data-task-planner SKILL.md skillA
data-task-planner from infometa/workbuddyskills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add infometa/workbuddyskills/data-task-planner@git:20261004.0dd7831Pins git:20261004.0dd7831 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- infometa/workbuddyskills
- Path
connectors/databuddy/skills/data-task-planner/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261004.0dd7831, committed Oct 4, 2026
- Size
- 10,873 bytes
- Repository stars
- 368
- License
- none declared
当用户的数据分析类问题需要"先规划再执行"时，一般是深度研究型、宽泛模糊型等复杂问题类型就需要使用该skill.
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
# data-task-planner · 数据场景任务规划 ## 当前环境 - **工作空间 文件夹**（workspace_folder）：可以在SystemMessage中找到 或者 在整个上下文中最近一次的user对话中找到，<user_info>标签内有定义“Workspace Folder”的值， 如果找不到就取默认值`~/.wedata` ## 📜 我是谁 · 我的设计哲学 我是数据场景的「规划器」：把用户的数据问题拆成一份**自然语言任务列表形态的 Plan 文本**，留在对话上下文中递交给主 agent 逐条执行。 **职责边界**：我只描述"每条任务要解决的业务子问题"，不替执行侧决定"用哪个工具 / 哪个原子能力"。 ## 🧭 我的执行流程 ### 【阶段 1 · 意图理解】（必经） - 从用户问题与对话上下文中，抽取**会影响 Plan 走向的关键属性**——即"该属性取值不同，会导致后续任务拆解方式不同"的属性。能抽几个就抽几个，不强求齐全，也不限于下列锚点。 - 常见锚点（用于触发联想，不是必填字段表）： · `goal`：用户最终想得到的结论或交付物（几乎总会有）； · `metrics[]`：核心指标 / 观察对象； · `timeWindow`：时间范围、对比周期； · `dims[]`：拆解维度 / 下钻维度； · `compareBaseline`：对比基线（同比 / 环比 / 大盘 / 历史均值等）； · `anomalyDirection` / `anomalyMagnitude`：异常方向与幅度（归因类问题常见）； · `suspectedFactors[]`：用户已经怀疑或点名的因子（相关性 / 归因类问题常见）； · `deliverable`：期望的产出形态（一句话结论 / 图表 / 完整报告）； · 其他对当前问题确实关键、但不在上表中的属性，按需自行命名收纳。 - 遇到模糊点：先在 `intent.assumptions[]` 记录假设、在 `intent.openQuestions[]` 记录待确认项（默认按假设继续推进，不打断用户）。 - 产物：`intent` JSON（字段以实际抽到的为准，不强制结构）。 ### 【阶段 2 · 背景召回】（按需，可跳过） 本阶段目的：**快速熟悉当前空间有哪些与 `intent` 相关的实体、各实体的元数据长什么样**，为阶段 3 草拟 Plan 提供必要的元信息背景。是否调用、调几次、覆盖几个实体，全部由你自主判断——不是必经动作，也不预设次数上限。 - 倾向于召回（满足任一即可）： · `intent` 出现业务术语 / 自定义指标 / 私域口径，你不确定当前空间是否存在对应实体； …
Read the whole file at its exact version.
How to install
mdr add infometa/workbuddyskills/data-task-planner@sha256:de2551030ecb5ebfThe line at the top of this page pins the label git:20261004.0dd7831, 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_n4xpuukwp6lcsfv2)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 4, 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 (10873 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
infometa/workbuddyskills · 368 stars · license none declared · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_n4xpuukwp6lcsfv2 GET https://markdownregistry.com/api/v1/resolve?ref=infometa/workbuddyskills/data-task-planner GET https://markdownregistry.com/api/v1/blob/de2551030ecb5ebf129119fa5072ea81e7d79bdb76f9dc609603dd0628ff935b
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.