技能雷达 · GITHUB

值得安装的 Agent Skills。

汇总公开仓库中已验证的 Skills。安装前先看清它能做什么、包内包含什么、热度如何，以及来源是否可靠。

目录范围: 已验证
Skills: 10,772
仓库: 1711
最近同步: 2026年9月23日

10,772 Skills

adapty-integration

Use when a user wants to integrate Adapty SDK into a mobile app, set up in-app purchases with Adapty, add a paywall to their app, or move to Adapty from another purchase system. Triggers on "integrate Adapty", "add Adapty to my app", "set up subscriptions", "add a paywall", "migrate from RevenueCat", "replace RevenueCat with Adapty", "move off Superwall", or similar.

安装量: 1
GitHub Stars: 6
最近更新: 9月10日

查看详情 →

sumsub-create-cross-check-preset

Create or update a Sumsub cross-check preset (name/address comparison rules between POI and POA documents) via POST/PATCH /resources/api/agent/crossCheckPresets and GET /resources/api/agent/crossCheckPresets/{id}. TRIGGER ONLY when the user EXPLICITLY asks to override how cross-checks compare names or addresses — e.g. "switch name match to strict", "allow fuzzy address match", "ignore middle-name mismatch", "create a custom cross-check preset". SKIP by default — Sumsub ships sensible defaults tuned for the best conversion and approval rate, so most clients should NOT create a custom preset. SKIP for level creation (the default cross-check preset auto-applies to every level), for general KYC config, or any request that doesn't specifically name "cross-check rules", "name comparison", or "address comparison".

安装量: 1
GitHub Stars: 6
最近更新: 9月3日

查看详情 →

sumsub-create-level

Create or update a Sumsub applicant level. POST /resources/applicants/-/levels to create new, PATCH same path to update (id in body), GET /resources/applicants/-/levels/{id} to read one back. TRIGGER when the user asks to "create / add / build / update / edit a Sumsub level", supplies a list of required steps for an applicant flow (identity / selfie / proof-of-residence / questionnaire / payment methods / email or phone verification / KYB / e-sign), or wants a level wired to a specific questionnaireDefId. SKIP for other Sumsub entities (questionnaires, workflows, applicants) or for one-off subsetting tweaks not covered by the compact spec (use sumsub-api-generic for those).

安装量: 1
GitHub Stars: 6
最近更新: 9月3日

查看详情 →

sumsub-integrate-travel-rule

End-to-end recipe for integrating Sumsub Travel Rule — deciding which of the three exchange flows applies, identifying the counterparty VASP, submitting the transfer, reading the exchange status, finalising or cancelling it, answering requests other VASPs send you, handling the unhosted-wallet path when no VASP is attributed, and finding existing transactions (deduplication before after-settlement exchanges). TRIGGER when the user asks to "integrate / add / implement Travel Rule", "send Travel Rule data with a withdrawal", "collect Travel Rule data for a deposit that already arrived", "respond to / answer incoming Travel Rule requests", asks why their exchanges sit at onHold or completed and never reach finished, why counterparties never answer, how to test Travel Rule in Sandbox, about "unhosted / self-hosted / non-custodial wallet verification", "prove the user owns the wallet", "Satoshi test", what happens on counterpartyVaspNotFound or applicantKytTxnAwaitingUser, or to "find / search transactions", "check whether a transaction already exists for this hash". SKIP for building the transaction payload itself (use sumsub-create-transaction), for writing the scoring rules that act on the outcome (use sumsub-create-kyt-rules), for bulk-registering wallet addresses (use sumsub-manage-wallet-address-book), and for KYC/AML work unrelated to transfers between VASPs.

安装量: 1
GitHub Stars: 6
最近更新: 9月3日

查看详情 →

sumsub-manage-wallet-address-book

Register the crypto wallet addresses an organisation controls, so Sumsub can resolve address ownership without a human. Bulk-imports addresses into the Wallet Address Book via POST /resources/kyt/walletAddress/import, and registers a single address against a specific applicant via POST /resources/api/applicants/{applicantId}/payments. TRIGGER when the user asks to "upload / import / register our wallet addresses", "add addresses to the Wallet Address Book", "register a user's crypto wallet as a payment method", says Travel Rule requests are "not matching automatically" or "always land in manual review", or asks how to stop confirming the same address by hand on every exchange. SKIP for looking up which VASP owns a counterparty address (that is attribution — use sumsub-api-generic against /resources/api/wallet-attribution), for confirming ownership on one specific transaction (use sumsub-integrate-travel-rule), and for deleting addresses (no public endpoint — use the dashboard).

