Claude Code Skills Marketplace is a collection and marketplace of skills, plugins, agents, and instructions that extend Claude Code with specialized development workflows. It is for developers who want to install existing workflows or create, validate, and package their own Claude Code skills.
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 daymade/claude-code-skills --skill daymade-sector-researchgit clone --depth 1 https://github.com/daymade/claude-code-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/daymade/claude-code-skills/daymade-sector-research)<a href="https://agentmods.dev/skills/daymade/claude-code-skills/daymade-sector-research"><img src="https://agentmods.dev/badge/skills/daymade/claude-code-skills/daymade-sector-research/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/daymade/claude-code-skills/daymade-sector-research"><img src="https://agentmods.dev/badge/skills/daymade/claude-code-skills/daymade-sector-research.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 | $0.00358 | $0.02711 |
| Opus 5 | $0.00179 | $0.01355 |
| Sonnet 5 | $0.00072 | $0.00542 |
| Haiku 4.5 | $0.00036 | $0.00271 |
Grade A, and why
daymade-sector-research scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 国内站点（东财/新浪/巨潮）curl/脚本必须去代理：`env -u http_proxy -u https_proxy -u all_proxy -u HTTP_PROXY -u HTTPS_PROXY -u ALL_PROXY` How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A股行业投研 Skill
对某个申万行业/东财板块做一次完整投研交付：Top N 涨幅标的 → 公告窗口检索 → 市场情绪判断 → Agent Team 对抗验证 → 综合报告。
铁律（每次执行都必须遵守，违反代价最高）
- 宁可标注不确定，不可给错误答案（用户原话，最高纪律）。没有十足把握的事实写「不确定/未核实」，不编、不猜、不省略来源。推断与观察必须分开表述。
- 基于证据、基于数据。每个结论 trace 到一手数据源（API 返回 / CSV 落盘 / 官方公告）；汇报数值时从工具输出原文照抄，禁凭印象转写。
- 证据分级 L1–L3：L1 一手行情（交易所/行情接口实时值）；L2 带时间戳的媒体/公告报道；L3 未核实标题或传闻。判断情绪时只允许 L1/L2 承重，L3 只能作为「待核实线索」列出。
- 0 条双向读：月窗口公告 0 条 ≠ 真无公告。必须扩宽窗（90 天）+ 第二数据源核对，证明「真无」或发现参数错误，才能下结论。
- 双源交叉：公告检索必须巨潮 + 东财两源对照；单一数据源发现的「重要公告」也要在另一源确认存在，不一致必须如实标注。
- 盘中快照标注漂移：盘中取的行情数值是瞬时快照会漂移，任何引用必须带快照时间戳，报告里注明「盘中快照」。
- 数值照抄落盘 CSV：中间数值必须落盘（脚本输出 CSV / agent 落盘文件），报告引用时照抄 CSV 值，不凭对话记忆。
- Agent Team 编排纪律：见 references/agent-orchestration.md——子代理显式
model:'sonnet'；SendMessage 交付协议；每条 finding 带可证伪锚点；验证用 fresh-context 对抗性 agent；禁 spawn 重复 agent。
工作流（五阶段）
Phase 0 数据能力侦察 → 必要时 pivot 公开源
Phase 1 并行三 agent：Top N 名单 / 涨跌幅分桶分布 / 情绪证据清单
Phase 2 公告检索：Top N 全标的 × 周窗口 + 月窗口，双源交叉
Phase 3 对抗验证：fresh-context agent 复核假设（用户原话：「看哪些假设是错的」）
Phase 4 综合报告：名单 + 公告 + 情绪分级 + 显式不确定标注
Phase 0 — 数据能力侦察（Gangtise pivot 决策）
若用户点名 Gangtise（或其官方 skill），先侦察可用性再决定数据源：
- 对照实验判「额度」：同一凭据某些端点可用（如
quote.py、stockpool.py、get_industries.py）而内容搜索端点全报POINT_NOT_ENOUGH→ 这是积分不足的整体性解释，同一凭据一通一挂已否定「网络/配置问题」；若不同端点表现不一致，别急着下「额度耗尽」结论，做对照实验（换端点/换参数/最小请求）。 - pivot 决策表：内容搜索不可用 → Top N 改东财成分股+新浪快照；公告改 cninfo+东财；情绪改公开行情+媒体。侦察结论与 pivot 决策必须告知用户，不静默切换数据源。
- 完整侦察矩阵（各端点实测形态、积分报错、对照实验）→ references/gangtise-scout.md
Phase 1 — 并行三 agent
派 3 个并行 agent（显式 sonnet），每个 prompt 附可证伪锚点要求：
| Agent | 交付物 | 数据链 |
|---|---|---|
| Top N 名单 | top{N}_{board}_{日期}.csv |
scripts/top_n_pipeline.py（东财成分股 → 新浪快照 → 涨幅排序） |
| 涨跌分桶分布 | distribution_{board}_{日期}.csv + 市场宽度结论 |
全板块快照按 6 分桶（>5%/2-5%/0-2%/0%/-2-0%/<-2%）+ up/down/flat 汇总，六桶 count 加和必须等于 total |
| 情绪证据清单 | 分层证据表（L1/L2/L3 各列） | 一手行情 + 媒体检索 |
行情与板块接口细节 → references/market-data.md；情绪证据方法与信源 → references/sentiment-evidence.md。
What ships with it
7 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 · 110 lines · 358 tokens per session scan A 77e6c5cfe27f
daymade-sector-research is a skill published in the GitHub repository daymade/claude-code-skills (1,384 stars, last pushed yesterday), licensed MIT. It adds 358 tokens to every session and 2,711 once invoked, about $0.0018 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.