Formal Methods Drift Guard

Use after a formal model or verifier check already exists and the user wants to maintain it over time. Helps Codex compare specs/docs, implementation code/tests/config/logs, and formal models or CI checks for drift; classify whether the drift is in the spec, code, model abstraction, harness, or unresolved domain decision; run or plan verifier checks; and translate SAT/UNSAT changes, counterexample traces, proof failures, stale models, and CI results into domain-language review questions and ledger entries.

423 stars 6 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add mizchi/skills --skill formal-methods-drift-guard
Manual install
git clone --depth 1 https://github.com/mizchi/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/formal-methods-drift-guard ~/.claude/skills/formal-methods-drift-guard

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Formal Methods Drift Guard

Use this skill when a team already has a model/check and now needs to keep
`spec -> code -> model` aligned as the product changes.

This is not the first-modeling skill. If no useful model exists yet, use
`formal-methods-reconciler` first. This skill starts after at least one of
these exists: a Z3/Alloy/TLA+/P/Dafny/MoonBit/Lean/Rocq check, a CI verifier
job, a model ledger, or a domain decision that was previously locked.
Use `formal-methods-reconciler` for first extraction, tool selection, and
initial model design; use this skill for ongoing drift maintenance.

## Core Rule

Do not make the model green by silently changing the property.

Treat every red check, stale claim, missing source mapping, or changed witness
as a drift signal. Translate it into domain language before proposing a fix.

## Workflow

1. **Build the triplet inventory.**
   - Spec side: docs, ADRs, API contracts, product rules, threat model,
     support runbooks, incident decisions.
   - Code side: implementation, tests, config, schema, migrations, logs,
     telemetry, traces.
   - Model side: formal files, harness scripts, expected SAT/UNSAT assertions,
     CI workflows, pinned tool versions, previous ledger decisions.
   - Assign stable claim IDs when missing, such as `AUTHZ-SETTINGS-001`.

2. **Map each claim across the three surfaces.**
   - Expected domain claim: what the business rule says.
   - Implementation observation: what code/config/logs currently do.
Read the full skill on GitHub

Details

Skill name
formal-methods-drift-guard
Repository
mizchi/skills
Path
formal-methods-drift-guard/SKILL.md
Repo updated
18 November 2026

FAQ

What does the Formal Methods Drift Guard skill do?

Use after a formal model or verifier check already exists and the user wants to maintain it over time. Helps Codex compare specs/docs, implementation code/tests/config/logs, and formal models or CI checks for drift; classify whether the drift is in the spec, code, model abstraction, harness, or unresolved domain decision; run or plan verifier checks; and translate SAT/UNSAT changes, counterexample traces, proof failures, stale models, and CI results into domain-language review questions and ledger entries.

How do I install the Formal Methods Drift Guard skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add mizchi/skills --skill formal-methods-drift-guard. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Formal Methods Drift Guard popular?

It lives in mizchi/skills, which has 423 GitHub stars and 6 forks.

Related skills

Actions CI Tuning

423

mizchi/skills

Use when auditing or improving GitHub Actions workflows for a project. Covers cache setup (npm/pnpm/yarn), job parallelism, shard-based test splitting, artifact handling pitfalls, and Playwright-specific patterns. Trigger on: slow CI, cache miss, flaky shard jobs, merge-reports failures, or an explicit 'tune CI' request.

Testing & QA

AI Index

423

mizchi/skills

Method and tooling for measuring how AI-generated a piece of prose reads, in Japanese or English. Two layers — a deterministic lint for removable surface tells (scripts/slopscore.py, no API) and a judgment layer of typed probabilistic questions (Jev noul/score) for the tells that survive editing. Includes measured human/AI baselines, a gap-first calibration procedure, and labeled fixtures. Use when building or calibrating an AI-likeness score, or when a draft needs a defensible number rather than a vibe. For writing guidance use natural-writing-ja / natural-writing-en instead.

AI, LLMs & Agents

Apm Usage

423

mizchi/skills

Reference for APM manifests, installation, targeted updates, deployment paths and lockfiles. Invoke when the user explicitly asks about APM or apm.yml, or an unfamiliar APM command/error needs exact CLI details. Do not automatically invoke for every project that happens to have installed skills.

DevOps & Cloud

Multi Agent Orchestration

423

mizchi/skills

Use when deciding whether to spawn subagents, choosing sequential vs fan-out vs supervisor vs debate vs dynamic DAG, designing a coding-agent workflow with write-scope isolation, or when extra agents may waste tokens without independent evidence. Trigger on multi-agent, orchestration, fan-out, worktree, blackboard, verifier, AgentTask, or "should I parallelize this".

AI, LLMs & Agents

Empirical Prompt Tuning

423

mizchi/skills

Methodology for iteratively improving agent-facing instructions (skills / slash commands / CLAUDE.md / code-gen prompts) via bias-free executor + two-sided evaluation (self-report + instruction-side metrics). Meta-skill, invoke ONLY when the user explicitly asks for an "empirical" eval of a prompt or skill, or for the Iter-0 description / body consistency check. Do NOT auto-invoke after every skill edit; this loop is operator-triggered by name.

AI, LLMs & Agents

Publish Agent Skill

423

mizchi/skills

Package, publish, verify and update an agent skill through a Claude Code plugin marketplace, APM or the npx skills CLI. Use when preparing skill distribution or diagnosing installation, missing resources and stale updates.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.