安装量: 1
GitHub Stars: 6
最近更新: 9月3日

查看详情 →

sumsub-manage-webhooks

Manage Sumsub clientWebhooks (event subscriptions for applicantReviewed / applicantPending / kytTxn / etc.) — reads via /resources/api/clientWebhooks, writes via /resources/api/agent/clientWebhooks. Sandbox only — production webhooks must be created by a human directly in the Sumsub dashboard. TRIGGER when the user asks to "list / retrieve / show webhooks", "create / add / register a webhook", or "update / edit / change a webhook target / event list / secret / signature algorithm" against their sandbox tenant. SKIP for production webhook setup (refer the user to the dashboard), for unrelated webhook surfaces (Stripe / videoIdent / Fireblocks / NFC / partner-specific receive paths under /resources/webhooks/...), for testing one-off delivery (use the inspectionCallbacks/testWebhook endpoint directly), and for KYT-only webhook routing (that's managed in the Sumsub dashboard's KYT section). The public API does not expose delete or per-webhook delivery stats — for those, refer the user to the Sumsub dashboard UI.

安装量: 1
GitHub Stars: 6
最近更新: 9月3日

查看详情 →

prestashop-update-check

Check if a PrestaShop store is ready to be updated. Use when the user wants to assess compatibility or available versions without starting an update.

安装量: 1
GitHub Stars: 5
最近更新: 9月8日

AFL-3.01 文件

查看详情 →

e2e-testing

Create, run, and debug JSON-driven E2E browser tests with Chrome pool integration

安装量: 1
GitHub Stars: 3
最近更新: 6月8日

Apache-2.011 文件

查看详情 →

python-supply-chain

Hardens a Python repository's supply chain — Dependabot update automation, pip-audit vulnerability scanning, secret scanning and push protection, CodeQL, OpenSSF Scorecard, SBOMs, CODEOWNERS. Use for 'set up dependabot', 'audit dependencies', 'someone committed a key — stop that happening again', 'protect paths with CODEOWNERS', 'harden this repo'. Not for CI quality gates, workflow hardening, or PyPI publishing.

安装量: 1
GitHub Stars: 3
最近更新: 9月10日

查看详情 →

build-alone

Carry a set of requirements all the way to a tested, self-reviewed implementation that's ready to hand back, deciding open questions on your own and only interrupting for true showstoppers. Use when the user asks you to implement a feature, task, or ticket autonomously, end-to-end, or with minimal supervision — e.g. "build this on your own", "implement the whole thing", "go ahead and ship it".

安装量: 1
GitHub Stars: 2
最近更新: 9月10日

查看详情 →

explore-solutions

- Explores different approaches to a software requirement and compares their trade-offs, so the user knows which approaches are workable and at what cost. Scans the codebase for what exists and what will get in the way, generates genuinely different solution approaches, compares them from a bird's-eye view, and tracks which ones the user keeps or rejects, until a primary candidate and its fallbacks remain. The input is a requirement whose approach is still open, typically the size of a feature or ticket. The output is a small set of candidate approaches with their trade-offs, not a plan. This is a heavy, multi-turn session. Use only when the user explicitly asks for a solution exploration: "explore solutions for this", "run a solution exploration", "explore the solution space for this ticket". Not for a quick question about options or alternatives, which gets a direct answer.

安装量: 1
GitHub Stars: 2
最近更新: 9月10日

查看详情 →

wuming-ai-ppt-cover

使用 imagegen 生成 AI、Agent、Skills、工具市场、课程或产品发布主题的 16:9 PPT 封面。适用于用户要求“AI PPT 封面”“PPT 封面”“Skills 市场封面”“封面大字”“直接出图”或给出一句封面文案，希望生成大标题、科技感、演示页风格横版封面时使用；默认主题为“Skills 市场：海量 Skills 应有尽有”，默认调用 imagegen 出图，用户明确只要提示词时仅输出提示词。

安装量: 1
GitHub Stars: 1
最近更新: 7月24日

查看详情 →

prelude-docs

Manage a consumer repo's Prelude docs viewer content — prelude.docs.pages, groups, mdSplit README hero, and generated nixosOptions pages. Use when adding or fixing project documentation shown by docs / x docs, wiring the README landing page, or generating option docs.

安装量: 1
GitHub Stars: 1
最近更新: 9月8日

查看详情 →

orchestrator

Commander-driven multi-CLI worker orchestration. The invoking agent or session classifies implementation units by risk, dispatches them to Devin, Codex, Cursor, Claude Code, or Grok workers in isolated git worktrees, pipelines each completion (review as soon as a worker finishes — never barrier-wait the whole cohort), then merges into one integration branch. Use when the user asks to "split work across agents", "have Devin/Codex/Cursor/Grok implement in parallel", "act as commander/orchestrator", or otherwise delegate implementation to other CLIs.

