10039.7k7d agoCLAUDE.md
Scraplingby D4Vinci100103.6k2d agoMCP Server

Frequently asked questions

How do I install create-skill-test?
Run npx skills add dotnet/skills --skill create-skill-test. The install tabs above show the steps for each supported agent.
Which AI agents does create-skill-test work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is create-skill-test safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is create-skill-test still maintained?
The repository was last updated about 2 months ago, so create-skill-test is actively maintained.

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.yaml for 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.md files — use create-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 use the native SDK agent lane. Vally 0.14 cannot register custom agents, so agent.* specs do not run through the skill experiment. The evaluation workflow discovers them separately, runs the target agent through skill-validator evaluate, and adapts that evidence into the same schema-versioned result and dashboard pipeline. The distinct-stimulus floor applies to both skill and agent evals.

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: replaces config: — it does not join it. config is a deprecated alias for the same block and vally throws on a spec declaring both. Some existing evals still open with config:; when you change settings, replace it with one defaults: 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.

  1. Distinct stimuli ≥ 5, else the verdict is underpowered — never a pass, never a regression.
  2. 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 property give arithmetic, not evidence.
  • Give every stimulus a stable, unique name. Vally pairs comparison trajectories by (stimulus name, trial index); duplicate names make slot identity ambiguous.
  • Include a boundary / no-op stimulus for any skill that migrates or rewrites code, proving it leaves already-correct input alone.

Step 5: Configure the environment

environment:
  files:
    - src: fixtures/broken-build/App.csproj      # path relative to eval.yaml
      dest: App.csproj                           # path in the agent's working directory
    - src: fixtures/broken-build                 # a directory
      dest: .
  commands:
    - dotnet build -bl || exit 0                 # guard intentional failures

Do not set environment.skills in a skill eval. The experiment declares vary: /environment/skills and supplies the value itself — [] for the baseline arm and plugins/<plugin>/skills/<skill> for the skilled arm — so anything the eval declares is replaced, in every arm. It cannot add a skill to one arm only. environment.skills is meaningful in an agent.* eval; the native agent lane loads those entries only in the isolated target run, while the plugin run loads the production plugin's complete skill surface. Copy the shape from an existing agent eval such as tests/dotnet-test/agent.test-quality-auditor/eval.yaml rather than reproducing a remembered form — the specs in this repo are not consistent about how they spell those entries.

Fixture rules — each one has already cost a real result:

  • Every referenced fixture must be tracked by git. .gitignore (e.g. coverage*.xml) has silently swallowed a committed fixture: the eval passed locally and failed at setup in CI. Verify with git ls-files, not by looking at the working tree.
  • Every fixture must behave as its stimulus assumes. A fixture meant to be healthy must build; a fixture meant to be broken must fail for the exact reason the stimulus is about, and no other. Judges penalize agents for unrelated "pre-existing build issues" that the fixture author introduced.
  • Every fixture must reproduce the bug its stimulus is named for. If it does not, the baseline scores well and the skill has nothing to add.
  • Coverage fixtures must be internally consistent. A Cobertura report whose declared line-rate, summary totals (lines-covered/lines-valid), and <line> elements disagree lets the two arms read different truths, and the loss is the fixture's fault. Update any rubric item or prompt that quotes a figure in the same change.
  • Do not wire duplicate fixtures to raise n; rename leftovers add trials without evidence.
  • A setup command that is expected to fail while still producing its artifact must be guarded (|| exit 0), or vally drops the trial.
  • A cleanup command that strips sources must skip directories containing SKILL.md — the staged skill lives there, and deleting it aborts only the skilled arm.

Step 6: Write graders

Graders are hard pass/fail checks evaluated on every arm.

| Type | Required config | Purpose | |------|-----------------|---------| | output-matches / output-not-matches | pattern | Regex over agent output | | output-contains / output-not-contains | substring | Literal text in output | | file-exists / file-not-exists | path | Glob against the work directory | | file-contains / file-not-contains | path, value | Content of a produced file | | run-command | command (plus optional expected_exit_code, timeout, stdout_matches) | Verify produced code actually builds/runs | | exit-success | — | Agent produced non-empty output | | prompt | — | Runs the LLM judge against the rubric |

Rules:

  • A grader whose config is absent or missing its required key parses fine and enforces nothing. The usual cause is an indentation slip during an edit; check_eval_quality.py blocks it.
  • Prefer broad patterns that several valid approaches satisfy: (root cause|primary error|underlying issue).
  • If the skill mandates an output shape, assert on it. A skill required to emit a decisive Recommendation: line can silently stop doing so while the eval still passes.
  • Use file-not-contains / file-not-exists to prove the agent avoided an incorrect action.

Step 7: Write rubric items

Rubric items are judged pairwise (baseline vs. skilled). The overfitting judge classifies each item:

| Classification | Description | Goal | |---------------|-------------|------| | outcome | Whether the agent reached a correct result — WHAT, not HOW | Target this | | technique | Whether the agent used a skill-specific procedure | Minimize | | vocabulary | Whether the agent used the skill's terminology | Avoid |

  1. Test outcomes, not methods: "Identified the root cause of the build failure", not "Replayed the binlog using dotnet build /flp".
  2. Accept any valid approach.
  3. Never reference the skill by name, and never reuse SKILL.md phrasing.
  4. Never reward using the skill — the harness reports activation separately, so a rubric item that does this measures nothing and inflates the overfit score.
  5. Do not test knowledge the model already has; it adds no delta.
  6. Keep each item independently evaluable.
  7. Do not reward raw volume (test count, report length); judges will compare it when both arms act.

Good:

rubric:
  - Correctly identified the missing NuGet package as the root cause of the build failure
  - Recognized that downstream failures cascaded from that root cause
  - Suggested a concrete fix that resolves it

Overfitted:

rubric:
  - Replayed the binary log using 'dotnet build /flp:v=diag'   # technique
  - Measured cold, warm, and no-op build scenarios             # vocabulary
  - Used the template-comparison skill                         # rewards activation

Step 8: Add constraints sparingly

constraints:
  expect_tools: [bash]
  reject_tools: [edit, create]
  reject_skills: [some-skill]
  • expect_tools: [bash] on an advisory question f

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars5.5k
CategoryAutomation
Updated1mo ago
Forks418

Languages

C#

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions