Agent Skills › different-ai/openwork › fraimz

fraimz

GitHub

兼容已废弃的遗留流程运行，仅在用户显式请求时执行evals/flows下的现有文件。禁止创建或修改新流程，强制转向新版测试规范。

.opencode/skills/fraimz/SKILL.md different-ai/openwork

触发场景

用户请求运行现有的legacy flow文件需要执行evals/flows目录下已存在的评估流程

安装

npx skills add different-ai/openwork --skill fraimz -g -y

更多选项

非标准路径

npx skills add https://github.com/different-ai/openwork/tree/dev/.opencode/skills/fraimz -g -y

不安装直接使用

npx skills use different-ai/openwork@fraimz

指定 Agent (Claude Code)

npx skills add different-ai/openwork --skill fraimz -a claude-code -g -y

安装 repo 全部 skill

npx skills add different-ai/openwork --all -g -y

预览 repo 内 skill

npx skills add different-ai/openwork --list

SKILL.md

Frontmatter

{
    "name": "fraimz",
    "description": "DEPRECATED legacy flow compatibility. Load only when a user explicitly asks to run an EXISTING evals\/flows\/*.flow file. New coverage uses write-a-spec and run-tests."
}

Legacy Fraimz Compatibility

This guide exists only to run a user-requested flow that is already present in evals/flows/. The corpus is frozen.

For current verification, use prove-a-pr → write-a-spec → run-tests → publish-evidence.

Hard boundary

Refuse requests to create, scaffold, copy, rename, or modify a legacy flow.
Do not use a legacy flow as coverage for new work.
For any new or changed executable end-to-end coverage, switch to write-a-spec → run-tests → diagnose-a-red-run when failing, then publish-evidence for existing ambient test evidence.

Run an existing flow

Confirm the requested ID already exists with pnpm evals:legacy --list, launch the app if that existing flow requires it, then run:

pnpm evals:legacy:demo --flow <existing-id> --cdp-url <electron-cdp-url>

Report the legacy runner result honestly. If the flow itself is broken or no longer represents the behavior, stop and report that limitation; do not repair the flow. evals/README.md documents the frozen compatibility lane.