Formal Methods Reconciler

Use when reconciling software specs, docs, tests, configs, code, logs, or incidents with formal methods. Helps Codex extract claims, decide whether docs or implementation are the source of truth, choose an appropriate tool such as Z3, Alloy, TLA+, P, Dafny, MoonBit prove, Lean, Rocq, Why3, Verus, CBMC, Tamarin, or ProVerif, build the smallest useful model, run or plan verifier checks, and translate SAT/UNSAT, traces, proof failures, or proof obligations into domain-language questions and regression guards.

423 stars 6 forksWriting & Content

Install

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

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 Reconciler

Use this skill to turn a vague correctness concern into a small formal-methods check and a domain-readable decision record.

The core stance: the LLM proposes and repairs candidate models; the solver, model checker, verifier, or proof assistant decides; the final result is translated back into domain language for a human decision.

This is the first-modeling and reconciliation skill. If a useful formal model,
CI verifier, expected result, or locked domain decision already exists and the
task is to keep it aligned with later spec/code/log changes, switch to
`formal-methods-drift-guard`.

## Workflow

1. **Choose the source of truth.**
   - If trusted specs/docs/ADRs/API contracts exist, treat them as the expected contract and compare code against them.
   - If specs are missing or unreliable, treat code/tests/config/logs as de-facto behavior, not as automatically correct.
   - If both disagree, do not decide alone. Produce a domain question.

2. **Extract claims before choosing a tool.**
   - Separate declared intent from implicit behavior.
   - Extract claims as: allowed, forbidden, eventually happens, never happens, equivalent, reachable, unreachable, preserves invariant.
   - Note empty/missing/error/timeout/retry/crash behavior explicitly.

3. **Classify the shape of the question.**
   - Pure predicate: input -> Bool.
   - Relation: user/role/resource/tenant/ownership/graph.
   - State transition: lifecycle, retry, crash, queue, eventual.
Read the full skill on GitHub

Details

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

FAQ

What does the Formal Methods Reconciler skill do?

Use when reconciling software specs, docs, tests, configs, code, logs, or incidents with formal methods. Helps Codex extract claims, decide whether docs or implementation are the source of truth, choose an appropriate tool such as Z3, Alloy, TLA+, P, Dafny, MoonBit prove, Lean, Rocq, Why3, Verus, CBMC, Tamarin, or ProVerif, build the smallest useful model, run or plan verifier checks, and translate SAT/UNSAT, traces, proof failures, or proof obligations into domain-language questions and regression guards.

How do I install the Formal Methods Reconciler skill?

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

Is Formal Methods Reconciler 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

Mizchi Blog Style

423

mizchi/skills

Japanese style guide and AI-tone rubric for mizchi-authored blog posts (zenn / dev.to), calibrated on 18 articles / 937 sentences / 766 paragraphs. Scores a draft structure-first — paragraph granularity, heading form, code cadence, closing move — because marker rates (口語・文末・自分) can be hit exactly while the text still reads as pastiche. Use after drafting an article during the style-matching revision loop.

Writing & Content

Tiktok Category Strategy

188

aronhy/tiktok-agent-skills

Use when a user wants to evaluate, enter, position, or operate a TikTok or TikTok Shop category and needs market, product, shop, content, creator, competition, or category strategy.

Writing & Content23

Natural Writing En

423

mizchi/skills

English prose norm for writing explanatory text that does not read as machine-generated. One diagnostic axis (does a sentence update the situation or the document?) plus measured thresholds for burstiness, hedging, enumeration and paragraph openings, with corrections to widely-cited signals that false-positive on human technical writing. Use when drafting or revising English articles, docs, READMEs or long-form explanations, especially after an LLM produced the draft. For Japanese use natural-writing-ja; for scoring a draft use ai-index.

Writing & Content

Browse the most popular Claude skills, all writing & content skills, or write your own with the skills generator.