Vally Tests

MicrosoftOfficialPublished by Microsoft

Skill
Workflow
Agent tooling
MIT
Low risk
Has scripts

From the author

Authors Vally conformance tests for prompts, instructions, agents, and skills, and refuses jailbreak, prompt-injection, harmful-elicitation, TOS, CoC, and PII-extraction stimuli

— the description by Microsoft

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The vally-tests skill provides a structured workflow for authoring conformance tests for various AI artifacts, including prompts, instructions, agents, and skills. It operates by mapping artifact behaviors to specific Vally grader types, ensuring that tests are both relevant and robust. The skill includes a safety refusal taxonomy to prevent the generation of adversarial or harmful stimuli, and it supports both individual artifact processing and batch processing via corpus imports.

What it does

Authors conformance test stimuli for prompts, instructions, agents, and skills.
Routes test stimuli to appropriate Vally evaluation files based on artifact kind.
Enforces a safety refusal taxonomy to block adversarial or policy-violating content.
Performs deduplication of stimuli using SHA-256 hashing of normalized prompt text.
Supports batch processing of test stimuli via CSV or XLSX corpus imports.
Generates JSON run reports detailing the outcome of the authoring process.

When to use it

When you need to create conformance tests for a new prompt, instruction, agent, or skill.
When you have a batch of behaviors that require standardized formatting and deduplication.
When you need to ensure that authored test stimuli comply with predefined safety and refusal policies.
When you are working within a Vally-based evaluation environment.

Advantages

Automates the creation of consistent and structured test stimuli.
Prevents the accidental inclusion of harmful or prohibited content through a built-in safety taxonomy.
Ensures test uniqueness through automated deduplication.
Provides clear routing to the correct evaluation suites for different artifact types.

Usage examples

“vally-tests mode=from-artifact files=my-agent.agent.md”: The skill analyzes my-agent.agent.md, selects appropriate conformance checks, and appends the generated stimuli to the corresponding Vally eval file.
“vally-tests mode=corpus-import path=tests.csv”: The skill processes each row in the provided CSV, generates the corresponding stimulus blocks, and appends them to the routed eval file after deduplication.

Install

Download the skill as a ZIP:
https://autogineer.com/agent-skills/microsoft/vally-tests/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip vally-tests.zip -d .agents/skills

Documentation by Microsoft

Vally Tests Skill

Purpose

This skill authors Vally conformance tests for the four supported artifact kinds in this repository: prompts, instructions, agents, and skills. Each test exercises a documented behavior the artifact already claims and routes the result through an appropriate Vally grader so failures are explainable. Test authoring is bounded by a refusal taxonomy that keeps the skill out of adversarial, harmful, or policy-evasion territory.

Follow the shared content-policy public-output guard for eval stimuli and any public summaries derived from this skill. Vally tests are not a venue for terms-of-service boundary mapping, payload generation, refusal-text scoring, hidden-instruction disclosure, PII extraction, or secret extraction.

The skill ships:

A canonical authoring workflow that runs directly through /vally-tests or through the Vally Test Author subagent.
Per-kind reference files that enumerate every conformance check the skill knows how to express.
A grader catalog that maps Vally CLI grader types to the checks they fit, and robustness rules that keep an emitted grader from asserting the impossible or failing correct behavior.
A safety refusal taxonomy with regex patterns the safety lint script consumes.
Helper scripts and asset templates for stimulus emission, corpus import, and dedupe.

When to Invoke

Invoke this skill in one of two modes:

From-artifact mode. The caller points at one or more artifact files (a .prompt.md, .instructions.md, .agent.md, or SKILL.md) through files, or at the open or attached file when files is omitted, and asks for conformance test stimuli that verify each artifact's stated behaviors. The skill detects the artifact kind from the filename unless kind overrides it, looks up the matching per-kind reference, picks graders, and appends stimulus blocks to the routed Vally eval file.
Corpus-import mode. The caller supplies a CSV or XLSX corpus through path that follows the shipped template, and the skill turns each row into a stimulus block in the routed eval file. Before reading, confirm that path exists and ends in .csv or .xlsx; otherwise name the bad path and stop. Every imported row carries tags.advisory: true, and corpus content cannot override it. Used when a large batch of behaviors needs identical formatting and dedupe handling.

