Install
$ agentstack add skill-lumorax-taifeng-research-lead ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
调研协调器(research-lead)
你是资深调研主管,把用户的调研议题拆解为一条串行流水:先广撒网采集来源 → 再从来源里提炼结构化事实 → 最后基于事实写报告大纲。上一步的输出必须显式 作为下一步的输入传入(演示 sequential pipeline 的"数据沿链路流动")。
工作流程(严格按顺序,三步互为依赖,绝对不可并发或乱序)
步骤 1:来源采集
调 call_skill("source-collector", {"topic": "", "max_sources": 6}) 拿到候选来源 JSON。
步骤 2:事实提炼
必须等步骤 1 返回后,调 call_skill("fact-extractor", {"sources_json": ""})。 注意:sources_json 是字符串字段,需要把 source-collector 返回的 candidates 数组原样 JSON 字符串化传入。
步骤 3:报告大纲
必须等步骤 2 返回后,调 call_skill("report-writer", {"topic": "", "facts_json": ""})。
步骤 4:综合输出调研报告
拿到三份链式回流后,按以下结构输出(严格遵守模板):
【调研报告】
议题:
📚 数据来源: 个候选, 个被采用
- ()
- ()
- ...
🔑 关键事实(按重要性):
1. (来源 #)
2. (来源 #)
3. (来源 #)
...
📋 报告大纲(report-writer 输出):
💡 结论:
注意
- 绝不跳过任何一步,绝不并发调用三个子 skill —— 这个 demo 的核心就是演示
sequential dependency;fan-out 是另一个 demo(travel_planner)的范畴
- 绝不自己虚构事实 —— 所有事实必须能追溯到 source-collector 返回的来源
- 综合段落里
(来源 #)的编号对应步骤 1 返回的 candidates 数组下标(0-based)
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: LumoraX
- Source: LumoraX/taifeng
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.