Loading...
Loading...
Found 836 Skills
Python backend testing patterns with pytest for FastAPI applications. Use when writing Python tests: unit tests for services and repositories, integration tests for API endpoints with httpx.AsyncClient, fixture creation, factory setup with factory_boy, async testing with pytest-asyncio, mocking strategies, and parametrized tests. Covers test organization (tests/unit, tests/integration), conftest hierarchy, and coverage requirements. Does NOT cover frontend tests (use react-testing-patterns) or E2E browser tests (use e2e-testing).
Build or extend a course outline in your format, from class notes and casebook. Scaffolds — it does not write the outline for you. Use when the user says "outline [subject]", "add to my outline", "build an outline from", or points at class materials.
This skill should be used when the user asks to "create an agent", "make an agent", "write an agent", "build a subagent", "add an agent to a plugin", "design an autonomous agent", "generate an agent file", "write a system prompt for an agent", "what frontmatter does an agent need", "create a specialized agent". Not for skills or commands — use create-skill.
HK IPO Subscription Analysis — A "Four-Dimensional Evaluation" framework to diagnose whether Hong Kong new stocks are worth subscribing (Pricing Rationality / Issue Quality / Market Timing / Fundamental Outlook). Outputs three-tier ratings: Recommend / Neutral / Avoid, plus prospectus highlights, risk warnings, and subscription references. It is retail-investor friendly with conclusions upfront. Covers three scenarios: in-depth evaluation of a single new stock, browsing recent IPO subscription calendars, and judging whether to chase newly listed stocks after missing the subscription. Prioritizes data from Longbridge CLI (ipo detail / ipo subscriptions / ipo wait-listing / ipo listed / peer-comparison / news / quote / kline / index-quote, etc.); uses MCP fallback for data missing from CLI; uses WebSearch as a last resort for data still unavailable (prospectus TAM, original cornerstone announcement, claw-back ratio, grey market price, underwriter industry ranking). **The report must end with a fixed "Data Source Details" appendix**, where every figure can be traced to line number + capture time + period. Only covers Hong Kong Main Board and GEM; does not involve US / A-share IPOs; must actively prompt leverage risks when margin financing (孖展) is involved. Triggers: "打新", "港股打新", "新股申购", "新股申購", "新股", "打新分析", "新股分析", "招股", "招股书", "招股書", "基石投资者", "基石投資者", "国际配售", "國際配售", "公开发售", "公開發售", "暗盘", "暗盤", "回拨机制", "回撥機制", "孖展", "新股盈亏", "新股盈虧", "次新股", "破发", "破發", "中签率", "中籤率", "新股几手", "新股幾手", "新股值不值得打", "新股能不能打", "港股 IPO 推荐", "港股 IPO 推薦", "近期港股新股", "HK IPO analysis", "hong kong IPO worth it", "HK new listing", "cornerstone investor", "prospectus highlights", "grey market premium", "subscription ratio", "claw-back", "margin financing IPO", "0700.HK", "09988.HK", "01024.HK"
ELI5-style explanations with analogies and multiple examples. Explains concepts at different levels (ELI5, high school, undergraduate, graduate). Uses real-world analogies and visual metaphors. Use when explaining difficult concepts, clarifying confusing topics, or learning new subjects. Triggers - explain concept, ELI5, explain like I'm 5, what is, how does, why does, analogy for, simple explanation.
Use when the user asks "what predefined metrics are available", "which built-in metrics should I use", "what does CSAT measure", "how does hallucination detection work", "what's the difference between Interruption Score and AI Interrupting User", "which metrics are free", "which metrics need audio", "configure silence threshold", "set up sentiment metric", or any question about Cekura's out-of-the-box metrics. Covers the full catalog of predefined metrics — what each does, costs, constraints, configuration options, and when to use each one.
Fetch raw OHLCV price data using the aipa CLI. Use this skill whenever the user asks for price data, candle data, OHLCV data, historical prices, stock quotes, crypto prices, moving averages, volume data, or any raw market data without AI analysis. Also use for: top performers, worst performers, best stocks, top gainers, biggest losers, market movers, ranking tickers by price change / volume / value / MA scores / money flow (`aipa performers`); volume profile, POC, point of control, value area, support/resistance by volume, volume-by-price histogram (`aipa volume-profile`). Also use for fundamental data: company info, financial ratios, PE, PB, ROE, NPL, CAR, fundamental ranking and screening (`aipa fundamentals info/ratios/rank/screen`). Also use when the user wants to inspect what data is available, build charts, perform their own calculations, or get numbers for a spreadsheet. Even if the user doesn't mention "aipa", trigger this skill for any raw financial data, fundamental data, or market ranking request.
Internal sub-skill for job-hunt suite. Performs STAR decomposition of resume and scores JD-resume match across 4 dimensions. Does NOT generate tailoring suggestions (handled by tailor). Do NOT invoke directly — use the job-hunt main skill instead.
Generate a pull request subject line and a concise description by analyzing the commits and diff on the current local git branch. Use this whenever the user is preparing a PR and wants help writing its title or body — phrases like "write a PR description", "summarize my changes for a PR", "what should the PR title be", "draft the PR for this branch", or "describe these commits". Trigger even if the user doesn't say the exact words "pull request" but is clearly wrapping up branch work and wants it summarized for review. This skill only reads git locally and prints the result for the user to copy — it never pushes or edits anything on GitHub.
Owns the smoke test contract for an ML experiment: a small, diagnostic-by-construction pytest that fits the experiment's learner on a portion of the real `data/` source and predicts on a *disjoint* portion that deliberately carries **no pre-history buffer**. The assertion is structural — the number of predictions must equal the number of rows in the predict grid. A pipeline that loads-then-features-then-splits will silently drop the cold-start rows of the predict slice and the test will fail with a row-count mismatch; a pipeline that marks X early and references upstream history nodes from feature steps will pass trivially. The smoke test is the executable proof of the X-marker placement rule from `build-ml-pipeline`. TRIGGER when: `test-ml-pipeline` has dispatched here to write the smoke test for an approved experiment; `pytest tests/smoke/` is failing on row count; the user asks "why is the smoke test failing?"; a pipeline edit in `build-ml-pipeline` needs an executable proof; an experiment script changes the pipeline shape and the matching smoke test needs revisiting. SKIP when: the design note does not exist or is not yet approved (route to `iterate-ml-experiment`); the user is asking about a regression test or schema invariant (route to `regression-test-ml-pipeline` / `distribution-test-ml-pipeline` once those exist); the question is the *interpretation* of CV metrics, not predict-time correctness (route to `evaluate-ml-pipeline`). HOW TO USE: read the matching experiment's `journal/NN_*.md` and `experiments/NN_*.py` first to understand the pipeline's source binding (what env-dict keys does `build_learner` expect?). Then construct two env-dicts from the **real `data/` source** — a train env and a predict env — such that the predict env carries *only the rows we want predictions for* and *no pre-history buffer*. The hard assertion is that the prediction count matches the predict-env row count exactly. The soft assertion is that the smoke set's MAE is within `3 × CV_mean` (or the task-appropriate analogue). **Do not write the design note or run CV — that's other skills' job.**
Interactive prompt studio for HappyHorse 1.0 video generation. Guides users through scenario discovery with vivid examples, then assembles production-ready prompts in JP/CN/EN. Use when someone wants to create AI video content with HappyHorse but doesn't know where to start, or when they have a specific scenario and need a polished prompt. Covers manga drama, character PV, manga motion, virtual idol MV, and free-form scenarios.
Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /hui-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers.