New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Sdd Riper One Light

by openyida in openyida/openyida

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。

MITAuto-check passedAgent Workflows

Install Sdd Riper One Light

skills CLI
$ npx skills add openyida/openyida --skill sdd-riper-one-light -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install openyida/openyida sdd-riper-one-light --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/openyida/openyida.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/sdd-riper-one-light .claude/skills/sdd-riper-one-light && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
sdd-riper-one-light
GitHub stars
220
Token cost
~1.5k tokens
SKILL.md length
385 words
Files
20 (incl. scripts, references)
Skills in repo
58
Repo updated
First seen
Licence
MIT

At a glance

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。

  • Agent Workflows work in your project
  • SKILL.md covers 核心定位, 硬约束, 默认假设 and 任务深度, plus 4 more sections

What it does

Sdd Riper One Light is an agent skill from openyida/openyida. 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。

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 24 other files, including scripts and reference files (for example `README.md`, `agents/openai.yaml` and `examples/README.md`).

It sits in Agent Workflows. It works with OpenAI. The repository describes itself as: Your own personal YiDA AI assistant! The licence is MIT.

When your agent uses it

  • Agent Workflows work in your project

Example prompts

  • “/sdd-riper-one-light”

What it can do on your machine

Read from SKILL.md and the folder at commit b52e65e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/, which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sdd Riper One Light loads about 1.5k tokens when it runs, and up to ~7.8k if it reads all its reference files. Until then it costs about 44 tokens; SKILL.md has 385 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~44
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from openyida/openyida at commit b52e65e, republished under its MIT licence (© openyida). 385 words, ~1,473 tokens.

Download SKILL.mdSave it as .claude/skills/sdd-riper-one-light/SKILL.md (or your agent's skills folder). This skill also uses 19 other files; get the full folder from GitHub.
name
sdd-riper-one-light
description
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。
version
0.12.0
x-source
aone-open

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。
  • Project Sync Boundary：项目级规则和知识入口由项目 AGENTS.md 或用户定义。SDD 只在 Reverse Sync / Review / handoff / new chat / debug 收尾时识别 Project Sync Candidate，按已定义落点同步；未定义时先提出候选和建议，等待用户确认。详细边界按需读取 references/project-sync-boundary.md。
  • 隐私提交边界：系统级知识、Feature Spec、handoff、Project Spec / Project Memory 和用户偏好可能包含隐私或内部信息。可以主动识别、总结、提出候选，但默认不得暂存或提交到仓库；只有用户明确要求提交，且内容已按目标仓库脱敏确认后，才允许纳入 git。

硬约束

  • Spec is Truth：spec 是持久化上下文、压缩记忆与协作真相源。
  • No Spec, No Code：未形成或更新最小 spec 前，不进入代码实现。
  • Spec Boundary：普通任务默认落 Feature Spec；项目级长期事实只作为已确认的 Project Sync Candidate，按项目 AGENTS.md 或用户定义的落点同步。
  • No Approval, No Execute：未得到明确执行许可，不进入实现或高影响变更。
  • Restate First：用户输入任务后，先用模型自己的话复述理解，再进入 spec 或计划。
  • Core Goal as Loop Anchor：阶段性核心目标是当前 loop 的唯一锚点；进入执行前、发生偏差后、完成验证时，都必须重新对齐该锚点。
  • Recap Checkpoint：长任务、暂停返回、执行前、阶段收尾或用户问“现在到哪了”时，输出并按需落盘一段短 recap；它应比 spec 短得多，但必须包含下一步和验证/风险。
  • Minimal Chaos Sanity Check：只做轻量 sanity check。若任务明显太大、边界明显不清或风险明显升高，提醒用户并建议升级 deep 或切到 sdd-riper-one；否则默认相信用户拆分。
  • Checkpoint Before Execute：实现前必须给一次短 checkpoint，确认理解、目标、下一步、风险与验证方式。
  • Done by Evidence：完成应由验证结果与外部反馈证明，而不是由模型自行宣布。
  • Reverse Sync：执行后必须把结果、偏差、验证结论回写 spec。
  • Project Sync Scan：任务收尾、new chat、handoff、用户反复纠正或发现稳定项目事实时，主动扫描是否有 Project Sync Candidate；没有也要说明无可同步长期知识。
  • Resume Ready：长任务或暂停前，应在 spec 中留下最小恢复锚点，支持重启与交接；用户触发 new chat / handoff / resume pack 时，调用 $new-chat-ready 生成落盘交接包和可直接粘贴的续接 prompt。

