Updated 1d ago
by hao-ai-lab
vstack
Formal verification workflow and skill stack for coding agents (TLA+, Z3, Apalache, TLAPS)
62 GitHub stars (62)
+62 in 7 days
| Period | New stars |
|---|---|
| Nov 14 | +11 |
| Nov 15 | +27 |
| Nov 16 | +3 |
| Nov 17 | +7 |
- 11 skills (11 skills found in its SKILL.md files)
- 5 forks (5 forks)
- 1d ago last update (Last updated 1d ago)
Install
Skills CLI
npx skills add hao-ai-lab/vstack
Asks which skills and agents to install. Just one: npx skills add hao-ai-lab/vstack --skill verify-pd-kv-slot — add -g for every project.
Claude Code
git clone https://github.com/hao-ai-lab/vstackcp -r "vstack/examples/verify-pd-kv-slot" ~/.claude/skills/
Copies the verify-pd-kv-slot skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add hao-ai-lab/vstack
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
verify-pd-kv-slot
Illustrate an S8 (package and maintain regression) regression skill for PD KV slot ownership, release and reuse; use as a project adaptation example.
examples/verify-pd-kv-slot/ on GitHub (opens in a new tab)SKILL.md -
vstack-mode
Run the Verification Stack for a concurrent, distributed or systems-software property, from source archaeology through calibrated models, red team, proof and maintained regression. Use for /vstack-mode or an end-to-end verification workflow.
skills/vstack-mode/ on GitHub (opens in a new tab)SKILL.md -
vstack-s0-decompose
Map a pinned system into control, data and boundary views and build evidence-backed historical anchors before verification.
skills/vstack-s0-decompose/ on GitHub (opens in a new tab)SKILL.md -
vstack-s1-select
Choose verification tools and assurance tiers per property using state, scale, ownership and consequences.
skills/vstack-s1-select/ on GitHub (opens in a new tab)SKILL.md -
vstack-s2-spec
Derive observable contracts, calibrate both legal and illegal behavior, then freeze owner-approved specifications and configurations.
skills/vstack-s2-spec/ on GitHub (opens in a new tab)SKILL.md -
vstack-s3-model
Construct state transitions or computation descriptors from pinned code without hiding interleavings or unchecked assumptions.
skills/vstack-s3-model/ on GitHub (opens in a new tab)SKILL.md -
vstack-s4-calibrate-tv
Calibrate buggy/fixed/ablated behaviors and validate model conformance using real traces, witnesses and explicit mismatch triage.
skills/vstack-s4-calibrate-tv/ on GitHub (opens in a new tab)SKILL.md -
vstack-s5-redteam
Audit calibrated verification through independent attacks on fidelity, property/gate strength and scope extrapolation.
skills/vstack-s5-redteam/ on GitHub (opens in a new tab)SKILL.md -
vstack-s6-hunt-fix
Search within a trace-validated model scope, classify counterexamples and validate fixes in both the model and real code.
skills/vstack-s6-hunt-fix/ on GitHub (opens in a new tab)SKILL.md -
vstack-s7-prove
Prove pinned design-model properties in one shared TLAPS module tree after invariant discovery, calibration and trace alignment.
skills/vstack-s7-prove/ on GitHub (opens in a new tab)SKILL.md -
vstack-s8-package-maintain
Package verified scope into a project-local five-step regression skill and keep it aligned with future code revisions.
skills/vstack-s8-package-maintain/ on GitHub (opens in a new tab)SKILL.md
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.