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 huangrichao2020/pretty-skills --skill a-share-swing-snipergit clone --depth 1 https://github.com/huangrichao2020/pretty-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/huangrichao2020/pretty-skills/a-share-swing-sniper)<a href="https://agentmods.dev/skills/huangrichao2020/pretty-skills/a-share-swing-sniper"><img src="https://agentmods.dev/badge/skills/huangrichao2020/pretty-skills/a-share-swing-sniper/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/huangrichao2020/pretty-skills/a-share-swing-sniper"><img src="https://agentmods.dev/badge/skills/huangrichao2020/pretty-skills/a-share-swing-sniper.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 | $0.00278 | $0.05543 |
| Opus 5 | $0.00139 | $0.02772 |
| Sonnet 5 | $0.00056 | $0.01109 |
| Haiku 4.5 | $0.00028 | $0.00554 |
Grade A, and why
a-share-swing-sniper 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 today.
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 — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A 股尾盘短线狙击 (a-share-swing-sniper)
核心：用 4 步法把"尾盘选股 → 次日冲高跑路"跑成可重复流水线。 不做：中长线 / 主题投资 / 追首板 / 求是 9 大 / SMC 4 层漏斗。 数据源：akshare 优先（跟 aliyun info-hub 一致），tushare 备选。
0 · 触发场景
| 类别 | 触发词 |
|---|---|
| 选股 | 尾盘选股 / 7 条件 / 筹码分歧回补 / 缩量企稳放量回补 |
| 分析 | 4 维度 / 板块景气 / 资金面 / 基本面 / 消息面 / 主力成本线 |
| 操作 | 竞价抢筹 / 高开 3-5% / 放量滞涨 / 跌破 5 日线 / 主力净流出 |
| 风险 | 接盘防御 / 鱼尾 / 接刀 / 主力净流出 + 散户净流入 / 尾盘偷袭 |
| 过滤 | 季节×chip / 鱼头鱼身鱼尾 / A/B+/B/C/D/E 分级 / 接刀线 85% |
用户给具体股票/事件/关键词 → 直接进 4 步法。
1 · 4 步法（必走，不跳步）
[Step 1 · 14:30 尾盘选股]
7 条件筛选（筹码分歧回补型）→ 排除涨停 → 按资金面排序
↓
[Step 2 · 14:50 4 维度分析]
板块 × 资金 × 基本面 × 消息面 = 4 维评分（0-4 分）
≥3 维 = 短线冲高型 ★ | 4 维 = 持续行情型
↓
[Step 3 · 次日 9:15-9:25 竞价抢筹]
3 情景：🟢 乐观（高开 3-5%）/ 🟡 中性（平开）/ 🔴 悲观（低开 2%+）
↓
[Step 4 · 9:30 开盘后执行]
买入：竞价抢筹 + 站稳主力成本线 + 主力净流入（3 条 AND）
卖出：放量滞涨 / 破 5 日线 / 主力净流出（3 选 1）
止盈：主力成本 + 压力位突破后 → 前高
止损：跌破 5 日线 或 主力成本线
时间窗口：
| 时间 | 动作 |
|---|---|
| 14:30-14:50 | Step 1 选股 |
| 14:50-15:00 | Step 2 4 维分析 |
| 15:00 收盘 | 确认 3-5 只候选 |
| 次日 9:15-9:25 | Step 3 竞价判断 |
| 9:30-10:00 | Step 4 开盘观察 |
| 10:00-14:30 | 盘中监控（3 选 1 触发即卖） |
| 14:30-15:00 | 尾盘评估（次日是否继续持有 / 止盈 / 止损） |
2 · Step 1 · 7 条件选股（筹码分歧回补型 · 核心）
核心形态："缩量企稳 + 放量回补" —— 昨日缩量说明卖盘枯竭，今日放量说明资金重新介入，涨幅克制说明资金以吸筹为主而非情绪炒作。
| # | 条件 | 阈值 | 数据源（akshare） |
|---|---|---|---|
| 1 | 前日获利比例 | > 50% | stock_cyq_em × 2 天前 |
| 2 | 昨日获利比例 | < 50% | stock_cyq_em × 昨天 |
| 3 | 昨日成交量 | < 5 日最大 × 50% | stock_zh_a_hist |
| 4 | 今日获利比例 | > 50% | stock_cyq_em |
| 5 | 今日放量 | 是（今日量 > 昨日量 × 1.2） | stock_zh_a_hist |
| 6 | 今日涨幅 | ≤ 7% | stock_zh_a_spot_em |
| 7 | 板块 | 主板（沪 60/00/30 + 深 00） | 股票代码前缀 |
任一不满足 → 排除（不打折）
执行脚本：scripts/stock_filter.py
3 · Step 2 · 4 维度分析（0-4 分）
| 维度 | 权重 | 核心指标 | 阈值 |
|---|---|---|---|
| 板块景气度 | 中 | 政策 + 订单 + 价格 三选一上行 | 满足 2/3 = 1 分 |
| 资金面 | ★ 最高 | 5 日主力净流入 + 量比 + 换手率 | 满足 3 项 = 1 分 |
| 基本面 | 中 | 营收 + 净利 + 毛利率 | 满足 3 项 = 1 分 |
| 消息面 | 低 | 公告 + 业绩说明会 + 研报 | 满足 2 项 = 1 分 |
What ships with it
17 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.
- examples/zhongtian-600522-2026-09-11.md 6.5 KB
- manifest.json 6.4 KB
- placeholder-config.json 826 B
- README.md 4.3 KB
- references/4-dim-analysis.md 6.8 KB
- references/7-conditions.md 6.7 KB
- references/9-4-case.md 5.0 KB
- references/auction-strategy.md 7.1 KB
- references/risk-control.md 8.3 KB
- scripts/auction_check.py 6.2 KB runs code
- scripts/dim_analyzer.py 7.4 KB runs code
- scripts/scheduled_run.sh 2.2 KB runs code
- scripts/stock_filter.py 8.8 KB runs code
- templates/4-dim-template.md 5.2 KB
- templates/auction-signal-template.md 6.2 KB
- templates/select-workflow.md 3.5 KB
- templates/trade-record.md 4.7 KB
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.
- today First seen · 341 lines · 278 tokens per session scan A f5cd529cd8c2
a-share-swing-sniper is a skill published in the GitHub repository huangrichao2020/pretty-skills (54 stars, last pushed today), licensed MIT. It adds 278 tokens to every session and 5,543 once invoked, about $0.0014 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 2026-09-12.
Other skills, from other repositories
german-elster-tax-filing
Use this skill to run a complete intake for a german personal income tax return in elster for tax years 2024 onward, estimate the tax result, and map the final values into the correct official forms and fields.
cn-check
Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.
aomi-transact
Build natural-language crypto/DeFi agents and EVM MCP plugins (Claude Code, Cursor, Codex, Gemini). Aomi turns prompts into wallet-signed txs on Ethereum, Base, Arbitrum, Optimism, Polygon, Linea — non-custodial, fork-simulated. 40+ apps: Uniswap, Aave, Lido, Morpho, GMX, Hyperliquid, Polymarket.
fred-economic-data
Query FRED (Federal Reserve Economic Data) API for 800,000+ economic time series from 100+ sources. Access GDP, unemployment, inflation, interest rates, exchange rates, housing, and regional data. Use for macroeconomic analysis, financial research, policy studies, economic forecasting, and academic research requiring…
tinker-training-cost
Calculates training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.
story-long-write
A Chinese-language coaching workflow for creating a long online novel from the initial idea through the outline and chapter text. It starts by defining the intended emotion, then uses research and story-planning stages to guide writing.