默认假设

  • 强模型默认自行分解任务，不强制展开冗长 Research / Innovate / Plan / Execute / Review 文本。
  • 用户默认已经完成主要任务拆分；light 只辅助检查，不替用户重新拆任务。
  • 默认 prompt 文档只放最小路由和边界，不复制完整 skill，避免污染长期上下文。
  • 小任务不为了协议而拆；大任务也不为了仪式感写长计划。
  • 真正必须保留的，是最小 spec、先复述理解、recap checkpoint、执行前 checkpoint、明确批准、执行后回写。
  • 默认不反复喂 spec；checkpoint 时先让模型自总结当前目标、进度、风险和验证状态，再按需回读当前相关 spec 区块。
  • 如果任务还没重到需要完整 spec，recap checkpoint 可以作为临时上下文锚点；一旦进入多文件实现、跨轮恢复或需要验收证据，应把 recap 回写到 micro-spec / spec / handoff。
  • 如果长对话后行为漂移、忘记 spec/checkpoint/validation、新 chat 继续旧任务、或用户质疑 skill 是否生效，按需回读 references/anti-context-decay-lite.md 和 references/skill-injection-check.md。

任务深度

zero（零 Spec 通道）
  • 适用于纯机械性改动（typo 修复、日志添加、配置值变更等无决策性的单点修改）
  • 跳过 micro-spec，直接执行并在完成后用一句话 summary 回写
  • 一旦发现复杂度超出预期，立即升级到 fast 或 standard
fast
  • 先写 micro-spec，不裸改。
  • 用 1-3 句写清目标、涉及文件、主要风险、验证方式。
  • 用户明确批准后再执行。
  • 复杂度上升时升级到 standard 或 deep。
Show full SKILL.md (153 more words)Show less
standard
  • 默认模式，适用于大多数 2+ 文件改动、一般功能开发、普通缺陷修复。
  • 补齐必要上下文，维护一份轻量 spec 并落盘。
  • 执行前给一次短 checkpoint，获批后实施并回写结论。
deep
  • 适用于需求模糊、架构改动、未知根因、跨模块/跨项目、长链路迭代。
  • 允许显式分析、方案比较、风险说明，但仍保持短。
  • 先把深思考结果写回 spec，再给用户审阅；获批后再进入实现。
  • 按需加载 references/modules.md，而不是把深流程常驻。
  • 如果 deep 中需要主动拆分最小混沌单元、生成完整 codemap/context、频繁阻塞和训练用户，建议切到 sdd-riper-one。

最小工作流

  • 用户给出任务后，先复述模型自己的理解，确保核心目标强一致。
  • 轻量确认任务是否明显不是最小混沌单元；若没有明显问题，直接进入最小 spec 和 checkpoint。
  • 用最小 spec 固化目标、边界、事实、计划与结论，并尽快落盘。
  • 在 spec 中用 1-3 行写清 Done Contract：什么算完成、由什么证明、哪些情况算仍未完成。
  • 实现前给一次短 checkpoint：当前理解、核心目标、recap、下一步 1-3 个动作、风险、验证方式。
  • 若测试、日志、人工反馈暴露出偏差，先基于外部证据重述“当前核心目标是否变化、还差什么”，再决定继续执行还是调整方案。
  • 用户明确批准后执行；若范围或方案变化，先更新 spec 再重新请求批准。
  • 执行后回写 Change Log / Validation / Resume or Handoff，并说明“当前核心目标是否已由证据证明完成；若未完成，下一轮核心目标是什么”。
  • 收尾时做一次 Project Sync Boundary 检查：本次过程留在 Feature Spec；稳定、可复用、跨任务会再次影响判断的事实列为 Project Sync Candidate，并按项目已定义落点或用户确认同步。

何时暂停

遇到以下情况，先暂停并说明原因：

  • 需求存在会改变实现方向的关键歧义。
  • 需要破坏性、高风险、不可逆操作。
  • 任务明显不是最小混沌单元，且继续执行会导致大范围漂移。
  • 模型提出的路径明显越过用户给定边界。
  • 连续验证失败后仍沿同一路径推进，缺少回炉判断。
  • 涉及架构级改动、公共接口变更、数据模型变更、迁移策略变更。
  • 涉及跨项目修改，而用户未明确允许或范围未清楚。
  • 发现现有 spec 明显错误、过期或与代码现实冲突。
  • 尚未形成最小 spec 或尚未得到明确执行许可。