安装量: 1
GitHub Stars: 1
最近更新: 9月10日

查看详情 →

swarm-discussion

Exploratory discussion pattern for unsolved problems. Replicate the thinking of Staff+ engineers: "When there's no clear answer, expose blind spots by confronting diverse perspectives." True multi-agent discussions where experts directly engage with each other through team-based + messaging architecture.

安装量: 1
GitHub Stars: 1
最近更新: 2月6日

查看详情 →

jinko

- Discover and route Jinkō QSP and mechanistic-modeling requests to the public Jinkō skill that owns the work. Use when the user is starting a Jinkō session, asks what capability or skill to use, describes a multi-area modeling request, or has not yet identified the relevant jinko- or jinko-task- skill. This skill does not make scientific decisions, plan workflows, execute SDK calls, or decide that a task step is complete.

安装量: 1
GitHub Stars: 1
最近更新: 9月7日

查看详情 →

jinko-context

- Explain core Jinkō context, navigation, version management, and domain language for agents and users. Use this skill whenever the user needs a mental model of Jinkō projects, folders, project items, snapshots, sources, extracts, protocols, trials, calibration, virtual populations, references, or modeling context; when translating between generic terms and Jinkō terminology; or when an agent needs orientation before navigating or modifying Jinkō artifacts. This skill is conceptual and terminology-focused; use dedicated jinko- workflow skills for creating or editing specific artifacts.

安装量: 1
GitHub Stars: 1
最近更新: 9月7日

查看详情 →

jinko-data-table

- Create or inspect Jinkō data tables via the jinko-sdk. Use this skill whenever the user wants to upload observed data for trial overlays or calibration objectives from CSV, SQLite, or pandas DataFrame; check data-table schema columns; inspect existing data tables; or verify metadata.public.validForFitnessFunction. Do not use this skill for output sets; use jinko-output-set for that.

安装量: 1
GitHub Stars: 1
最近更新: 9月7日

查看详情 →

jinko-sdk-setup

Authenticate and configure access to a Jinkō project via the jinko-sdk. Use this skill whenever the user wants to connect to Jinkō, install the SDK, set up credentials or a .env file, verify API access, fail-fast check that a JINKOAPIKEY and JINKOPROJECTID work, or debug ConfigurationError, AuthenticationError, or AuthorizationError from the SDK. Do not use this skill for creating models, vpops, protocols, output sets, or trials.

安装量: 1
GitHub Stars: 1
最近更新: 9月7日

查看详情 →

jinko-task-cmaes

- Execute a CMA-ES calibration from confirmed Jinkō inputs: assemble the model, protocol, output sets, fitness data tables, parameter priors, and optimizer options; create and run the Calibration; and return the supported results. Use when the user wants to perform a CMA-ES calibration, not when they need to choose a calibration strategy, infer priors, design objectives, or decide whether results are acceptable.

安装量: 1
GitHub Stars: 1
最近更新: 9月7日

查看详情 →

jinko-task-from-nonmem

- Convert a NONMEM run into a Jinkō trial set-up via the jinko-sdk. Use this skill whenever the user wants to import, translate, port or migrate a NONMEM model, control stream, .mod/.ctl/.lst file, .ext estimates, .phi individual estimates or a NONMEM data set into Jinkō, or asks to reproduce a published population-PK model that exists as NONMEM code. Emits the computational model, virtual population, protocol design and output set, checks the result numerically against a declared reference, and can publish the evidence as a Jinkō document. Use jinko-model to author a model from scratch, jinko-protocol to edit an existing protocol, jinko-vpop to edit a population, and jinko-calibration-cmaes to fit parameters.

安装量: 1
GitHub Stars: 1
最近更新: 9月7日

查看详情 →

run-ui-registry-variations

Manual-invocation skill — run only when the user explicitly asks for "run-ui-registry-variations" or invokes it as a slash command. Do not auto-trigger on adjacent topics. Force UI work through shadcnblocks, Aceternity, or https://shadcn.darkmatter.io; validate private registry access before use; build exactly three user-reviewable variations.

安装量: 1
GitHub Stars: 0
最近更新: 9月10日

查看详情 →

test-driven-development

Use when the user asks for TDD, test-first, red-green-refactor, or an end-to-end happy-path test of a public contract. Do not use for ordinary implementation, refactors, helpers, or comment-only changes.

安装量: 1
GitHub Stars: 0
最近更新: 9月10日

查看详情 →

ui-ux-pro-max

UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, and flat design. Topics: color systems, accessibility, animation, layout, typography, font pairing, spacing, interaction states, shadow, and gradient. Integrations: shadcn/ui MCP for component search and examples.

安装量: 1
GitHub Stars: 0
最近更新: 9月10日

查看详情 →