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 csmar432/finai-research --skill fin-brief-generatorgit clone --depth 1 https://github.com/csmar432/finai-researchWrote 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/csmar432/finai-research/fin-brief-generator)<a href="https://agentmods.dev/skills/csmar432/finai-research/fin-brief-generator"><img src="https://agentmods.dev/badge/skills/csmar432/finai-research/fin-brief-generator/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/csmar432/finai-research/fin-brief-generator"><img src="https://agentmods.dev/badge/skills/csmar432/finai-research/fin-brief-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.02769 |
| Opus 5 | $0.00021 | $0.01385 |
| Sonnet 5 | $0.00008 | $0.00554 |
| Haiku 4.5 | $0.00004 | $0.00277 |
Grade A, and why
fin-brief-generator 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 12d 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 — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fin-brief-generator
根据用户输入或已有研究输出(文献综述/想法报告/新颖性报告),自动生成或更新FIN_BRIEF.md,减少用户填写负担。
触发条件
- 关键词:
生成简报FIN_BRIEFbrief研究简报简报研究概要 - Skill语法:
Skill: fin-brief-generator - 前置条件: 可选 — 已有研究输出文件
三种工作模式
模式一:推理模式 (Inference Mode)
当项目中已有研究输出文件时,从现有文件中自动推断字段值。
输入文件优先级:
1. output/fin-literature/LIT_REVIEW.md → 提取研究领域、方法、文献缺口
2. output/fin-ideas/IDEA_REPORT.md → 提取候选想法、评分
3. output/fin-novelty/NOVELTY_REPORT.md → 提取定位策略
4. output/fin-refinement/REFINED_DESIGN.md → 提取研究设计细节
执行流程:
from scripts.brief_generator import BriefGenerator, InferenceMode
generator = BriefGenerator(project_root=".")
# 推理模式:从现有文件推断
brief = generator.generate_from_outputs(mode=InferenceMode)
# 仅向用户展示未知字段
unknown_fields = brief.get_unknown_fields()
print(f"需要您补充 {len(unknown_fields)} 个字段:")
for field in unknown_fields:
print(f" - {field}")
示例:
已推断字段: 12/17
- 研究主题: 碳排放权交易对企业绿色创新的影响 ✅
- 因果推断方法: 双重差分法 (DID) ✅
- 目标期刊: 经济研究 ✅
需补充字段: 5/17
- 主要作者: ?
- 协作者: ?
- 资助机构: ?
- 文献综述截止日期: ?
- 初稿截止日期: ?
模式二:问卷模式 (Questionnaire Mode)
当有部分信息时,通过结构化问卷收集缺失信息。
问卷流程:
from scripts.brief_generator import QuestionnaireMode
generator = BriefGenerator(project_root=".")
# 运行问卷
answers = generator.run_questionnaire(
questions=[
{
"id": "topic",
"question": "研究主题是什么?请用一句话描述",
"type": "text",
"required": True,
},
{
"id": "journal",
"question": "目标期刊是哪个?",
"type": "choice",
"options": ["JF", "JFE", "RFS", "经济研究", "金融研究", "管理世界", "其他"],
"required": True,
},
{
"id": "data_source",
"question": "主要数据来源是什么?",
"type": "choice",
"options": ["Tushare/A股", "CSMAR", "Wind", "Yfinance/美股", "手动收集", "其他"],
"required": True,
},
{
"id": "method",
"question": "有偏好的研究方法吗?",
"type": "choice",
"options": ["DID", "IV/2SLS", "RDD", "合成控制", "PSM", "面板GMM", "无偏好"],
"required": False,
},
],
interactive=True, # 对话式问卷
)
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.
- 12d ago First seen · 366 lines · 42 tokens per session scan A 7eb865ca900e
fin-brief-generator is a skill published in the GitHub repository csmar432/finai-research (100 stars, last pushed 3d ago), licensed MIT. It adds 42 tokens to every session and 2,769 once invoked, about $0.0002 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
r-econometrics
Run IV, DiD, and RDD analyses in R with proper diagnostics.
econometrics-phd-level
A guide to econometrics, the use of statistics to study relationships in data, based on a 12-part Korean lecture series. It routes questions to explanations of topics such as regression, panel data, instrumental variables, and causal comparisons.
did-causal
Use this Skill when the user needs to estimate causal treatment effects using difference-in-differences (DID) designs: two-way fixed effects (TWFE) regression, parallel trends pre-testing, Callaway-Sant'Anna staggered adoption estimator, and Goodman-Bacon decomposition. Covers both Python (linearmodels) and R (did…
r-econometrics
Generates rigorous, modern, reproducible R code for causal inference and panel econometrics with fixest, heterogeneity-robust DiD estimators (Callaway-Sant'Anna, Sun-Abraham, BJS, de Chaisemartin-D'Haultfoeuille), weak-IV-robust inference, optimal-bandwidth RDD via rdrobust, and wild cluster bootstrap. Use when the…
audit-reproducibility
Enforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata / Python outputs. Report PASS/FAIL per claim against tolerance thresholds. Use before submission and before releasing a replication package.
review-paper
Comprehensive manuscript review with three modes: single-pass (default), --adversarial critic-fixer loop, and --peer [journal] simulated peer-review pipeline (editor + 2 dispositioned referees + editorial decision, calibrated to a target journal). R&R continuation via --peer --r2/--r3; hostile-editor stress test via…