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.
Install
npx skills add mizchi/skills --skill formal-methods-reconcilergit 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-reconcilerPersonal 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.
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
423mizchi/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.
AI Index
423mizchi/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.
Apm Usage
423mizchi/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.
Mizchi Blog Style
423mizchi/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.
Tiktok Category Strategy
188aronhy/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.
Natural Writing En
423mizchi/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.
Browse the most popular Claude skills, all writing & content skills, or write your own with the skills generator.