AI & ML

ai-sns Bundle

Generate an image from a text prompt using an OpenAI-compatible image generation API (gpt-image-1-mini or compatible). The image is uploaded to the gofile.io public file sharing service and ONLY the public download page URL is returned. Trigger when user asks to draw, paint, generate, or create an image.

ai-sns Bundle

Fetch an A2A agent card JSON from a given endpoint URL. Tries direct GET first, then falls back to /.well-known/agent.json.

ai-sns Bundle

Generate an image from a text prompt using an OpenAI-compatible image generation API (gpt-image-1-mini or compatible). The image is uploaded to the gofile.io public file sharing service and ONLY the public download page URL is returned. Trigger when user asks to draw, paint, generate, or create an image.

ashish7802 Skill

Enforces reliable LLM function calling, finite agentic loops, and typed output schema contracts.

broomva Skill

Reference for the `broomva` Rust CLI — manage prompts, skills, and context from the terminal or Claude Code sessions. Includes the auto-tracing protocol that turns this skill into the runtime dispatcher for broomva.tech/prompts. When a user asks to "use the X prompt", "run the X prompt as instructions", or "pull X prompt", this skill is the answer.

cham0287 Bundle

Review backend plans and code changes using evidence from the actual repository, callers, contracts, data writers, and runtime boundaries. Use for explicit backend review requests and for changes involving transactions, concurrency, permissions, public APIs, migrations, backfills, multi-model writes, external side effects, or new fallback and compatibility branches. Supports `quick`, `plan`, and `deep` modes. Do not trigger for formatting, imports, localized mechanical edits, documentation-only work, or tests that do not change production behavior.

chenxi-bot21 Skill

Methodology for evidence-based cover letters: an evidence bank mined from the candidate's real record, JD keyword mirroring, honest gap handling via transferable proof, a four-paragraph structure with a clear ask, and a draft-generator pattern the agent can run per posting. Use when drafting or reviewing a cover letter or building letter tooling.

chenxi-bot21 Skill

An enterprise-style operating standard for running a multi-project personal workspace with an AI agent — written roles, one-conversation-one-lane focus, a chronological work ledger with decision records, a live action board, and a hand-off checklist so any new session (or person) can take over cold. Use at the start of any work session, before and after making changes, and whenever standards, traceability, pickup, or handoff come up.

chuk-development Bundle

Turn a live browser session into a fast headless monitor. Use when the user says "monitor this website / page / dashboard", "watch X for changes", "tell me when Y updates", "keep an eye on this", or wants a login-gated page polled cheaply. The agent drives the site once with Playwright MCP (open, look, log in), finds the real HTTP request behind the data, and generates a standalone curl_cffi Python script (real Chrome TLS fingerprint, persisted cookie jar, reverse-engineered/refreshing login, change-diff, hook notification) that replays that request forever without a browser. Runs with uv.

contentstack Skill

Use when changing Contentstack SDK usage, Live Preview, env configuration, or content queries in kickstart-next-ssr.

curvefit Skill

Use to turn rough thoughts into a clear coding task prompt.

dc995 Bundle

Conductor — a full-stack engineer agent for the MCP Apps EXTENSION (not a single app). Builds, secures, hosts, tests, and audits MCP Apps and their hosts, composing MCP server → UI resource → host → explicit application state. Defaults new core work to MCP 2026-07-28 and isolates legacy sessionful behavior. Use for 'build an MCP App and a host to render it', 'compose the full MCP App stack', 'threat-model my MCP App host', 'why won't my tile render / drag / theme', 'host an MCP App in my own web app', 'make a stateful multi-turn MCP App (game/wizard)', 'wire OAuth / PDF / sampling through a host', 'audit my app for host compatibility', 'add an MCP App ext agent'.

dc995 Bundle

Test MCP Apps across hosts. Server API tests, Playwright E2E, cross-host validation, and debugging with ui-inspector. WHEN: 'test my MCP App', 'write tests for MCP server', 'cross-host testing', 'debug MCP App iframe', 'Playwright MCP tests', 'why is my MCP App broken', 'validate across hosts'.

dc995 Skill

Audit and rewrite existing MCP Apps for host compatibility. Review apps for CSP violations, external CDN dependencies, eval usage, blocked permission APIs, and provide specific rewrite patterns. WHEN: 'audit my MCP App', 'review MCP app compatibility', 'why does my app break in VS Code', 'rewrite for VS Code', 'fix CSP errors', 'make my MCP app work everywhere', 'check host compatibility'.