按需模块

  • references/spec-lite-template.md：最小 spec 模板。
  • references/routing-map.md：场景到 reference/script 的文档地图；不确定读什么时先看它。
  • references/mode-selection-lite.md：light/one 选择、升级/降级条件。
  • references/anti-context-decay-lite.md：长对话、新 chat、skill 遗忘时的回读和恢复规则。
  • references/project-sync-boundary.md：项目知识沉淀、Project Sync Candidate、AGENTS / PROJECT_KNOWLEDGE / PROJECT_MEMORY / PROJECT_SPEC / Feature Spec 分流不清时读取。
  • references/skill-injection-check.md：检查 agent / 项目规则 / 默认 prompt 是否实际注入本 skill。
  • references/default-prompt-setup-lite.md：建立项目级/系统级默认 prompt 文档的最小写法。
  • references/script-map.md：可直接调用的脚本入口，包含默认 prompt 检查/写入脚本。
  • references/modules.md：Deep Planning / Debug / Review / Multi-project。
  • references/conventions.md：落盘目录、命名规则、micro-spec 与正式 spec 的分流规则。
  • $new-chat-ready：跨对话交接能力；触发 new chat / 换对话 / handoff / resume pack / 上下文压缩时使用，light 只维护 spec 锚点，不内嵌交接模板。

输出风格

  • 默认中文，但不强制；用户、项目或目标文档明确使用其他语言时，跟随更具体的语言要求。
  • 默认短输出，不复述完整协议。
  • 优先给“当前理解 + 核心目标 + recap checkpoint + 下一步 + 必要风险”；只有不确定或需要证据时才补相关 spec 锚点。
  • 不强制打印阶段状态机。
  • 核心目标采用“事件触发式复述”：阶段开始、执行前 checkpoint、偏差暴露后、阶段收尾时必须重对齐；其他轮次不机械复读。
  • 需要长链路推进时，优先给最小 Done Contract 与 Resume/Handoff，而不是扩写长计划。
  • 小任务用 micro-spec + micro-summary；复杂任务再按需展开。

© openyida, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 19 other files (scripts, references) in .agents/skills/sdd-riper-one-light of openyida/openyida.

  • SKILL.md
  • README.md
  • agents/openai.yaml
  • examples/README.md
  • examples/codemap/codemap-feature-content-control.md
  • examples/specs/spec-light-runtime-compat.md
  • examples/specs/spec-standard-security-status-race.md
  • package.json
  • references/anti-context-decay-lite.md
  • references/conventions.md
  • references/default-prompt-setup-lite.md
  • references/mode-selection-lite.md
  • references/modules.md
  • references/project-sync-boundary.md
  • references/routing-map.md
  • references/script-map.md
  • … and 4 more

Open the folder on GitHubat commit b52e65e

Compare with similar skills

Sdd Riper One Light next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Sdd Riper One Light compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sdd Riper One Light this skillopenyida/openyida220—~1.5kAutomated safety check: PassMIT
Codex with ChatGPT Planning LoopXiaoDuoYa/codex-with-chatgpt7.1k—~11kAutomated safety check: NotesMIT
Nagentdavidondrej/skills4.1k—~1.7kAutomated safety check: NotesMIT
Cao MCP Appsawslabs/cli-agent-orchestrator1.4k—~1.9kAutomated safety check: PassApache-2.0
LLM Councilgcpdev/llm-council-skill461—~1kAutomated safety check: NotesMIT
Daily Logsmemodb-io/Acontext3.7k—~243Automated safety check: PassApache-2.0

Similar skills

  • Codex with ChatGPT Planning Loop

    XiaoDuoYa/codex-with-chatgpt

    Uses ChatGPT in the browser as the planning and review brain for a Codex session, with Codex keeping all execution and ChatGPT reading the workspace through a bridge.

    7.1k GitHub stars~11k tokensUpdated 9 days ago
    Agent WorkflowsAuto-check: notes

  • Nagent

    davidondrej/skills

    Launch a new bb worker thread with the right project, model, worktree, and task brief.

    4.1k GitHub stars~1.7k tokensUpdated yesterday
    Agent WorkflowsAuto-check: notes

  • Cao MCP Apps

    awslabs/cli-agent-orchestrator

    Official

    Enable, operate, and extend CAO's MCP Apps surface — the host-rendered fleet dashboard visible inside MCP App hosts (Claude Desktop, ChatGPT, VS Code Copilot, Goose, Postman).

    1.4k GitHub stars~1.9k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • LLM Council

    gcpdev/llm-council-skill

    Multi-LLM collaborative brainstorming and planning. An agent skill from gcpdev/llm-council-skill.

    461 GitHub stars~1k tokensUpdated 9 mo ago
    Agent WorkflowsAuto-check: notes

  • Daily Logs

    memodb-io/Acontext

    Track daily activity logs and summaries for the user. An agent skill from memodb-io/Acontext.

