Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/csmar432/finai-researchnpx agentmods add skills/csmar432/finai-research/fin-full-pipelineWrote 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-full-pipeline)<a href="https://agentmods.dev/skills/csmar432/finai-research/fin-full-pipeline"><img src="https://agentmods.dev/badge/skills/csmar432/finai-research/fin-full-pipeline/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-full-pipeline"><img src="https://agentmods.dev/badge/skills/csmar432/finai-research/fin-full-pipeline.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 | $0.00063 | $0.08111 |
| Opus 5 | $0.00032 | $0.04056 |
| Sonnet 5 | $0.00013 | $0.01622 |
| Haiku 4.5 | $0.00006 | $0.00811 |
Grade A, and why
fin-full-pipeline 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 — 1,026 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fin-full-pipeline:经济金融研究端到端完整流程
端到端的经济金融学术研究流程,从用户描述研究方向开始,到生成可投稿论文 PDF 结束。
Agent-host / 隔离槽位(重要)
若任务要求「不要询问、不要 Mock、缺失配置则跳过并写报告」:
先运行python scripts/agent_host_entry.py(或读取其写出的output/SKIPPED_CONFIG.md/output/FINAL.md)。
若该入口因无 LLM 等原因以非 0 退出,停止本 Skill,不要自建平行复现流水线或编造结果。
交互式 HITL 路径仍用start_research.py/agent_pipeline.py --use-hitl。
研究方向输入
↓
阶段1: FIN_BRIEF.md 生成 [FIN_BRIEF.md]
↓ checkpoint
阶段2: 文献综述 [LIT_REVIEW.md]
↓ checkpoint
阶段3: 想法生成 + 数据验证 [IDEA_REPORT.md]
↓【想法-数据交叉验证】← P1 强制检查点,不跳过
↓ checkpoint
阶段4: 新颖性验证 [NOVELTY_REPORT.md]
↓ checkpoint
阶段5: 实证方法设计 [REFINED_DESIGN.md]
↓ checkpoint
阶段6: 数据获取 [DATA_MANIFEST.md + data/*.csv]
↓ checkpoint
阶段7: 论文大纲 [PAPER_OUTLINE.md + FIGURE_PLAN.md]
↓ checkpoint
阶段8: 正文写作 [draft_v1/main.tex]
↓ checkpoint
阶段9: 图表生成 [draft_v1/figures/*.pdf]
↓ checkpoint
阶段10: 对抗性Review [REVIEW_REPORT.md]
↓ checkpoint
阶段11: LaTeX编译 [draft_v1/main.pdf]
↓ checkpoint
阶段12: 投稿前检查 [SUBMIT_CHECK_REPORT.md]
↓
最终输出: 可投稿论文 PDF + 完整研究包
核心原则:数据优先
数据验证必须在阶段3(想法生成)完成,不等到阶段6(数据获取)才发现无数据。
传统流程(有问题):
想法生成 → 新颖性验证 → 实证设计 → 数据获取 ← 到这里才发现无数据!
↓ ↓
浪费大量时间 不得不返回更换主题
改进流程(当前):
想法生成 → 【想法-数据交叉验证】→ 新颖性验证 → 实证设计 → 数据获取
↓ ↓
在此处检查数据可行性 数据已知可行,只需执行
无数据→立即告知用户 预先设计的获取方案
执行前的准备
系统准备(每次启动必须执行)
# 检查环境并初始化输出目录(PROJECT_DIR 自动取当前目录)
PROJECT_DIR="$(pwd)"
cd "$PROJECT_DIR" || exit 1
# 创建所有输出目录
mkdir -p \
output/fin-literature \
output/fin-ideas \
output/fin-novelty \
output/fin-refinement \
output/fin-experiments/data/finance \
output/fin-review/round_1 \
output/fin-manuscript/draft_v1/figures \
output/fin-manuscript/draft_v1/tables \
output/fin-manuscript/draft_v1/scripts
# 检查 Python 关键依赖
python3 -c "import json, yaml, pandas, numpy, matplotlib, seaborn, statsmodels; print('[✓] All Python deps OK')" 2>/dev/null \
|| echo '[!] Python deps missing — run: pip install pandas numpy matplotlib seaborn statsmodels pyyaml'
# 检查 LaTeX 编译器
for cmd in pdflatex xelatex bibtex; do
if command -v $cmd &>/dev/null; then
echo "[✓] $cmd"
else
echo "[!] $cmd not found"
fi
done
# 检查 Docker MCP 服务是否运行
for svc in mcp_eastmoney_reports mcp_financial mcp_enhanced_finance; do
if docker ps --format '{{.Names}}' | grep -q "^${svc}$"; then
echo "[✓] $svc running"
else
echo "[!] $svc not running"
fi
done
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 · 1,026 lines · 63 tokens per session scan A 5696fbdec7ea
fin-full-pipeline is a skill published in the GitHub repository csmar432/finai-research (100 stars, last pushed 3d ago), licensed MIT. It adds 63 tokens to every session and 8,111 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
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…