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 mayuemarsha-del/pm-skills --skill research-reportgit clone --depth 1 https://github.com/mayuemarsha-del/pm-skillsWrote 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/mayuemarsha-del/pm-skills/research-report)<a href="https://agentmods.dev/skills/mayuemarsha-del/pm-skills/research-report"><img src="https://agentmods.dev/badge/skills/mayuemarsha-del/pm-skills/research-report/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mayuemarsha-del/pm-skills/research-report"><img src="https://agentmods.dev/badge/skills/mayuemarsha-del/pm-skills/research-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00126 | $0.01094 |
| Opus 5 | $0.00063 | $0.00547 |
| Sonnet 5 | $0.00025 | $0.00219 |
| Haiku 4.5 | $0.00013 | $0.00109 |
Grade A, and why
research-report 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 11d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Report
Use this skill for formal research reports.
1. Default workflow
Step 1: define the task before researching
Before doing any research, first state:
- 任务背景
- 调研目标
- 调研范围 / 产品清单
- 执行步骤（3~7条）
If the scope is too broad, narrow it or explicitly say what is included/excluded.
Step 2: collect facts
Research by category, not randomly. Typical dimensions:
- 产品定位
- 目标用户
- 页面结构
- 核心功能
- 算法 / 架构
- 计费方式
- 对我们的启示
When information is uncertain, mark it as 待确认 instead of guessing.
Step 3: summarize before details
Always write summary first, then details. Do not dump notes in chronological order.
Step 4: produce a report, not raw notes
The output should read like a formal report, not a chat log or research scratchpad.
2. Default report structure
Research reports default to this structure:
- 背景与目标
- 调研背景
- 调研目标
- 调研范围 / 产品清单
- 摘要总结
- 分类结论
- 关键差异总结
- 对我们的启示
- 调研明细
- 按分类或按产品展开
- 选型建议 / 结论建议（if relevant)
- 附录
- 参考链接
- 备注 / 待确认项
3. Product-level detail standard
If the report compares products, each important product should preferably include:
- 产品定位
- 页面结构
- 核心功能按钮 / 模块
- 算法 / 架构特点
- 计费方式
- 对我们的启示
Do not keep all products at headline level only. The report should support follow-up product judgment.
4. Writing rules
A. Start with conclusions
- 先给分类和差异结论
- 再给支持这些结论的产品细节
- 让读者先抓重点，再决定是否看细节
B. Separate fact from judgment
Clearly distinguish:
- 事实：公开信息、产品页面、定价、功能
- 判断：差异、趋势、启示、建议
C. Prefer comparison tables
For multi-product research, prefer tables for:
- 分类
- 页面结构
- 功能模块
- 算法架构
- 计费方式
- 选型建议
D. Keep product categories explicit
For AI product reports, usually classify before comparing. Typical categories include:
- 通用助手
- 垂直应用（如客服 AI）
- Agent 平台
- LLM 开发平台
- 执行型 Agent
Do not mix all products in one flat list without a taxonomy.
E. Mark uncertainty explicitly
If some product details are not directly confirmed:
- write
待确认 - state the basis of current judgment
- do not fabricate precise UI/function details
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.
- 11d ago First seen · 147 lines · 126 tokens per session scan A c182ad2c6aec
research-report is a skill published in the GitHub repository mayuemarsha-del/pm-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 126 tokens to every session and 1,094 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
setup
A project-initialization workflow for creating a new Workframe project or connecting an existing project to Workframe.
material-intake
A planning tool for sorting existing project files into a suitable structure and suggesting a basic and submodule tree. It inventories files, recommends where each group should go, and produces a plan without moving anything.
code-review
A code-review skill that examines changes for requirement fit, correctness, security, maintainability, and performance. It reports findings with risk levels.
feature-breakdown
A guide for breaking a large request into an epic, user stories, and smaller tasks. An epic is a broad goal, a user story describes one independently useful outcome, and a task is a concrete piece of work.
html-demo
A workflow for building a self-contained interactive HTML demo from a screenshot and a short requirement. The demo imitates the interface and includes simulated controls so its states can be explored.
product-metrics-design
A method for designing a product measurement system using frameworks such as AARRR, HEART, North Star, and OKR. It organizes measurements into a main outcome, supporting drivers, and guardrails that prevent harmful trade-offs.