    3.7k GitHub stars~243 tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed

  • Chatgpt Apps

    Haohao-end/openagent

    Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI.

    808 GitHub starsUsed in 1 repo~4.9k tokens
    Agent WorkflowsAuto-check passed

More from openyida/openyida

All 58 skills in this repo

  • Yida Canvas Custom Page

    openyida/openyida

    宜搭自定义页面开发规范，使用 YidaCodeCanvas 组件实现现代 React18 自定义页面。用于官网、看板、工作台、列表、详情、门户壳、可视化、hooks 交互、表单入口，以及需要门户组件、数据管理视图、成员、部门或上传组件的场景；发布层自动注入 yida/utils window 桥。

    220 GitHub stars~4.3k tokensUpdated yesterday
    Auto-check passed

  • Openyida Release

    openyida/openyida

    快速发布 OpenYida npm 正式版或测试版。用户说“发布正式版”“发布测试版”“发 beta”或要求按当天日期生成版本 tag 时使用；不用于宜搭应用或自定义页面发布。

    220 GitHub stars~520 tokensUpdated yesterday
    Auto-check passed

  • Yida Design Plan

    openyida/openyida

    Plan 模式的视觉设计分支。基于需求选择视觉方向，再结合业务页面规划维护 build-plan.json 的 visualStyle，供 CLI 派生 design.md。

    220 GitHub stars~756 tokensUpdated yesterday
    Auto-check passed

  • Yida Openyida Publish Guard

    openyida/openyida

    Prevent stale local OpenYida custom page source from overwriting live designer edits.

    220 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

  • Codemap

    openyida/openyida

    Generate, update, or drift-check agent-facing CodeMaps as progressive code terrain indexes for projects, features, capabilities, functions, modules, or bug chains.

    220 GitHub stars~1k tokensUpdated yesterday
    Auto-check passed

  • Yida Canvas Data Binding

    openyida/openyida

    自定义页面真实数据接入技能。用于在使用 YidaCodeCanvas 组件实现的页面中用 dataBinding + 发布层 yida/utils window 桥接入宜搭表单、流程 API、连接器代理或同源接口数据，处理返回体包裹解析、totalCount 保护、DataBridge 状态和静默刷新。触发词：dataBinding、DataBridge、数据桥、YidaCodeCanvas…

    220 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Sdd Riper One Light

What does Sdd Riper One Light do?

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。. Sdd Riper One Light is an agent skill from openyida/openyida.

When should I use Sdd Riper One Light?

Sdd Riper One Light fits situations like: agent Workflows work in your project.

How do I install Sdd Riper One Light in Claude Code?

Run `npx skills add openyida/openyida --skill sdd-riper-one-light -a claude-code`. Or copy the skill folder (.agents/skills/sdd-riper-one-light in openyida/openyida) into .claude/skills/sdd-riper-one-light in your project. Claude Code loads it when a task matches its description.

How do I install Sdd Riper One Light in Codex?

Run `npx skills add openyida/openyida --skill sdd-riper-one-light -a codex`. Or copy the skill folder (.agents/skills/sdd-riper-one-light in openyida/openyida) into .agents/skills/sdd-riper-one-light in your project. Codex loads it when a task matches its description.

Can I use Sdd Riper One Light in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add openyida/openyida --skill sdd-riper-one-light -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sdd-riper-one-light, .gemini/skills/sdd-riper-one-light, .github/skills/sdd-riper-one-light and .opencode/skills/sdd-riper-one-light in your project.

What does Sdd Riper One Light need to run?

SKILL.md names no scripts, command-line tools or credentials: Sdd Riper One Light is instructions for the agent only.

Does Sdd Riper One Light access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Sdd Riper One Light safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Sdd Riper One Light use?

Sdd Riper One Light is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Sdd Riper One Light use?

About 1.5k tokens (SKILL.md is roughly 5.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6.3k tokens, read only when the agent opens those files.

What are the alternatives to Sdd Riper One Light?

Skills that share tags, products or a category with Sdd Riper One Light: Codex with ChatGPT Planning Loop (XiaoDuoYa/codex-with-chatgpt, 7.1k stars), Nagent (davidondrej/skills, 4.1k stars), Cao MCP Apps (awslabs/cli-agent-orchestrator, 1.4k stars) and LLM Council (gcpdev/llm-council-skill, 461 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sdd Riper One Light?

openyida (a GitHub organization) maintains it in openyida/openyida, which has 220 GitHub stars. The repository holds 58 skills in this directory. The repository was last updated on October 8, 2026.

Source: openyida/openyida on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.