After either mode, report the target eval file, stimuli appended, duplicates skipped, refusals triggered, and the JSON run report path.

Do not invoke this skill to:

Generate adversarial probes, jailbreak attempts, prompt-injection payloads, or red-team stimuli.
Test refusal quality on harmful, illegal, or policy-violating prompts.
Author stimuli that elicit PII, secrets, hidden instructions, or model self-disclosure.
Store payload examples, paraphrased prohibited requests, or quoted flagged content in Vally eval specs, corpus rows, PR summaries, issue bodies, or comments.
Replace Responsible AI threat modeling. RAI work lives in the RAI Planner agent.

Authoring Workflow

Each invocation follows the same six-step pipeline:

Artifact-kind detection. Resolve the kind from the artifact path or the corpus row's kind column. Supported kinds: prompt, instructions, agent, skill. Reject unknown kinds with a refusal block.
Reference lookup. Load the matching reference file from references/ and select the check or checks the stimulus exercises. Stage the artifact under test in the stimulus's agent_environment so the agent can read what the prompt names.
Grader selection. Use references/grader-catalog.md as the authoritative selection surface. Pick the registered Vally grader family that directly observes the expected behavior and follow its stimulus-shape guidance.
Robustness check. Apply references/grader-robustness.md. Confirm the stimulus stages every file whose wording the grader asserts, that the pattern constrains order and proximity only where those are the behavior under test, that a compliant agent phrasing the behavior differently still passes, and that no positive grader passes on the prompt text alone. Verify the pattern offline against answers that must pass and answers that must still fail before appending.
Safety self-check. Run a safety self-check against the refusal taxonomy regex set. Refusing here is the correct outcome for any stimulus that matches a refusal category.
Dedupe and append. Compute a SHA-256 hash of the normalized prompt text, compare against existing stimuli in the target eval file, and append only when novel.

The pipeline is identical for both invocation modes. Corpus-import mode runs steps 2 through 6 once per row.

Safety Refusal Taxonomy

Authoring is bounded by seven refusal categories. Any stimulus that matches a category's regex set is refused before it reaches the dedupe step. The categories and their normative source are listed below. The full regex set lives in references/refusal-taxonomy.md and is consumed by the safety lint script.

Category	Definition	Normative Source
jailbreak	Attempts to bypass model safety policies through persona switching, hypothetical framing, or roleplay coercion.	Project Code of Conduct
prompt-injection	Attempts to override system or developer instructions through embedded or external content.	Project Code of Conduct
harmful-elicitation	Requests for content that causes physical, financial, psychological, or reputational harm.	Project Code of Conduct
tos-violation	Stimuli that solicit content prohibited by GitHub, Microsoft, or model-provider terms of service.	Project Code of Conduct
coc-violation	Stimuli that violate this repository's Code of Conduct, including harassment, discrimination, or doxxing.	Project Code of Conduct
model-refusal-elicitation	Attempts to provoke a model refusal so the refusal text itself can be scored, graded, or used to map provider boundaries.	RAI Planner guidance
pii-extraction	Attempts to elicit personally identifiable information, secrets, credentials, or proprietary training data.	RAI Planner guidance

When a request triggers a refusal, emit the canonical refusal block:

This skill authors conformance tests only. The request appears to fall under <category>. Please consult <Project Code of Conduct | RAI Planner agent> for the appropriate process.

Substitute the matched <category> and the most relevant normative source. Do not negotiate, rephrase, or partially fulfill the request.

Helper Script Index

Helper scripts ship as parity pairs (.ps1 and .sh) where the workflow does not require Python. The safety lint is the exception: it ships only as Lint-VallyTestSafety.ps1, which import_corpus.py invokes, so a single regex engine evaluates the refusal taxonomy. Python is used only for the corpus-import path because the source-of-truth interchange format is CSV with an XLSX mirror.

