搜索「Prompt」的结果

io.clawhub.greatape42069/clawdvault

Access and interact with Clawdvault large-scale on-chain applications and AI-powered smart contract initiatives securely.

io.clawhub.cinience/volcengine-ai-image-generation

Create images with prompt control on ARK

io.clawhub.beelkic/acpx

Use acpx as a headless ACP CLI for agent-to-agent communication, including prompt/exec/sessions workflows, session scoping, queueing, permissions, and output...

io.github.sadri-dridi/think-steps

Return a three-step thinking template. Prompt discarded.

io.github.Vohlsyr/trustfetch

Prompt-injection scanning and safe webpage fetching for AI agents reading untrusted content.

io.github.aistoragedepot-admin/aistoragedepot-mcp

Prompt, rules, skills & docs library over MCP. No token = read-only sample of the public library.

com.completionkit/evals

Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.

io.github.ZentricProtocol/zentric-protocol-mcp

Prompt injection + PII detection for LLM apps and agent pipelines. Deterministic, sub-25ms.

io.github.bch1212/injectshield

Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.

io.github.abcxz/conviction-mcp

The arena where AI agents compete for real returns. Prompt a strategy.

io.github.relaticle/relaticle/mcp-development

Use this skill for Laravel MCP development. Trigger when creating or editing MCP tools, resources, prompts, servers, or UI apps in Laravel projects. Covers: artisan make:mcp-* generators, routes/ai.php, Tool/Resource/Prompt/AppResource classes, schema validation, shouldRegister(), OAuth setup, URI templates, read-only attributes, MCP debugging, MCP UI apps, the x-mcp::app Blade component, createMcpApp(), default AppResource handle() auto-infers view from class name, Response::view(), AppMeta/Csp/Permissions/appMeta() configuration, #[RendersApp] attribute, Library enum for CDN libraries (Tailwind, Alpine), and host theming via CSS variables. Use this whenever the user mentions MCP apps, MCP UI, interactive MCP resources, styling MCP apps with Tailwind or Alpine, or building visual interfaces for AI agents.

io.github.sddevelopment-be/quickstart_agent-augmented-development/automation-script

Prompt for DevOps Danny to generate an automation script based on requirements or direct prompt

io.github.anthropics/claude-code/hook-development

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

Framesail

vlatest

io.smithery.framesail.framesail

Create long-form (faceless YouTube) videos end to end from any MCP client: script, locked character references, storyboard, voiceover, and final video editing — with characters and style held consistent across every shot. Making long-form AI video today means 8+ tabs stitched by hand — an LLM for the script, a voice model, an image model, a video model — with characters drifting between tools and style resetting at every export. Framesail replaces the patchwork: the whole pipeline runs in one place and manages your video's context end to end. Six stages: Style (paste images, videos, or YouTube links and Framesail reverse-engineers the look, voice, and direction), Script (write it yourself or generate it in your narrative style), Reference images (auto-generated for every character, place, and prop), Voiceover (one narrator or many characters, with word-level timing), Storyboard (planned scene by scene), and Editor (captions, music, SFX, then export). No black box: you control every prompt, asset, model, an

//beforeyouship — LLM cost modeling from your editor

vlatest

io.smithery.beforeyouship.cost-model

Model the realistic monthly cost of an LLM app **before you build it**. Not a token calculator: retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth are modeled in, across GPT-5.x, Claude, Gemini, DeepSeek, and more. **Works without a key.** Connect and ask — demo mode covers the six free-tier models. A Pro API key ([beforeyouship.dev](https://beforeyouship.dev)) unlocks the full 18-model catalog. ## Tools | Tool | What it does | |---|---| - **`estimate_cost`** Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case $/mo per model, growth scenarios, and an opinionated recommendation. | - **`get_model_prices`** Current per-1M-token pricing (input, output, cached, batch) with context windows and staleness metadata. | - **`list_archetypes`** Seven preset architecture patterns (chatbot, RAG pipeline, multi-step agent, …) used as starting points for estimates. | ## Try it Paste into Claude Code or Cursor after connecting: > Estimate the monthl

designforyou

vlatest

io.smithery.swapp19902.designforyou

Generate finished, on-brand designs from a prompt - logos, social posts, app-store screenshots, comic pages, and visual-novel sprite sheets. Browse templates, get a recommendation, then generate editable, production-ready artwork. OAuth + per-user credits built in.

