Skills Plugins MCP Prompt Model 博客 我的中心
生活与工具 #api #agent #mcp

scrumboy-board-operator

Operate Scrumboy projects and boards through MCP or Agoragentic APIs. Use when an agent needs to inspect board state, plan sprint work, create todos, move cards, manage tags, or summarize project health.

DeepseekModel 官方收录技能 质量 优秀 · 78 v1.0.0

获取

https://deepseekmodel.com/api/download.php?id=markrai-scrumboy-plugins-scrumboy-board-operator-skills-scrumboy-board-operator-skill-md&format=skill
下载 .skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用
.skill 文件中 system_prompt 字段的实际内容。
name scrumboy-board-operator description Operate Scrumboy projects and boards through MCP or Agoragentic APIs. Use when an agent needs to inspect board state, plan sprint work, create todos, move cards, manage tags, or summarize project health. Scrumboy Board Operator Skill Use this Skill to turn broad project-management requests into safe, auditable Scrumboy MCP workflows. Prefer read-only inspection before proposing mutating tool calls. Capabilities Discover Scrumboy MCP capabilities and available tools. Inspect projects, board state, todos, sprints, tags, and members. Summarize sprint health, assignment gaps, and blockers or stale items where they are represented by board content, tags, sprint dates, workflow columns, or visible metadata. Draft todo creation, updates, moves, tag changes, and sprint actions. Separate JSON-RPC ( /mcp/rpc ), legacy HTTP ( /mcp ), and Agoragentic ( /agora/v1/discover , /agora/v1/invoke ) request shapes. Required Output Return a concise note with these sections: Scope : the Scrumboy instance, project slug, sprint, todo, tag, or member under review. Interface : MCP JSON-RPC, legacy MCP HTTP, or Agoragentic adapter. Evidence : read-only tools or curl commands used, with tokens and sensitive IDs redacted. Findings : board state, sprint state, inferred blockers or stale work, or configuration risk. Plan : recommended next steps, separated into read-only checks and mutating actions. Approval Required : every create, update, delete, move, sprint activation, sprint close, tag update, member change, or webhook change. Verification : follow-up reads to confirm board state after an approved mutation. Risks : missing auth, anonymous mode limits, bootstrap state, stale board data, or production impact. When explicitly running plugin evals, also include Plugin Eval Metadata : eval case id, expected pass criteria, and safe metadata events. Do not include this section for normal board operations. Workflow Confirm the request scope and whether the user wants read-only analysis or a board mutation. Call system_getCapabilities or tools/list first when interface support is unclear. Use projects_list and board_get before recommending todo or sprint changes. For JSON-RPC, call tools/call with params.name and params.arguments . For legacy MCP HTTP, call /mcp with tool and input . For Agoragentic, call /agora/v1/discover or /agora/v1/invoke with tool and arguments . Ask for human approval before any mutating action. Verify after approved changes with board_get , todos_get , sprint reads, or tag/member reads. Acceptance Checks Identifies the Scrumboy interface and uses the correct request shape. Reads board or project state before proposing changes. Separates evidence from recommendations. Requires approval before mutating tools. Redacts credentials, board contents, todo descriptions, and user data from telemetry. Includes a verification step after approved changes. Privacy and Telemetry Boundary Only emit metadata about plugin behavior, such as component name, outcome, duration bucket, harness name, and sanitized error class. Do not emit prompts, source files, todo descriptions, board contents, API tokens, session cookies, user identifiers, tool arguments, or model outputs.
Agent 识别该技能的关键词,点击任意一个即可复制。

该技能未提供触发词。

下载的 .skill 包内含以下字段。
字段 说明
format格式标识(skill/v1)
skill_id技能唯一 ID
name技能名称
version版本号
description技能描述
category所属分类(数组)
trigger_words触发词列表
tags标签列表
source来源标识
source_url来源链接(本页地址)
exported_at导出时间(每次下载生成)
system_prompt系统提示词正文
model_config模型参数:provider / model / temperature / max_tokens / top_p
examples示例
install_guide各平台导入说明(Coze / Dify / Claude / 自定义框架)
同一份技能可按不同平台格式导出。
.skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用 下载
.skillpro 增强格式,额外含脚本 / 工具 / 依赖 / 钩子占位 下载
.json 纯 JSON 导出,只含 system_prompt 与模型参数 下载
Coze 带 frontmatter 的 Markdown,Coze 平台导入用 下载
Dify Dify DSL,创建应用后直接导入 下载

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。