dc995 Bundle

Build MCP Apps with interactive UIs. Scaffold new apps, register tools and resources, configure vite-plugin-singlefile, and target multiple hosts safely. Replaces create-mcp-app with host-aware pre-build safety checks. WHEN: 'create an MCP App', 'add a UI to an MCP tool', 'scaffold an MCP App', 'build an interactive MCP View', 'MCP Apps SDK patterns', 'UI-resource registration', 'MCP App lifecycle', 'host integration'.

dc995 Bundle

Threat-model and secure MCP Apps, MCP servers, and custom hosts. Review iframe isolation, postMessage validation, tool authorization, Streamable HTTP Origin checks, session safety, OAuth, SSRF, XSS, prompt injection, secrets, and untrusted MCP content. WHEN: 'secure my MCP App', 'MCP App threat model', 'review MCP host security', 'is this iframe sandbox safe', 'prevent SSRF', 'secure MCP OAuth', 'validate postMessage', 'security audit MCP server'.

deep153 Skill

Stress-tests a plan or design by interviewing the user in depth, walking the decision tree branch-by-branch until there is a shared understanding. For each point, the agent offers a recommended answer. Use when the user ask any questions in plan mode or mention stress-tested, or "grilled," or when they say "grill me."

dnth Skill

Edit prose into tight, warm, human writing with clean sentences, no throat-clearing, no hype, no AI tells, and concrete source-grounded detail. Use when the user asks to edit writing, tighten prose, make writing sound human, apply a clear writing prompt, or remove clutter from drafts.

gaixianggeng Bundle

在 Sol 主线程执行工程任务时，根据 auto、sol-only 或 ask-each-time 路由偏好，判断是否把边界明确、独立、可验收的执行项交给 GPT-5.6 Luna Max，并由主 Agent 最终验收。用户提到 Luna、Luna Max、降低 Sol 使用成本、自动调度子代理、配置 luna_worker、批量执行清晰小任务或让主 Agent 规划后交给低成本 Worker 时使用；不要用于需求模糊、架构决策、多个 Agent 同改一批文件或无人验收的高风险操作。

ory Skill

Build your own AI agent that authenticates the user, authorizes every tool call against Ory Permissions, and records structured activity — by dropping `@ory/argus` directly into the Claude Agent SDK, OpenAI Agents SDK, Mastra, Vercel AI SDK, PydanticAI / LangGraph, or as an external service called by Salesforce Agentforce. Use when the user wants to wire Ory into a custom agent they own — phrases like "add Ory to my own agent", "build a custom agent with Ory auth", "wrap my Claude Agent SDK tools with Ory permissions", "OpenAI Agents SDK with Ory", "Mastra agent with Ory permissions", "Agentforce action with Ory", "use `@ory/argus` directly". For wiring Ory into an existing agent harness (Claude Code, Codex, Gemini CLI, OpenClaw, OpenCode) use the corresponding `@ory/<harness>` plugin instead.

ory Skill

Scaffold a [Temporal](https://temporal.io) TypeScript worker where every Activity execution is gated by Ory — the user is authenticated, the worker's agent identity is resolved via DCR, each Activity invocation runs an Ory Permission check, and the full lifecycle emits structured activity events. Use when the user asks to "add Ory to my Temporal worker", "wire Ory permissions into Temporal activities", "create a Temporal worker with Ory auth", "build a Temporal TypeScript project with the Ory agent client", or any close variant. The skill scaffolds the project in the user's repo following <https://docs.temporal.io/develop/typescript/set-up-your-local-typescript> — it does not run the worker.

ory Skill

Onboard native agent-tool authorization with default allow and explicit deny overrides. Covers connecting the plugin, reviewing allowed and blocked tools, writing blocks in the Ory Console, and promoting the project from observe to enforce. MCP and PermissionMode remain grant-based.

zaxbyhub Skill

Apply when implementing features, fixing bugs, debugging errors, investigating failures, tracing root causes, reviewing tech debt, tracing issues, planning fixes, or completing any task. Enforces parallel sub-agent implementation, independent adversarial review, and a 95% confidence gate before stopping.

gitguardian Bundle

Check whether a known credential has already leaked publicly via GitGuardian's HasMySecretLeaked (HMSL) hash-lookup service. Use when the user inherits credentials, suspects a specific token leaked, wants to vet a HashiCorp Vault inventory, or asks "has this secret leaked", "is this compromised", or "check against HMSL". Distinct from scan-secrets, which finds unknown secrets in code; this checks known secrets against the HMSL corpus. User-run only — this is a command-handoff skill, so the agent prepares the commands, the user runs them in their own terminal, and the agent only interprets the sanitized output the user pastes back.

gitguardian Bundle

Use when triaging or reviewing GitGuardian secret incidents already detected in the dashboard, when asked what is leaking in the org or what to fix first, when remediating or rotating a credential flagged in an incident, after a Public Monitoring alert, or to assign, tag, or resolve incidents. Operates through the GitGuardian Developer MCP server.

