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 idea2realClaw/myAgent --skill a-stock-limit-upgit clone --depth 1 https://github.com/idea2realClaw/myAgentWrote 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/idea2realclaw/myagent/a-stock-limit-up)<a href="https://agentmods.dev/skills/idea2realclaw/myagent/a-stock-limit-up"><img src="https://agentmods.dev/badge/skills/idea2realclaw/myagent/a-stock-limit-up/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/idea2realclaw/myagent/a-stock-limit-up"><img src="https://agentmods.dev/badge/skills/idea2realclaw/myagent/a-stock-limit-up.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 | $0.00000 | $0.02052 |
| Opus 5 | $0.00000 | $0.01026 |
| Sonnet 5 | $0.00000 | $0.00410 |
| Haiku 4.5 | $0.00000 | $0.00205 |
Grade A, and why
a-stock-limit-up 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 10d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A股涨停板分析Skill (v6)
功能说明
获取A股涨停板数据，仅分析第一次涨停的股票（自动过滤连板股），进行客观评分，生成复盘报告。
核心特点 (v6更新)
- 三维度评分体系 — 封板强度(40分) + 换手健康(30分) + 行业赛道(30分)
- 智能连板过滤 — 优先通过API获取连续涨停天数，回退到本地历史，确保只分析首板
- 行业赛道评分 — S/A/B/C四级赛道，当前市场主线（如锂电、算力）给予最高权重
- 区分科创板/创业板 — 统一评分但仓位更保守（20cm波动风险）
- 两阶段流程 — 盘中只做过滤，收盘后才做完整分析
- 纯客观评分 — 基于真实数据评分，不使用预测胜率
连板过滤策略（v6核心改进）
优先方案：API实时查询
- 通过东方财富API批量查询每只股票的
f128（连续涨停天数）和f136（连板标记） - 连续涨停天数 >= 2 的股票自动标记为连板股，排除出评分范围
- 20线程并发查询，30秒超时
回退方案：本地历史记录
- 当API查询失败时，使用
limit_up_history.json记录的昨日涨停数据 - 如果昨天涨停过且今天又涨停，则标记为连板
- 历史过期时（跨周末/假期）跳过过滤
过滤原则
- 宁留勿误删：API查不到的股票默认保留（不误删首板）
- 明确输出：打印被过滤的连板股列表
⚠️ 两阶段执行规则
阶段一：盘中过滤（9:35 - 15:00）
- 触发时机：开盘后30分钟内
- 执行内容：获取涨停列表 → 过滤连板 → 初步评分 → 输出TOP5简报
- 不生成完整复盘报告，不给买卖建议
阶段二：收盘完整分析（15:05 之后）
- 触发时机：收盘后5分钟
- 执行内容：获取最终数据 → 过滤连板 → 完整评分 → 深度分析 → 生成报告
- 包含：评分表、TOP10深度分析、操作建议、仓位建议
时间判断逻辑
当前时间 < 9:30 → 不执行（盘前）
9:30 ≤ 时间 ≤ 15:00 → 阶段一（盘中过滤简报）
时间 > 15:05 → 阶段二（收盘完整分析）
15:00 < 时间 ≤ 15:05 → 等待（数据可能未完全更新）
评分标准（100分制，三维度）
维度一：封板强度（满分40分）
核心：封单金额 / 流通市值 = 封单力度
| 封单力度 | 分数 | 说明 |
|---|---|---|
| ≥ 15% | 40 | 极强，主力封板决心大 |
| ≥ 10% | 35 | 很强 |
| ≥ 7% | 30 | 强 |
| ≥ 5% | 25 | 较强 |
| ≥ 3% | 20 | 中等 |
| ≥ 2% | 15 | 一般 |
| ≥ 1% | 10 | 偏弱 |
| < 1% | 5 | 极弱，封板不牢 |
维度二：换手健康（满分30分）
主板
| 换手率 | 分数 | 说明 |
|---|---|---|
| 3% - 8% | 30 | 最佳区间，筹码交换充分 |
| 2-3% 或 8-12% | 22 | 尚可 |
| 1-2% 或 12-20% | 15 | 偏高/偏低 |
| > 20% 或 < 1% | 5 | 异常 |
科创/创业板（放宽）
| 换手率 | 分数 | 说明 |
|---|---|---|
| 5% - 15% | 30 | 最佳区间（科创波动大） |
| 3-5% 或 15-25% | 22 | 尚可 |
| 1-3% 或 25-35% | 15 | 偏高/偏低 |
| > 35% | 5 | 异常 |
维度三：行业赛道（满分30分）
基于股票所属概念板块的热度评分
| 赛道等级 | 分数 | 当前包含的赛道 |
|---|---|---|
| S级 | 30 | 锂电/储能/锂矿/固态电池、算力/CPO/光模块/AI芯片/玻璃基板/先进封装 |
| A级 | 25 | 半导体/芯片设备/光刻胶/稀土/钨/机器人/具身智能/商业航天/光伏/风电 |
| B级 | 20 | 消费电子/医药/创新药/CXO/汽车/智能驾驶/数字经济/军工/PCB/覆铜板/食品/美妆 |
| C级 | 10 | 房地产/银行/纺织/钢铁/煤炭/传媒/农业/物流/公用事业 |
| 未知 | 15 | 无概念标签 |
⚠️ 赛道等级根据市场热点动态调整。当前S级以锂电和算力为主线。
What ships with it
13 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.
- limit_up_data.db 0 B
- references/data_source.md 18 B
- scripts/fetch_and_analyze_20260528.py 6.3 KB runs code
- scripts/fetch_limit_up.py 23 KB runs code
- scripts/generate_report.py 13 KB runs code
- scripts/intraday_simple.py 4.7 KB runs code
- scripts/kelly_bet.py 5.9 KB runs code
- scripts/limit_up_db.py 15 KB runs code
- scripts/limit_up_history.json 194 KB
- scripts/objective_score.py 14 KB runs code
- scripts/run_analysis.py 14 KB runs code
- scripts/stock_deep_analysis.py 26 KB runs code
- scripts/top_stock_tracker.py 15 KB runs code
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.
- 10d ago First seen · 167 lines · 0 tokens per session scan A 9250f13f502e
a-stock-limit-up is a skill published in the GitHub repository idea2realClaw/myAgent (2 stars, last pushed 21d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,052 tokens. 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 2026-08-31.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.