temper-skills
把决策从生成式模型中剥离，得到可测试、可审计的确定性实现。
需要本地安装并执行 temper-skills CLI，可能运行外部命令。
通过 temper-skills CLI 将技能决策逻辑转为确定性可版本化的 Python 实现。
把 agent skill 的决策逻辑通过 temper-skills CLI 转成可版本化的确定性 Python 实现和测试集，便于测试、审计或冻结路由逻辑。用于没有子代理原语时想把 prompt/skill/playbook 逻辑变成可测代码的场景，需要 pip install temper-skills 和模型后端。特点是推理时零 LLM 调用，逻辑可复现可校验。
▸ 展开 SKILL.md 英文原文
Give an agent skill's decision logic a test suite and a deterministic implementation — a labeled validation dataset plus versionable Python — by driving the installed temper-skills CLI (never reimplementing the logic in prose). Use in agents without a native subagent primitive (Cursor, Hermes, generic tools) when the user wants to test, eval, audit, temper, freeze, or harden the routing/decision logic of a prompt, skill.md, or playbook ("test my skill", "what is this skill deciding?"), including auditing a whole skills directory; requires `pip install temper-skills` and a model backend (a logged-in claude/opencode CLI or an API key). Not for continuous scoring, text generation, or logic with no documentation the model can reach.
帮我安装这个 skill：https://raw.githubusercontent.com/CyrilLeMat/temper-skills/main/skills/temper-skills/SKILL.mdcurl -fsSL "https://raw.githubusercontent.com/CyrilLeMat/temper-skills/main/skills/temper-skills/SKILL.md"# Temper-Skills (library mode) Turn the decision logic of an agent skill or prompt into deterministic Python — zero LLM calls at inference — by **driving the installed `temper-skills` CLI**. You orchestrate the CLI and relay its output; the library does the tempering. You never write the decision tree yourself. > Use this skill when you do **not** have a native subagent/Task primitive to run the loop > yourself. Inside Claude Code, prefer the subagent-mode skill (it runs keyless, with a live > panel). This mode shells out to the CLI instead. ## When to use - A `.md` skill, system prompt, or playbook holds routing/decision logic (if-this-then-that over structured inputs) that should be