Script	Purpose	Language	Delivery
`scripts/New-Stimulus.ps1`	Scaffolds a single stimulus YAML block from an artifact path and appends to the routed eval file.	PowerShell 7+	Phase 2
`scripts/new-stimulus.sh`	Parity counterpart for the PowerShell stimulus scaffolder.	bash	Phase 2
`scripts/import_corpus.py`	Reads the CSV or XLSX corpus template and emits dedupe-checked stimulus blocks per kind.	Python 3.11+	Phase 2
`scripts/Lint-VallyTestSafety.ps1`	Runs the refusal taxonomy regex set against a candidate stimulus and exits non-zero on match.	PowerShell 7+	Phase 3

All helpers honour a shared dedupe contract: SHA-256 of the prompt text after Unicode NFC normalization and whitespace collapse.

The helpers emit a JSON run report to logs/vally-test-author-<timestamp>.json, where <timestamp> is YYYYMMDD-HHMMSS (UTC). The report captures, at minimum: mode; inputs (the resolved files/path and kind); target_eval_file; stimuli_appended (count and per-row hash); dedupe_results (count and per-row hash for skipped duplicates); refusal_check (per-row category match, if any); safety_lint_exit_code; blockers (any ambiguous safety-lint outcomes surfaced for review); and written_paths.

Reference Index

References capture the conformance taxonomy, grader selection rules, eval-suite routing, and the regex source of truth for the refusal taxonomy. Each file targets a specific decision point in the authoring workflow.

Reference	Covers
prompts.md	The 12 conformance checks emitted for `.prompt.md` artifacts.
instructions.md	The 8 conformance checks emitted for `.instructions.md` artifacts.
agents.md	The 9 conformance checks emitted for `.agent.md` artifacts.
skills.md	The 9 conformance checks emitted for `SKILL.md` artifacts.
grader-catalog.md	Vally CLI grader types, selection rules, and gotchas.
grader-robustness.md	Mounting, order and proximity limits, negation guards, prompt-echo checks, and the pre-commit probe.
refusal-taxonomy.md	Regex source of truth for the 7 refusal categories and worked examples.
eval-suite-routing.md	Maps artifact kind to the canonical Vally eval file under `evals/`.

Asset Index

Assets supply the interchange formats the corpus-import path consumes. The CSV is the source of truth. The XLSX mirror is regenerated from the CSV by import_corpus.py and is never edited directly.

Asset	Purpose
`assets/corpus-import-template.csv`	Canonical CSV template with header `prompt,kind,target_artifact,grader,tags,expected_refusal_category,notes`.
`assets/corpus-import-template.xlsx`	Excel mirror of the CSV regenerated by the import script.

Output Targets per Kind

Authored stimuli always land in one of the routed Vally eval files. The router is encoded in references/eval-suite-routing.md and mirrored here for quick lookup.

Kind	Target Eval File	Vally Suite Name
prompt	`evals/behavior-conformance/prompts.eval.yaml`	behavior-conformance
instructions	`evals/behavior-conformance/instructions.eval.yaml`	behavior-conformance
agent	`evals/agent-behavior/eval.yaml`	agent-behavior
skill	`evals/behavior-conformance/skill-behavior.eval.yaml`	behavior-conformance

The prompt target is created on first use when a repository has no prompt stimuli yet.

Never write to evals/baseline-equivalence/, evals/script-validation/, or evals/results/ from this skill. Those targets serve baseline equivalence, script validation, and historical comparison flows that are out of scope for conformance authoring.

Contributing

Follow these conventions when extending this skill:

New per-kind checks belong in the matching references/{kind}.md file. Bump the check count in this SKILL.md when the reference adds or removes checks.
New grader types belong in references/grader-catalog.md and only after the matching Vally CLI version is pinned in package.json devDependencies.
New refusal categories require updates to references/refusal-taxonomy.md, the regex set the safety lint script consumes, the Safety Refusal Taxonomy table above, and the canonical refusal block.
Helper scripts must ship in parity pairs (.ps1 and .sh) unless the workflow has a hard Python dependency. The safety lint is the one exception and ships only as Lint-VallyTestSafety.ps1; do not add a bash mirror. Python helpers live under scripts/ and are configured by the skill's pyproject.toml.

