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 serejaris/kimi-skills --skill financial-report-readergit clone --depth 1 https://github.com/serejaris/kimi-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/serejaris/kimi-skills/financial-report-reader)<a href="https://agentmods.dev/skills/serejaris/kimi-skills/financial-report-reader"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/financial-report-reader/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/serejaris/kimi-skills/financial-report-reader"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/financial-report-reader.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 | $0.00154 | $0.02434 |
| Opus 5 | $0.00077 | $0.01217 |
| Sonnet 5 | $0.00031 | $0.00487 |
| Haiku 4.5 | $0.00015 | $0.00243 |
Grade A, and why
financial-report-reader 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 9d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
财报三表解读 — 同比环比 + 异常检测
对企业利润表、资产负债表、现金流量表进行结构化分析:自动计算同比(YoY)/ 环比(QoQ)变动,运行多维度异常检测规则(应收暴增、现金流背离利润、存货积压、毛利率突变等),输出可读报告。
能力概览
| 能力 | 说明 |
|---|---|
| 同比分析(YoY) | 对比同期数据(如 2024Q1 vs 2023Q1),识别趋势变化 |
| 环比分析(QoQ) | 对比相邻期间数据(如 2024Q2 vs 2024Q1),捕捉短期波动 |
| 财务比率 | 毛利率、净利率、资产负债率、流动比率、应收周转天数等 |
| 异常检测 | 10 项规则自动扫描,输出风险等级和解读说明 |
Quick Start
# 基本用法:分析 JSON 格式的财务数据
python scripts/analyze_financials.py data.json
# 输出 JSON 格式结果
python scripts/analyze_financials.py data.json --json
# 导出到文件
python scripts/analyze_financials.py data.json --output report.json
# 生成示例数据文件(用于测试)
python scripts/analyze_financials.py --sample > sample_data.json
# 自定义异常检测阈值
python scripts/analyze_financials.py data.json --ar-threshold 0.25 --ocf-ratio 0.4
输入数据格式
脚本接受 JSON 文件,格式如下:
{
"company": "示例公司",
"currency": "CNY",
"unit": "万元",
"periods": ["2023Q1","2023Q2","2023Q3","2023Q4","2024Q1","2024Q2","2024Q3","2024Q4"],
"income_statement": {
"revenue": [5000, 5200, 4800, 6000, 5500, 5800, 5100, 6500],
"cost_of_revenue": [3000, 3100, 2900, 3500, 3400, 3600, 3200, 4100],
"operating_income": [800, 850, 750, 1000, 780, 820, 700, 900],
"net_income": [600, 650, 560, 780, 580, 620, 520, 680]
},
"balance_sheet": {
"accounts_receivable": [2000, 2100, 2200, 2300, 2800, 3200, 3600, 4200],
"inventory": [1000, 1050, 1100, 1200, 1100, 1150, 1200, 1300],
"total_current_assets": [5000, 5200, 5400, 5800, 6000, 6500, 7000, 7500],
"goodwill": [500, 500, 500, 500, 500, 500, 500, 500],
"total_assets": [15000, 15500, 16000, 16500, 17000, 17500, 18000, 18500],
"accounts_payable": [1500, 1600, 1550, 1700, 1650, 1750, 1700, 1800],
"total_current_liabilities": [4000, 4200, 4100, 4500, 4300, 4600, 4500, 4900],
"total_liabilities": [8000, 8200, 8400, 8600, 8800, 9000, 9200, 9500],
"total_equity": [7000, 7300, 7600, 7900, 8200, 8500, 8800, 9000]
},
"cash_flow": {
"operating_cash_flow": [700, 750, 620, 850, 300, 280, 250, 200],
"investing_cash_flow": [-200, -180, -250, -300, -400, -350, -300, -280],
"financing_cash_flow": [-100, -50, -80, -120, 200, 150, 100, 50],
"capex": [180, 160, 230, 280, 380, 330, 280, 260]
}
}
What ships with it
2 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.
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.
- 9d ago First seen · 157 lines · 154 tokens per session scan A 68ecc63a68f2
financial-report-reader is a skill published in the GitHub repository serejaris/kimi-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 154 tokens to every session and 2,434 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
fiscaliste
Fiscaliste IA pour la fiscalité personnelle des particuliers français : optimisation et déclaration de l'impôt sur le revenu, IFI, revenus du capital, revenus fonciers, equity salarial, crypto-actifs et PER. Couvre le calcul de l'IR (barème, quotient familial, décote, PAS, CEHR, revenus exceptionnels), la déclaration…
controleur-fiscal
Inspecteur des finances publiques IA. Simule un contrôle fiscal DGFIP complet sur les comptes d'une entreprise française (SASU, EURL, SAS, SARL). Analyse le FEC, la liasse fiscale, les charges déduites, le compte courant d'associé, la TVA, l'IS selon 8 axes de vérification. Identifie les chefs de redressement…
commissaire-aux-comptes
Commissaire aux comptes IA pour l'audit des comptes annuels d'entreprises françaises. Applique la démarche NEP en 7 phases : prise de connaissance, contrôle du FEC, vérification du bilan, du compte de résultat, de la balance, de la liasse fiscale, et contrôles transversaux. Émet une opinion motivée sur la fiabilité…
invest-setup
A first-time setup workflow for openInvest, a system for tracking investments and running portfolio analysis.
metengine-data-agent
Real-time smart money analytics API for Polymarket prediction markets, Hyperliquid perpetual futures, and Meteora Solana LP/AMM pools. 63 endpoints. Pay-per-request via x402 on Solana Mainnet USDC. No API keys.
meteora
Complete Meteora DeFi SDK suite for building liquidity pools, AMMs, bonding curves, vaults, token launches, and zap operations on Solana. Use when integrating DLMM, DAMM v2, DAMM v1, Dynamic Bonding Curves, Alpha Vaults, Zap, or Stake-for-Fee functionality.