io.clawhub.ivangdavila/rag

Designs, tunes, and debugs retrieval-augmented generation (RAG) pipelines: chunking, embeddings, hybrid retrieval, reranking, and grounded answers. Use when a system returns the wrong passages, misses a document that is indexed, cites nothing, or hallucinates over good context; when choosing a vector store, an embedding model, a chunk size, or a reranker; when similarity scores collapse after a model swap; when a metadata filter empties the result set; when answers ignore mid-context facts; when follow-up questions retrieve the wrong thing; when indexing PDFs, scanned pages, tables, code, or transcripts; when GDPR erasure, tenant isolation, or prompt injection from indexed documents is the problem; or when per-query cost or p95 latency has to come down. Covers reindex migrations, corpus freshness, evaluation sets, and agentic and graph retrieval. Not for splitter internals (`rag-chunking`), scoring rubrics (`rag-evaluation`), or LangChain APIs (`langchain`).

io.clawhub.ivangdavila/ios

Builds, ships, and debugs native iOS apps: lifecycle, permissions, entitlements, push, widgets, StoreKit, and App Store review. Use when a submission is rejected or a guideline blocks a release; when a permission prompt never appears, or a call fails with a missing-entitlement error; when push, background refresh, or a background upload never runs; when a universal link opens Safari instead of the app; when the app is killed by the watchdog, by jetsam, or with 0xdead10cc, hangs on launch, or crashes only on device; when a widget, Live Activity, or app extension runs out of memory; when purchases, subscriptions, or restore fail; when a privacy manifest, tracking prompt, or data label is required; when layout breaks under Dynamic Type; or when a new iOS release breaks a shipped app. Not for Swift language mechanics (`swift`), IDE, signing and build settings (`xcode`), store listings and submission workflow (`app-store`), or cross-platform apps (`react-native`, `flutter`).

Amber — Phone-Capable Voice Agent

v5.5.34

io.clawhub.batthis/amber-phone-capabilities

Give your OpenClaw agent real phone capabilities. Setup uses a short wizard; after setup, run calls and phone tasks with one natural-language prompt.

io.clawhub.yazelin/nanobanana-pro-fallback

Nano Banana Pro with auto model fallback — generate/edit images via Gemini Image API. Run via: uv run {baseDir}/scripts/generate_image.py --prompt 'desc' --filename 'out.png' [--resolution 1K|2K|4K] [-i input.png]. Supports text-to-image + image-to-image (up to 14); 1K/2K/4K. Fallback chain: gemini-2.5-flash-image → gemini-2.0-flash-exp. MUST use uv run, not python3.

MoltPe

vlatest

io.smithery.umg-gpt.moltpe

AI-native payment infrastructure that gives AI agents isolated wallets with programmable spending policies for autonomous USDC stablecoin transactions. **11 MCP tools** for Claude Desktop, Cursor, and Windsurf: - check_balance, send_payment, list_transactions, agent_info - create_invoice, pay_invoice, check_invoice_status, list_invoices - call_x402_endpoint, call_mpp_endpoint, plus more **Tri-rail support:** x402 (HTTP-native micropayments), MPP (session-based streaming), and traditional fiat. Multi-chain USDC on Polygon PoS, Base, and Tempo with sub-second settlement. **Non-custodial wallets** with Shamir key splitting — your keys, never ours. **Programmable spending policies** (daily caps, per-transaction caps, recipient allowlists, cooldowns) enforced at the infrastructure level. Your agent literally cannot overspend regardless of prompt injection or buggy retry loops. **Free tier** — no credit card, no KYC, no geographic gating. - Site: https://moltpe.com - Open source reference: https://github.com/

io.clawhub.emberdesire/hopeids

Inference-based intrusion detection for AI agents. Pattern matching + LLM analysis for jailbreaks, prompt injection, credential theft, social engineering. 108 detection patterns, OpenClaw plugin, auto-scan, quarantine. Commands: hopeid scan, hopeid test, hopeid setup, hopeid stats, hopeid doctor.

LLM Observability & Orchestration Agent

vlatest

io.smithery.a2a.llm-observability-orchestration

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing. Ideal for traced/observable LangChain pipelines, evaluating prompts, monitoring chain quality.

SkillAudit

vlatest

io.smithery.megamind-0x.skillaudit

Security scanner for AI agent skills and MCP servers. Detects credential theft, data exfiltration, prompt injection, obfuscated code, and 80+ threat patterns. Free API + CLI (npx skillaudit). Premium deep scans via x402 micropayments.