技能与智能体开发
5,949 个结果
- Risk AnalysisgeovannebStructured framework for identifying, assessing, and communicating risks in executive deliverables. Use when a task involves a risk register, a risk section in a report, or a situation where risks need to be surfaced and prioritized for a senior audience.
- Roblox StudioShiroKSHBuild, inspect, repair, validate, and playtest Roblox Studio maps and Luau through the local bridge. Use for SceneSpecs, terrain, Studio edits, gameplay objects, visual checks, and Rojo output.
- Session HandoffrenzrollonSave where this session stands to a handoff file before a context reset, so the next session or agent resumes without re-deriving decisions. Lists stranded work, redacts secrets, and proposes reusable rules for your instruction file.
- Session PrimerrenzrollonBrief a fresh session in one read-only pass, from git state, open plan checkboxes, the newest handoff file, and the instruction file. Use at session start or when the user says "where was I", "catch me up", "continue where we left off", "what's the state of this repo", or "brief me". Does not trigger on a question that names a specific file or feature, and never edits anything.
- Session RetrorenzrollonRetro the current session. Score it against session shapes, flag token waste with next-turn fixes, and propose wire-ins into the skills this conversation actually called.
- Shape Your Agentsanity-ioInteractive session to craft a system prompt for an AI agent powered by the Sanity Context MCP server. Use this skill when users want to define agent personality, set tone/voice, establish boundaries and guardrails, configure refusal behaviors, or control how their agent communicates.
- Skill CreatorBerryKuipersInteractive skill creation wizard that guides you through building properly formatted Claude Skills with YAML frontmatter, progressive disclosure, and best practices
- StartZoomStart here for any Zoom integration or app idea. Use when you need to choose the right Zoom surface, shape the architecture, or route into the correct implementation skill without reading the whole Zoom doc set first.
- StartitsOmidKaramiCreates a new Kraft Lite chain for the work and hands it to the first node. Use when the human asks to begin new work under Kraft Lite; continuing an existing chain is `kraft-lite:next`.
- StatusitsOmidKaramiReports where a Kraft Lite chain has got to (its node, running or blocked at a gate, attempts spent) and, on request, what a finished run took. Use when asked where a Kraft Lite chain is, whether it is stuck, or how long it ran; `kraft-lite:next` continues a chain and `kraft-lite:gate` answers a gate.
- StatusitsOmidKaramiReports which phase a Kraft work item is in and what runs next, and watches it until it finishes. Use when someone asks where a work item has got to or wants a handed-off item watched; for why it stopped, use kraft:triage.
- SteeritsOmidKaramiRedirects a Kraft work item by revising its spec or plan before it starts, or by pausing and resuming it with a steer once it has. Use when a work item is heading the wrong way or its spec or plan needs revising; to find out why one stopped, use kraft:triage.
- Sumsub API AuthsumsubAuthenticate to the Sumsub API with an App Token + secret key (HMAC-SHA256 request signing). TRIGGER when the user asks to "call / sign / authenticate Sumsub API requests", debugs `401 Unauthorized` / signature errors against `api.sumsub.com`, or needs a working request example with `X-App-Token` / `X-App-Access-Sig` / `X-App-Access-Ts` headers.
- Sumsub API GenericsumsubCatch-all fallback for any Sumsub API task that does NOT match a more specific skill (e.g. `create-sumsub-level`, `sumsub-create-questionnaire`, `sumsub-api-auth`). TRIGGER when the user wants to call, inspect, or debug a Sumsub API endpoint not otherwise covered — fetching applicants, listing levels, reviewing AML hits, exporting data, generating SDK tokens, anything against `api.sumsub.com`.
- Sumsub Check PermissionssumsubFetch the current tenant's allowed entitlements (BackgroundCheckTarget list). Returns JSON `{"allowedChecks":{key:label}}` — a map whose keys are the enabled entitlement keys. Called by sumsub-create-level (and other create-* skills) before building a payload to gate entitlement-required features.
- Sumsub Check Skills VersionsumsubVerify that the locally installed Sumsub agent-skills package is compatible with the published version before doing any Sumsub work. TRIGGER at the start of any task that touches Sumsub — Sumsub Dev MCP tools (mcp__Sumsub_Dev__*), KYC/AML workflows, applicants, checks, transactions, verification levels, verification links, questionnaires, fraud network, VASP lists, or anything Sumsub-related —…
- Sumsub Create Cross Check PresetsumsubCreate 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.
- Sumsub Create Poa PresetsumsubCreate or update a Sumsub Proof-of-Address (POA) preset. POST `/resources/api/agent/poaStepSettings` to create new, PATCH same path to update (id in body), GET `/resources/api/agent/poaStepSettings/{id}` to read one back.
- Sumsub Create QuestionnairesumsubCreate or update a Sumsub KYC questionnaire definition. POST `/resources/api/agent/questionnaires` to create new (fails 409 if id exists), PATCH same path to update (fails 404 if id is unknown), GET `/resources/api/agent/questionnaires/{id}` to read one back.
- Sumsub Supported Id DocumentssumsubQuery AND edit Sumsub's supported identity documents. READ the built-in catalogue (documentsByCountries) — which document types are supported per country, whether they're double-sided, which OCR fields are default vs. available. EDIT a client's own supported-document overrides (idDocSettings.countryMappings) via the global-settings API.
- TriageitsOmidKaramiDiagnoses why a Kraft work item stopped, failed or is stuck needing a person, and routes it to a retry, a raised cap or the right sibling skill. Use when someone asks why an item stopped or how to get it going again; a pending gate alone belongs to kraft:gates.
- virtual-agent/androidZoomZoom Virtual Agent Android integration via WebView. Use for Java/Kotlin bridge callbacks, native URL handling, support_handoff relay, and lifecycle-safe embedding.
- virtual-agent/iosZoomZoom Virtual Agent iOS integration via WKWebView. Use for Swift/Objective-C script injection, message handlers, support_handoff relay, and URL routing policies.
- Wikimemnaman10parikhSelf-improving LLM knowledge base. Use WHEN you need to ingest a file/URL/folder into a wiki, query your own knowledge with LLM-powered search, sync a connector (Slack/GitHub/Gmail/Discord/Notion/Linear/Jira + 30 more), run the Observer to score + improve your wiki nightly, or expose the wiki to Claude as a Custom Connector via MCP OAuth.