Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add agentscope-ai/QwenPaw-Data --skill analysis-plan-buildergit clone --depth 1 https://github.com/agentscope-ai/QwenPaw-DataWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/agentscope-ai/qwenpaw-data/analysis-plan-builder)<a href="https://agentmods.dev/skills/agentscope-ai/qwenpaw-data/analysis-plan-builder"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw-data/analysis-plan-builder.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 224 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00065 | $0.02602 |
| Opus 5 | $0.00032 | $0.01301 |
| Sonnet 5 | $0.00013 | $0.00520 |
| Haiku 4.5 | $0.00006 | $0.00260 |
Grade A, and why
analysis-plan-builder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
analysis-plan-builder
设计原则：行动优先
用户发出分析请求后最差的体验是"agent 一连串提问、什么都没做"。本 skill 要求：先收集上下文，再规划，最后根据信息充分性决定立即执行还是反问。 用户能看到信息不断收敛、分析在推进，同时保留随时打断纠偏的能力。
前置条件
开始规划前，确认以下信息已就绪：
- 用户问题的任务类型（如 BI 业务分析、数据探索、统计建模等）
Step 1: 上下文构建（Phase 1 — Context Gathering）
收集和补充构造分析计划所需的信息。本步骤应尽早执行，在向用户提问之前先通过工具获取尽可能多的上下文。
1.1 可用资源确认
确认当前可用的资源：
- 用户提供的数据文件或表
- 数据获取工具 / API
- 静态的域知识包
- 可获取业务领域模型的接口（后文称"语义层"），即能查询指标、维度及其关系的服务或工具
如果工具列表中包含 MCP 语义层工具（search_context / get_domain_overview / list_metrics 等），立即调用以获取域上下文：
- 推荐首个调用：
search_context(query=用户原始问题, domain=识别出的业务域)— 一次调用返回匹配的指标、口径、数据集和相关维度。 - 补充调用
get_domain_overview(domain)了解域全貌（当 search_context 返回不足时）。
实时向用户同步发现：将 MCP 返回的关键信息（指标名、口径定义、可用维度、数据表）以简洁文本输出到 assistant 消息。用户可随时打断纠偏。
如果没有 MCP 工具可用 → 跳过语义层调用，直接进入 1.2。
1.2 按任务类型补充上下文
- BI 业务分析 → 继续 1.3 ~ 1.5
- 其他任务类型（数据探索、统计建模等）→ 继续 1.6
BI 业务分析
若用户已明确指定了分析的指标（如"分析 DAU 变化"），可跳过 1.3 和 1.4，直接到 1.5 确认指标角色。
1.3 业务上下文识别
判定业务类型（ToB / ToC / ToD / Mixed）和业务子类型（如ToC 下的工具类 / 内容社区 / 电商 / 游戏），判定依据参考 references/bi-business-type-guide.md
1.4 分析范围确认
- 根据业务类型和子类型，读取
references/modules下对应的分析目录文件：
| 业务类型 + 子类型 | 文件 |
|---|---|
| ToC 工具类 | toc-tool.md |
| ToC 内容社区类 | toc-content.md |
| ToC 电商交易类 | toc-ecommerce.md |
| ToC 游戏类 | toc-game.md |
| ToB 产品类 | tob-product.md |
| ToD 开发者社区 | tod-developer.md |
- 根据用户问题匹配具体的分析模块和分析内容：
- 命中分析内容条目（如"用户留存"）→ 仅匹配该条目
- 命中分析模块（如"用户趋势与规模"）→ 匹配该模块全量条目
- 语义意图匹配（如"增长分析"）→ 匹配相关模块的相关条目
- 宽泛问题（如"分析 3 月数据"）→ 匹配全量模块和条目
1.5 指标细化
根据匹配的分析内容条目，参照 references/bi-metric-specification.md，确定每个条目涉及的具体指标。
非 BI 任务（数据探索、统计建模等）
1.6 数据探查
对用户提供的数据进行初步探查，建立对数据的基本理解：
- 读取数据 schema（字段名、类型、数量）
- 查看数据规模（行数、时间跨度等）
- 采样查看数据内容，识别数据特征（缺失值、异常值、分布形态等）
- 结合用户问题，判断哪些字段/特征与分析目标相关
Step 2: 生成分析计划
将 Step 1 的结果组织为结构化的分析计划。
BI 业务分析的计划
包含以下内容：
- 意图：目标、分析对象、问题类型
- 已知条件：时间范围、数据来源、用户提到的指标/维度、约束条件
- 额外上下文：可用数据接口（取数或者语义层工具/API）、域知识约束（如有）
- 缺失信息：已识别但未解决的信息缺口
- 分析内容：每个分析模块的名称、分析条目、指标（名称、角色）
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/bi-business-type-guide.md 4.4 KB
- references/bi-metric-specification.md 2.8 KB
- references/metrics/tob.md 1.7 KB
- references/metrics/toc.md 2.1 KB
- references/metrics/tod.md 1.9 KB
- references/modules/tob-product.md 429 B
- references/modules/toc-content.md 519 B
- references/modules/toc-ecommerce.md 453 B
- references/modules/toc-game.md 402 B
- references/modules/toc-tool.md 547 B
- references/modules/tod-developer.md 441 B
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 225 lines · 65 tokens per session scan A 023b679c9f05
analysis-plan-builder is a skill published in the GitHub repository agentscope-ai/QwenPaw-Data (63 stars, last pushed today), licensed Apache-2.0. It adds 65 tokens to every session and 2,602 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
mem0-tour
Browses all stored memories grouped by category with full content display. Use when reviewing all project memories, exploring stored knowledge, onboarding to a project, or getting an overview of captured decisions, conventions, and learnings.
peek
Searches memories and displays compact one-liner results, or looks up a specific memory by ID. Use for quick memory lookups, checking if a decision was recorded, resolving [mem0:id] citations, or browsing memories without full category detail.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
connect-recommend
Use this skill when the user asks about Stripe Connect configuration, charge patterns, Dashboard access, or how to get started with Connect, is building a marketplace, platform, multi-vendor store, gig platform, or subscription platform, needs to pay out sellers, vendors, or providers, mentions split payments, revenue…
frontend-feature
Build a new page, view, or data-driven feature in the Next.js frontend. Use when adding a route under the dashboard/marketing area, wiring UI to a backend endpoint, adding client state, or creating a localized page. Covers App Router, data fetching, Zustand stores, and i18n.