sdd-riper-one-light SKILL.md skillA
sdd-riper-one-light from openyida/openyida is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add openyida/openyida/sdd-riper-one-light@v0.12.0Pins v0.12.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- openyida/openyida
- Path
.agents/skills/sdd-riper-one-light/SKILL.md- Versions recorded
- 1
- Latest version
- v0.12.0, committed Jul 28, 2026
- Size
- 11,710 bytes
- Repository stars
- 230
- License
- MIT
面向 GPT-5.5 等强模型和熟练用户的轻量 AI Agent Harness / checkpoint-driven coding skill。默认用户已经把任务切到基本可执行的最小混沌单元；模型自行分解、探索与推进，人类通过最终目标、最小 spec、复述、checkpoint、证据验证与回写来低干扰控盘。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# SDD-RIPER-ONE Light ## 核心定位 - 这是面向强模型的轻量 **AI Agent Harness**，不是 `phase-heavy` 版本。 - 默认承认模型已经从“助手”变成事件推进的主体：模型负责分解、探索、试错和推进；人类负责方向、边界、节奏、风险与验收。 - 默认面向熟练用户、强模型和已经被用户拆得还不错的任务；它是无感安全带，不是 Harness 教练。 - 默认假设强模型已经能自行分解任务、补足局部计划、按需追溯上下文。 - 默认不主动做重度任务拆分，不频繁讲解理论，不把每一步都变成审批点。 - 主协议只保留少数高杠杆锚点，其余规范按需查看 reference。 - 目标不是减少控制力，而是减少低价值常驻 token。 - 不节约有效 token，但节约上下文：常驻只保留运行内核，模板、教学、诊断与长规则按需加载。 - `New Chat Startup Check`：进入 new chat 或新项目会话时，先检查可见的项目/系统提示词入口是否存在、是否包含本 skill 路由；缺失时询问用户是否需要新建或补充默认 prompt 文件。若用户拒绝或任务很急，继续当前任务但不静默写配置。 - 控制方式不是预设每一步，而是在关键节点设闸：Restate、Recap Checkpoint、Approval、Validation、Reverse Sync。 - `Recap Checkpoint` 是比 spec 更轻的持久化上下文：用 1-6 行记录“当前目标 / 已完成 / 关键决策 / 当前边界 / 下一步 / 验证风险”，防止长对话和暂停后的上下文腐烂；它不替代 spec，只负责让当前 loop 不断知道“我在哪”。 - **Spec 受众分层与上下文保护**：Spec 的第一受众是人类（持久化的任务上下文与组织记忆），第二受众才是模型。协议对模型的核心价值是四件事：**注意力聚焦**（让模型只关注当前该关注的）、**信息索引**（需要时按路径回读，而非全量常驻）、**防止上下文腐烂**（用落盘的 Spec 对抗长对话中的遗忘与漂移）、**辅助 Review**（提供 Spec vs 代码的交叉验证基准）。协议绝不应导致上下文被塞满挤爆——RIPER 管流程，Spec 管记录，模型按需取用。 …
Read the whole file at its exact version.
How to install
mdr add openyida/openyida/sdd-riper-one-light@sha256:df985d86eb4117d2The line at the top of this page pins the label v0.12.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_kb2hyu5srogsg223)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Jul 28, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (11710 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
openyida/openyida · 230 stars · license MIT · pushed 2026-11-02 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_kb2hyu5srogsg223 GET https://markdownregistry.com/api/v1/resolve?ref=openyida/openyida/sdd-riper-one-light GET https://markdownregistry.com/api/v1/blob/df985d86eb4117d26dd0e2a570099b075ba5af997219a70f968973d48111043c
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.