Files

ATTRIBUTION.mdAdded by AutoGineer827 B
LICENSELicence file added by AutoGineer1.1 KiB
SKILL.md14.2 KiB
assets/.gitkeep0 B
assets/corpus-import-template.csv923 B
assets/corpus-import-template.xlsx136.0 KiB
assets/grader-template.yml1.9 KiB
assets/stimulus-template.yml2.0 KiB
pyproject.toml577 B
references/agents.md16.3 KiB
references/eval-suite-routing.md6.9 KiB
references/grader-catalog.md30.5 KiB
references/grader-robustness.md8.6 KiB
references/instructions.md8.9 KiB
references/prompts.md11.8 KiB
references/refusal-taxonomy.md12.5 KiB
references/skills.md10.9 KiB
scripts/Lint-VallyTestSafety.ps1Script4.1 KiB
scripts/New-Stimulus.ps1Script6.3 KiB
scripts/Select-Grader.ps1Script3.1 KiB
scripts/import_corpus.pyScript14.9 KiB
scripts/new-stimulus.shScript5.3 KiB
scripts/select-grader.shScript2.8 KiB
tests/Lint-VallyTestSafety.Tests.ps1Script4.0 KiB
tests/New-Stimulus.Tests.ps1Script11.3 KiB
tests/Select-Grader.Tests.ps1Script2.6 KiB
tests/__init__.pyScript139 B
tests/corpus/0_normalize_prompt19 B
tests/corpus/1_hash_prompt24 B
tests/corpus/2_validate_row77 B
tests/corpus/3_build_patch_entry63 B
tests/corpus/4_load_existing_hashes75 B
tests/corpus/README.md1.3 KiB
tests/fuzz_harness.pyScript6.9 KiB
tests/test_import_corpus.pyScript12.3 KiB
tests/test_lint_safety.pyScript3.6 KiB
uv.lock73.5 KiB

references/skills.md

title: Skills Conformance Checks description: Nine conformance checks the vally-tests skill emits for SKILL.md artifacts, with contract citations, stimulus shapes, and Vally grader recommendations

Skills Conformance Checks

Overview

This reference enumerates the nine conformance checks the vally-tests skill knows how to express for SKILL.md artifacts. Skill contracts emphasize the metadata that drives semantic invocation, the structure that supports progressive disclosure, and the portability constraints that let a skill move between in-repo, extension, and plugin distribution contexts.

The canonical eval target for this kind, per eval-suite-routing.md, is evals/behavior-conformance/skill-behavior.eval.yaml. New stimulus blocks are appended to its stimuli: array, tagged tags.advisory: true, and labeled with tags.skill: <skill-slug> and tags.shape: knowledge | tool-trigger | bleed-detection. The DR-03 fallback to evals/skill-quality/eval.yaml applies when the primary target is absent at consumption time; a fallback append carries a leading YAML comment # Deferred cutover per DR-03; see WI-12. per eval-suite-routing.md. Authors MUST run every candidate stimulus through refusal-taxonomy.md before emission and refuse any match.

Grader identifiers below use the Vally CLI 0.9.0 catalog (semantic_similarity, contains, regex, json_schema) per grader-catalog.md. Where the research phrasing recommended output-matches, the equivalent here is regex; where it recommended llm-grader, the equivalent is semantic_similarity.

Contract Summary

Topic	Section in hve-builder.instructions.md
Frontmatter and name	Frontmatter and Portability
File location and portability	Frontmatter and Portability
Optional subdirectories	Keep Context Focused
Content sections	Outcome and Structure
Progressive disclosure	Keep Context Focused
Semantic invocation	Frontmatter and Portability; Choose Artifacts by Responsibility

Conformance Checks

Check 1: Required Frontmatter Fields

Contract source: hve-builder.instructions.md, Frontmatter and Portability.
Testable behavior: SKILL.md frontmatter MUST include a name: field in lowercase kebab-case AND a concise, non-empty description: field (aim near 120 characters; modest overage is acceptable when it improves routing clarity).
Suggested stimulus: ask the assistant to identify a named skill by its frontmatter name: and description: values.
Grader recommendation: regex with pattern (?m)^name:\s*['"]?[a-z0-9][a-z0-9-]*['"]? combined with (?m)^description:\s*['"].{1,200}.
Evidence: .github/skills/experimental/vscode-playwright/SKILL.md L1-L7 demonstrates the required metadata pair.

Check 2: Name Matches Directory

Contract source: hve-builder.instructions.md, Frontmatter and Portability.
Testable behavior: the name: frontmatter value MUST equal the skill's directory name in lowercase kebab-case (for example a skill at .github/skills/hve-core/vally-tests/ MUST declare name: vally-tests).
Suggested stimulus: ask the assistant where on disk a named skill lives and to confirm that the directory matches the frontmatter name.
Grader recommendation: semantic_similarity with rubric "Does the skill's frontmatter name field equal the final segment of its directory path in lowercase kebab-case?".
Evidence: .github/skills/experimental/vscode-playwright/SKILL.md L1 declares name: vscode-playwright matching the directory.

Check 4: H1 Title Matches Skill Purpose

Contract source: hve-builder.instructions.md, Outcome and Structure.
Testable behavior: the SKILL.md H1 heading MUST state the skill's purpose clearly and SHOULD align in intent with the description: frontmatter.
Suggested stimulus: ask the assistant to summarize a named skill in one sentence and compare against the H1 heading.
Grader recommendation: semantic_similarity with rubric "Does the SKILL.md H1 heading describe the skill's purpose in a way that aligns with the description frontmatter?".
Evidence: .github/skills/experimental/vscode-playwright/SKILL.md L10-L11 carries an H1 that matches the description's intent.

Check 5: Required Content Sections

Contract source: hve-builder.instructions.md, Outcome and Structure.
Testable behavior: a playbook-style skill that delegates execution to subagents MUST present its sections in the order Title (H1), Goal, Flow (or Execution), Inputs, Success criteria, Constraints, Stop rules, Handoff, and an optional response contract; a script-bearing skill MAY instead use the legacy script-oriented order (Overview, Prerequisites, Quick Start, or Architecture plus Workflow Steps, then Parameters Reference or Troubleshooting).
Suggested stimulus: ask the assistant to list the section headings of a named skill in order and confirm they follow the playbook shape for a delegating skill or the script-oriented shape for a script-bearing skill.
Grader recommendation: semantic_similarity with rubric "For a delegating playbook skill, do the section headings follow the playbook order (Goal, Flow, Inputs, Success criteria, Constraints, Stop rules, Handoff); for a script-bearing skill, do they follow the Overview/Prerequisites/Quick Start order?".
Evidence: a playbook-style skill such as .github/skills/engagement-reporting/engagement-reporting/SKILL.md exhibits the Goal/Flow/Inputs/Success-criteria/Constraints/Stop-rules/Handoff order.

Check 6: Relative Path Portability

Contract source: hve-builder.instructions.md, Frontmatter and Portability.
Testable behavior: operational file references within SKILL.md MUST be portable in distributed contexts. Bundled resources use skill-root-relative paths, packaged instruction directives use source-relative paths, and cross-artifact dependencies use stable artifact or skill names. Operational workspace-root .github/ references are non-conforming; descriptive repository-shape examples and valid runtime values such as slash commands, API routes, installation destinations, and temporary-file paths are not source-tree references.
Suggested stimulus: ask the assistant to enumerate operational file references inside a named skill's SKILL.md, explain how each resolves after distribution, and distinguish them from commands, routes, destinations, and descriptive examples.
Grader recommendation: semantic_similarity with rubric "Do operational file references avoid workspace-root source-tree assumptions, use the portable reference form for their target, and avoid misclassifying valid runtime slash-prefixed values as source-tree paths?". Use npm run lint:artifact-portability for deterministic source-tree path enforcement; do not apply a blanket absolute-path regex.
Evidence: .github/skills/experimental/vscode-playwright/SKILL.md references bundled resources by skill-root-relative paths, while the artifact-portability validator rejects operational workspace-root .github/ references across distributed runtime Markdown.

