vstack-s2-spec — Claude Code skill: what it does and setup
The vstack-s2-spec Claude Code skill turns a design into testable specifications and pinned checks. It runs during specification work based on an approved S1 design and obligation matrix.
MIT ★ 89 updated 2026-11-16
/plugin marketplace add hao-ai-lab/vstack
/plugin install vstack@hao-ai-lab-vstackWhat vstack-s2-spec does
The skill defines observable system behavior, explicit non-goals, and the assumptions behind each claim. It classifies properties for choosing checkers, scans consumer preconditions, and calibrates legal edge cases alongside failing examples. Calibration happens before the specification is frozen.
The coordinator pins the approved text, ideal model, and check configurations; the property owner approves them. scripts/check_spec_pins.sh ROOT PINS compares the pinned content, and the approved bad-implementation suite runs against the ideal model. Completeness checks are partly manual. A property change needs a new owner decision, regression comparison, and fresh pinning; old proof results do not carry forward.
What it helps with
- define observable behavior and explicit non-goals
- calibrate legal edge cases and failing examples
- match property clauses to checker classes and consumer requirements
- pin an approved specification and its check configurations
Example prompts for the agent
- Draft a specification from the approved S1 design and obligation matrix.
- Define observable behavior and non-goals for this protocol.
- Calibrate failing examples and assumptions for the ideal model.
How to install vstack-s2-spec
1Plugin marketplace
/plugin marketplace add hao-ai-lab/vstack/plugin install vstack@hao-ai-lab-vstackThis installs the whole vstack plugin with all its skills
2Skills CLI (Vercel)
npx skills add hao-ai-lab/vstack --skill vstack-s2-spec -a claude-code3Manually: put the files in place
~/.claude/skills/vstack-s2-spec/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/vstack-s2-spec/
1Skills CLI (Vercel)
npx skills add hao-ai-lab/vstack --skill vstack-s2-spec -a codex2Manually: put the files in place
.agents/skills/vstack-s2-spec/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add hao-ai-lab/vstack --skill vstack-s2-spec -a cursor2Manually: put the files in place
.cursor/skills/vstack-s2-spec/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install hao-ai-lab/vstack skills/vstack-s2-spec2Manually: put the files in place
.github/skills/vstack-s2-spec/SKILL.md1Skills CLI (Vercel)
npx skills add hao-ai-lab/vstack --skill vstack-s2-spec -a gemini-cli2Platform CLI
gemini skills install https://github.com/hao-ai-lab/vstack --path skills/vstack-s2-specManually: put the files in place
.devin/skills/vstack-s2-spec/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about vstack-s2-spec
How do I install vstack-s2-spec in Claude Code?
Run these commands in order: /plugin marketplace add hao-ai-lab/vstack, then /plugin install vstack@hao-ai-lab-vstack.
What does vstack-s2-spec do?
It develops testable specifications and an ideal reference model, pins check configurations, and calibrates legal and failing cases.
What input does vstack-s2-spec need?
It takes an approved S1 design and obligation matrix. The property owner approves the specification.
Source text
SKILL.md · MIT
--- name: vstack-s2-spec description: "Derive observable contracts, calibrate both legal and illegal behavior, then freeze owner-approved specifications and configurations." --- # S2 — Freeze specifications and contracts Read [Layer 0: shared operating rules](../../docs/layer-0.md), this stage and the assigned input bundle. ## Role and write scope The coordinator writes top-level promises and pins; the property owner approves them. Workers supply anchored evidence and staged proposals. ## 1. Input The approved S1 design and obligation matrix. ## 2. Procedure 1. Write a short, reviewable statement of observable consequences and explicit non-goals. Use [contract discovery](../../docs/contracts.md) and [the card template](../../templates/contract-card.md). Name each property clause's pillar and formal class from [property classes](../../docs/method-selection.md#property-classes-and-the-seven-pillars); the class decides the checker and whether fairness is needed. 2. Require top-level decomposition plus historical bugs or consumer requirements; complete one-step induction for ledger and protocol families. Scan all seven consumer-precondition categories. 3. Calibrate negative examples, legal edge behavior, witnesses and minimum scale before freezing. S4 repeats calibration on the complete model. 4. Expose environment assumptions and ambiguous semantics as sourced switches. State which interpretation each claim requires. 5. Have the coordinator pin the approved text, ideal model and check configurations: S2 freezes the property clauses and the ideal reference model of the [three artifacts](../../docs/contracts.md#three-artifacts); S3 builds the code-anchored model against them. Before deductive proof, also freeze the complete inductive invariant and root statement, including explicit parameter ranges and configuration premises. Check content hashes before every counted run. ## 3. Exit checks - Check approval, provenance, consumer scans and calibration records for completeness. This is partly manual. - Require `scripts/check_spec_pins.sh ROOT PINS` to succeed; it compares pinned bytes mechanically. - Run the approved bad-implementation suite against the frozen ideal: bad cases must fail and controls must pass. These project-specific runs do not grant approval. ## 4. Rollback Report an overly strong property or missing assumption with [a rollback ticket](../../templates/rollback.md). Stage the change, compare full regressions, obtain a new property-owner decision, then let the coordinator independently rerun and re-pin. An invariant change requires new Init and affected preservation checks in the same tree, then fresh acceptance. Old proof results do not carry over. ## Concrete Examples For a PD KV slot, a posted write must not simply disappear from the ideal model. Freeze that promise and the configurations that check it; revise them only through the property owner and coordinator.
© Hao AI Lab · MIT · hao-ai-lab/vstack