GITHUB AGENT SKILLS / 技能收录
给你的 AI 助手
装上专业技能
我们从 GitHub 持续收录、审核并分类优质的 Agent Skills,按职业与使用场景整理,复制一行命令即可安装到 Claude Code、Cursor 等智能体。
按职业浏览 Agent Skills
为不同岗位挑选的高频技能
按使用场景浏览 Agent Skills
从你要完成的任务出发
按创作者浏览 Agent Skills
按 GitHub Stars 排序的优秀创作者
Microsoft
@microsoftopenclaw
@openclawAnthropic
@anthropicsOpenAI
@openaiThe Apache Software Foundation
@apacheGitHub
@githubAutoGPT
@Significant-GravitasGarry Tan
@garrytan全部 Skills 482556
options-positioning
Dealer gamma exposure by strike, call and put walls, the gamma flip level, max pain, put-call ratios, and volatility smile geometry including at-the-money implied volatility, 25-delta risk reversal, butterfly, skew slope and the implied expected move. Use when the user asks where the walls are, whether dealers are long or short gamma, what the gamma flip level is, where max pain sits, what the put-call ratio is, how steep the skew is, what the market implies for a move, or asks about positioning and dealer hedging. This is chain-wide geometry rather than per-contract Greeks. Not for order placement and not for recommendations.
options-lean
Export fixed option legs to a local LEAN backtest bundle or import completed tagged results. Use when handing a plan to a historical engine, not modeled-premium strategy backtests.
options-greeks
Retrieve an approved or user-provided option chain and compute the full first to third order Greek ladder (delta, gamma, vega, theta, rho, lambda, vanna, vomma, charm, veta, speed, zomma, color, ultima, dual delta, dual gamma) for any US listed underlying. Use when the user asks about option Greeks for individual contracts, an option chain, a Greek by strike or expiry, theta decay, vega risk, or how one strike compares with another. For dealer gamma exposure, the walls, the gamma flip or the skew across a whole chain, use options-positioning instead. Not for order placement and not for recommendations.
options-backtest
Test an option structure against real price history with modelled premiums, and run a paper forward test that records positions before their outcome is known and marks them against later chains. Reports win rate, mean return on capital at risk, drawdown, a permutation test, a bootstrap interval and a buy-and-hold benchmark. Use when the user asks whether a strategy has worked historically, to backtest or forward test something, whether an edge is real or chance, how a structure performed, or asks to paper trade, track a position, or mark a trade. Not for order placement and not for recommendations, and a backtest result is not a forecast.
desk-setup
Install and verify the option desk command line tools so the option_* MCP tools and the optiondesk commands actually work. Use when a desk skill reports that no fresh figures can be produced, when optiondesk is not found, when the MCP tools are missing or failing, when the plugin was installed but nothing runs, or when the user asks how to set this up. Not for analysing options; it only gets the tools working.
actera-status
Show the Actera connection, mode, evaluation-failure behavior, whether the hooks run, and report delivery.
review-study
Review a QuestionPunk survey before launch for wording, answer choices, branching, and missing settings. Use for check my survey or review this draft before publishing.
manage-study
Find QuestionPunk studies, check status, publish an explicitly requested draft, or retrieve its participant link. Use for find my survey, publish this study, or how many people responded.
create-study
Create a saved QuestionPunk survey draft from a research brief or edit specified questions. Use for requests such as make a customer feedback survey or shorten my onboarding study.
analyze-results
Analyze QuestionPunk survey results with response counts, aggregate reports, segment comparisons, and supporting quotes. Use for summarize findings, compare segments, or export survey responses.
customize
Show every setting, template and catalog entry on one screen, and change only what the owner names.
pixeltable
Multimodal RAG over PDFs, web pages, Office files, images, and video; video search; image similarity search; frames, detection, captions; embeddings and vector search stored with your data; audio transcription, podcast summaries; a multimodal agent with tools; agent memory; incremental ML and data pipelines; dataset versioning. One Python backend: tables, computed columns that call models, embedding indexes, incremental updates, versioning, and HTTP. Create tables with pxt schema update. Serve with pxt service update. Use instead of LangChain, pandas-as-store, or a separate vector DB. Use when building RAG or a multimodal agent with tools, processing images/video/audio/documents, or serving an API. Do NOT use for general Python or direct PostgreSQL administration.
package-trust-check
Investigate whether one specific npm package is trustworthy — maintainer/ownership takeover signals, publish-provenance mismatches, and risky install scripts. Use when the user asks if a single named package is safe, compromised, hijacked, suspicious, or "can I trust this" — not for auditing a full package.json/lockfile (see dependency-audit) and not for a plain factual question like "what does X do."
new-dependency-evaluation
Help decide what to add as a NEW npm dependency — comparing 2-5 named candidates for the same job, evaluating one named candidate against its real peers, or shortlisting candidates from a described need, before anything is installed. Use for "which should we use for X," "axios vs got vs node-fetch," "is X a good pick for Y," "what should we use to do Z," "should we add X or is there something better." Not for auditing packages already in the project (see dependency-audit), not for a deep single-package compromise/trust investigation (see package-trust-check), and not for a plain factual question with no choice being made ("what does X do").
incident-response
Turn a flagged npm supply-chain finding — or just a vague, non-technical description of one ("this package looks sketchy," "someone said we got hacked," "npm install did something weird") — into concrete remediation steps. Use whenever the user wants to know what to actually do about a suspicious/compromised/flagged package, however precisely or vaguely they describe it — not for the initial trust/vulnerability investigation itself (see package-trust-check/dependency-audit for that).
dependency-audit
Audit a project's npm dependencies for known vulnerabilities and risky install scripts before installing, upgrading, or shipping. Use when the user pastes or attaches a package.json/lockfile, lists dependencies, or asks to check/audit/scan their packages for security issues — including comparing two snapshots (a PR diff) or checking license compliance.
ci-pr-gate
Turn a dependency change — a before/after package.json/lockfile snapshot, or one or more named "bump X from A to B" upgrades — into one deterministic PASS/WARN/FAIL verdict formatted for a CI check or PR-comment bot, not a conversational report. Use when the user explicitly wants a mergeable/blocking verdict, a "CI gate," a PR status comment, or asks "should this PR be blocked," "is this safe to merge," "gate this dependency bump." Not for a plain explanation of what changed in a diff (dependency-audit's own snapshot-diff flow already covers that conversationally) and not for a single already-installed package's trust investigation (package-trust-check).
fair-value-calculator
Look up what a listed stock is worth (fair value per share, valuation verdict, quality score, uptrend), compare and screen stocks, and read or change the signed-in watchlist, using the Fair Value Calculator tools. Use when a question is about a stock's fair value, whether a stock looks cheap or expensive, finding undervalued stocks, or the user's Fair Value Calculator watchlist.