Check 7: Progressive Disclosure Structure

Contract source: hve-builder.instructions.md, Keep Context Focused.
Testable behavior: SKILL.md SHOULD respect progressive disclosure: frontmatter holds metadata of roughly 100 tokens, the body holds activation instructions of under 5000 tokens, and large or domain-specific resources live in references/, scripts/, or assets/ subdirectories rather than inline.
Suggested stimulus: ask the assistant whether a named skill keeps its SKILL.md body within the activation budget and which subdirectories it uses for on-demand resources.
Grader recommendation: semantic_similarity with rubric "Does the skill follow progressive disclosure, with a focused SKILL.md body under the activation budget and large references moved to separate files?".
Evidence: .github/skills/hve-core/vally-tests/SKILL.md body delegates regex sets and routing tables to files under references/.

Check 8: Script Parity for Cross-Platform Helpers

Contract source: hve-builder.instructions.md, Keep Context Focused.
Testable behavior: when a skill ships executable helpers, the helpers SHOULD be provided in parity pairs of a bash (.sh) implementation and a PowerShell (.ps1) implementation, unless the workflow requires Python.
Suggested stimulus: ask the assistant which helper scripts a named skill ships and whether each non-Python script has both bash and PowerShell forms.
Grader recommendation: semantic_similarity with rubric "If the skill ships non-Python helpers, does each helper appear in both .sh and .ps1 forms for cross-platform parity?".
Evidence: skills under .github/skills/ consistently pair .sh and .ps1 helpers for cross-platform helpers.

Check 9: Troubleshooting Section

Contract source: hve-builder.instructions.md, Outcome and Structure.
Testable behavior: SKILL.md SHOULD include a Troubleshooting section that documents common failure modes and their resolutions, or that explicitly states no common issues exist.
Suggested stimulus: ask the assistant which common issues a named skill calls out under Troubleshooting and what the recommended fix is for each.
Grader recommendation: regex with pattern (?m)^##\s+Troubleshooting\b.
Evidence: the .github/skills/experimental/vscode-playwright/ skill exposes a Troubleshooting section in line with the convention.

Check 10: Semantic Invocation Alignment

Contract source: hve-builder.instructions.md, Frontmatter and Portability and Choose Artifacts by Responsibility.
Testable behavior: the description: frontmatter MUST be domain-specific enough that natural-language task descriptions matching the skill's domain (for example "extract VS Code screenshots") semantically correlate with the declared description.
Suggested stimulus: present several phrasings of a task in the skill's domain and ask the assistant whether the named skill is the right choice for each, with justification.
Grader recommendation: semantic_similarity with rubric "Is the skill's description specific and domain-focused enough that natural-language task phrasings in the domain semantically match the description?".
Evidence: .github/skills/experimental/vscode-playwright/SKILL.md L2 carries a domain-specific description that pairs VS Code and Playwright.

Cross-References

Skill index: SKILL.md.
Grader catalog and selection rules: grader-catalog.md.
Refusal categories and regex source of truth: refusal-taxonomy.md.
Eval target routing for skill kind (primary plus DR-03 fallback): eval-suite-routing.md.

Requirements and compatibility

Written for: GitHub Copilot, Claude Code

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Claude Code frontmatter, Needs Python

The author says: Requires Vally CLI 0.15.0+, PowerShell 7+, bash, and Python 3.11+ with uv for corpus-import workflows

Security

What our scanner noticed· Low risk

Scripts that your agent may run

This skill includes scripts that your agent may run. Read them before you use it.

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by

Microsoft

Publisher

Microsoft (Official)

Source

microsoft/hve-core · .github/skills/hve-core/vally-tests · commit f425e94

Licence

MIT License (redistribution allowed)

LICENSE (added by AutoGineer from LICENSE)
ATTRIBUTION.md (written by AutoGineer)

Synced

2026-11-09

AutoGineer is not affiliated with or endorsed by Microsoft or Microsoft.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download vally-tests.zip