ferueda Skill

Hand off work in progress or finished to another agent for continuation or review. Produce a structured summary with enough background context, what was worked on, how, why, files touched, and what remains. Trigger when the user says "hand off this work", "prepare a handoff", "document what was done for the next agent", or ending a session another agent should pick up.

ipea Skill

Save a structured state snapshot before stopping or handing off. Captures the active plan, recent decisions, file pointers (with line numbers), open questions, and the next 1–3 actions into a checkpoint file under `quality_reports/checkpoints/`. Optionally proposes `[LEARN]` entries to add to MEMORY.md. Use when user says "checkpoint", "save state", "snapshot before I stop", "where am I", "wrap up the session for handoff", or before a long break / model switch / collaborator handoff. Companion to (NOT replacement for) the narrative session-log workflow.

shhots Bundle

Write high-converting, claim-safe UGC ad scripts and visual treatments, then generate the finished video with the Shhots AI MCP server. Use this skill whenever the user wants a UGC ad, video ad, TikTok ad, Reel, creator-style ad, product video, ad script, ad hooks, or mentions Shhots, even if they only ask for "an ad for my product" without naming a format. Also use it when the user asks to improve, rewrite, or localize an existing ad script.

shhots Bundle

Generate hundreds of varieties of static image ads for any business type (D2C, SaaS, apps, services, local) using the Shhots AI MCP server, with 14 proven ad formats mapped to funnel stages. Use this skill whenever the user wants image ads, static ads, banner ads, Meta or Instagram or LinkedIn or Google display creatives, ad variations at volume, a creative testing matrix, or says things like "I need ads for my store/app/agency" or "give me lots of ad options", even if they don't say "static" or "image".

shhots Bundle

Produce art-director-grade creative direction for AI product photography and generate the images with the Shhots AI MCP server. Use this skill whenever the user wants product photos, a product photoshoot, studio shots, lifestyle images, ad images, hero images, PDP images, social images, or mentions Shhots image generation, even if they just say "make my product look good" or "I need photos for my store."

shhots Bundle

Generate distinctive AI ad styles with the Shhots AI MCP server, including claymation, animated, podcast-clip, viral hook stack, talking kids, talking animals, whiteboard explainer, stop motion, animated human body for supplement education, and toy brick motion. Use this skill whenever the user wants an ad in a specific creative style, a "different kind of ad", something scroll-stopping or unusual, a claymation or stop motion or LEGO-style or podcast-style ad, an explainer, or asks "what other ad styles can we try", even if they don't name a style.

xclouddev Bundle

Official xCloud plugin for agents: manage servers, sites, WordPress, SSL, and account data — MCP-first via the xCloud MCP server, with a bundled REST fallback.

mcdenil-skills Bundle

Создаёт анимационный Reels/Shorts без камеры из темы, сценария или готовой озвучки в AutoMontage-Agent: script, выбор аудио, таймкоды, motion brief, настоящий preview, явное утверждение, MotionReel final и QA. Используй для «ролик без камеры», «анимационный рилс», «кинетический текст», «motion-reel» и «видео из озвучки»; в новом чате предлагает готовый стиль, уникальный Creative Motion или работу по референсу.

mcdenil-skills Bundle

Собирает ролик под ключ в AutoMontage-Agent: проверяет исходник, транскрибирует речь, готовит один полный пакет ТЗ со сценами, текстами, кадрированием, анимацией и аудиопробой, ждёт явного утверждения, рендерит ReelScenes и сам проводит визуальный и звуковой QA. Обязательно используй, когда пользователь просит «смонтируй ролик», «ролик под ключ», «сделай Reels/Shorts», «собери lesson» или даёт видео для монтажа, даже если не называет навык. В новом чате сначала предлагает готовый стиль, уникальный Creative Motion или монтаж по референсу. Запросы анимации без камеры направляет в motion-reel.

mcdenil-skills Bundle

Собирает ролик под ключ в AutoMontage-Agent; в новом чате сразу предлагает готовый стиль, уникальный Creative Motion или монтаж по референсу, затем автономно ведёт исходник до preview, утверждения, final и QA. Используй при просьбах «смонтируй ролик», Reels, Shorts и lesson.

mcdenil-skills Skill

Собирает ролик под ключ в AutoMontage-Agent; в новом чате сразу предлагает готовый стиль, уникальный Creative Motion или монтаж по референсу, затем автономно ведёт исходник до preview, утверждения, final и QA. Используй при просьбах «смонтируй ролик», Reels, Shorts и lesson.