- name
SKILL.md
技能文件保留在发布者的仓库中。
在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add michael-denyer/pstack-claude --skill create-formal-verification-skill -a cursor -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add michael-denyer/pstack-claude --skill create-formal-verification-skill -a claude-code -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add michael-denyer/pstack-claude --skill create-formal-verification-skill -a codex -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add michael-denyer/pstack-claude --skill create-formal-verification-skill -a grok -y在 Grok Bot 聊天中发送复制的消息。Bot 会从 GitHub 获取这个 SKILL.md,并添加到你所有 Bot 共享的技能中。
Install this skill: https://github.com/michael-denyer/pstack-claude/tree/HEAD/plugins/pstack/skills/create-formal-verification-skill来自发布者
On Codex, read the platform mapping, including its per-skill notes, before following this skill.
On GitHub Copilot, read the platform mapping, including its per-skill notes, before following this skill.
On Muse, read the platform mapping, including its per-skill notes, before following this skill.
On Antigravity, read the platform mapping, including its per-skill notes, before following this skill.
A test checks the cases that someone thought to write. Formal verification checks every case in a stated scope: every order of steps in a model, every input up to a bound, or every input. This skill finds the part of the repo where that matters most, verifies one property of it, and leaves a project-local skill that lets the next agent check a change against that property. Write that skill for an agent who reads it cold, mid-change, and has never seen your work. The user must be able to trust the result and act on it without learning the verification language.
Answer from the codebase, and ask the user only what you cannot observe. If the user named an area or a bug, start there.
A good target is a promise the code makes, where a break harms users and tests rarely reach the case that breaks it. Choose the strongest such target in the repo, not the one that is easiest to verify.
Pick the tool that answers the question at the lowest cost: a model checker, a proof assistant, an SMT-backed verifier, or another tool. Whether events can happen in a bad order usually suits a model checker over a small model of the design, and TLA+ is the default for that in any language. Whether the code itself behaves for every input, as with memory safety, overflow, or a data-structure invariant, usually suits a verifier that runs on the code. If no verifier runs on this language, say so, and test the real code with generated inputs, not a hand model of the function. A property that must hold at every size, where a bound is not enough, can need a proof. Prefer a tool that the repo's developers can install and run, and tell the user why you chose it.
Write a project-local skill with frontmatter that names the area and says when to use it. Name the skill for the area, never verify or a verify- prefix, which belong to the driver skill /create-verification-skill writes. On Claude Code it lives at .claude/skills/<area>/SKILL.md. Without frontmatter, the skill never registers. From the skill alone, the next agent must be able to tell whether a change touches the verified code, run the check, tell a real bug from a modeling error, and update the verification when a change is intended. Put the coverage record and the sync commit in the skill, and tell the next agent to move the sync commit forward only after it confirms that the verification describes the code at the new commit. Use this repo's real commands, paths, and nouns, and leave no placeholders.
If the check is a TLA+ model, tell the next agent to read every result with the pstack /statechart skill. It shows each invariant violation the checker finds as its shortest path in plain words. When the check passes, /statechart draws a chart of how the system moves between states. Refer to /statechart by name. Its commands, options, and file paths change between releases and machines, so copy none of them into the generated skill or its scripts.
Follow the generated skill once, as the next agent would, on a scratch change that breaks the property in the real code. It must catch the break. Then drop the scratch change and confirm that the check is back where it started: passing, or failing only on the findings you will report. A formal verification skill that was never run is a draft. If the skill misses the break or a step does not run, fix the skill or the verification, not the scratch change.
Tell the user what you verified, which tool you used and why, the bounds, what the check found in plain words, how to run it, and what it does not cover. Suggest a second target only if you found a close one. Point the user at /maintain-formal-verification-skill for bringing the verification back in line after changes that did not recheck it.
Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in any language, with whichever verification tool fits. Use for /create-formal-veri
---name: create-formal-verification-skilldescription: Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the…---# plugins/pstack/skills/create-formal-verification-skill/SKILL.md概览
Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in any language, with whichever verification tool fits. Use for /create-formal-verification-skill, \"model-check this race\", \"prove this invariant\", or when concurrency, retries, state machines, parsers, or unsafe code need more than tests.
常见问题
从发布者处下载 plugins/pstack/skills/create-formal-verification-skill/SKILL.md,或复制路径后打开仓库。PlugMCP 只收录该技能,不托管文件。
发布者将它存放在 https://github.com/michael-denyer/pstack-claude。
Claude、Cursor、Codex 和 Grok Build 可以读取你从发布者仓库添加的 SKILL.md。在聊天中发送技能的 GitHub 文件夹链接,Grok Bot 就会安装它。