Automated summary
Pairs requirements and issue acceptance criteria with acceptance-level validation, closing the top of the V cycle for a feature or release slice.
Strengths
- Maps every acceptance criterion to a concrete validation method: automated check, scripted test, manual checklist, or monitored metric
- Enforces testable acceptance criteria, ideally with copy-pasteable steps
- Reuses validation drafting and detailing skills to derive scenarios once behaviour is known
- Suggests forward references to existing requirement clauses instead of duplicating prose
Limitations
- Assumes well-formed requirements and acceptance criteria already exist upstream
- Provides no automation tooling; executing the validations is still manual work
- Of little use outside a requirements-driven workflow or when no requirements documentation exists
Use when writing or refining an issue so each acceptance criterion maps to observable evidence, or when preparing a stakeholder demo, UAT, or audit trail.
Avoid for exploratory tasks or one-off fixes with no formalized requirements or acceptance criteria to validate.
Security analysis
SafeThis is a documentation-only process skill with no declared tools or executable instructions. It describes linking requirements to acceptance criteria and validation methods, with no destructive, exfiltration, obfuscation, or safety-disabling behavior.
No concerns found
How this analysis is madeExamples
Take the acceptance criteria in issue #142 and, for each one, name the validation method (automated test, scripted check, manual checklist, or metric) and flag any criterion that isn't testable yet.Review our feature ticket and rewrite vague acceptance criteria like 'works well' into measurable or binary checks, keeping a single canonical statement of intent and linking to the requirements doc instead of copying it.Build the acceptance-level validation plan for the current release slice: list each goal from the requirements doc, its linked acceptance criteria, and the evidence we'll show stakeholders during UAT.name: v-model-requirements-acceptance description: Pairs requirements and issue acceptance criteria with acceptance-level validation. Use when closing the top of the V for a feature or release slice. Third person.
V-model: requirements ↔ acceptance
Links left: requirements (2.x) and well-formed issue-acceptance-criteria with right: acceptance-oriented validation (8.x).
When to use
- Defining or refining an issue so each AC maps to observable evidence.
- Preparing stakeholder demo, UAT, or audit evidence for “what we said we would deliver.”
Instructions
- Ensure acceptance criteria are testable (copy-pastable steps where possible).
- For each AC, name the validation method: automated check, scripted test, manual checklist, or monitored metric.
- Use validation-draft to derive scenarios; refine with validation-detail once behaviour is known.
- If requirements docs exist (goals, constraints, scope from 2.x), add explicit forward references from AC to those clauses where helpful.
Pitfalls
- Duplicate prose: keep one canonical statement of intent; link instead of copying long specs into both issue and docs.
- Mushy AC: “works well” → replace with measurable or binary checks.
Related
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/v-model-requirements-acceptance-criteria-mrx3xyw4/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/v-model-requirements-acceptance-criteria-mrx3xyw4' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/v-model-requirements-acceptance-criteria-mrx3xyw4/download' --output '.skill-downloads/v-model-requirements-acceptance-criteria-mrx3xyw4/SKILL.md.part' && mv '.skill-downloads/v-model-requirements-acceptance-criteria-mrx3xyw4/SKILL.md.part' '.skill-downloads/v-model-requirements-acceptance-criteria-mrx3xyw4/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/v-model-requirements-acceptance-criteria-mrx3xyw4/SKILL.md' && test -s '.skill-downloads/v-model-requirements-acceptance-criteria-mrx3xyw4/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/v-model-requirements-acceptance' && cp -R '.skill-downloads/v-model-requirements-acceptance-criteria-mrx3xyw4' '.claude/skills/v-model-requirements-acceptance'Cursor
test -f '.skill-downloads/v-model-requirements-acceptance-criteria-mrx3xyw4/SKILL.md' && test -s '.skill-downloads/v-model-requirements-acceptance-criteria-mrx3xyw4/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/v-model-requirements-acceptance' && cp -R '.skill-downloads/v-model-requirements-acceptance-criteria-mrx3xyw4' '.cursor/skills/v-model-requirements-acceptance'Codex
test -f '.skill-downloads/v-model-requirements-acceptance-criteria-mrx3xyw4/SKILL.md' && test -s '.skill-downloads/v-model-requirements-acceptance-criteria-mrx3xyw4/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/v-model-requirements-acceptance' && cp -R '.skill-downloads/v-model-requirements-acceptance-criteria-mrx3xyw4' '.agents/skills/v-model-requirements-acceptance'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/v-model-requirements-acceptance-criteria-mrx3xyw4'openskills read 'v-model-requirements-acceptance-criteria-mrx3xyw4'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/v-model-requirements-acceptance-criteria-mrx3xyw4/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
ClickHouse Performance Comparison
Testing
Evaluate ClickHouse performance test results, check PR performance changes, compare with history, and assess whether a result is actionable.
Analyze CI Performance Reports
Testing
Analyze CI performance comparison reports for a ClickHouse PR. Cross-references master history to distinguish real regressions from flaky tests.
Santa Method
Testing
Multi-agent adversarial verification with two independent reviewers. Output is checked twice and iteratively fixed until both pass before shipping.