AI & ML

2799662352 Bundle

Use when writing high-stakes prompts for video or image generation models (Sora, Midjourney, Kling, Veo, Stable Diffusion), when designing prompt-engineering systems, or when the user wants outputs grounded in both academic research and creator craft. Triggers on phrases such as "Sora prompt", "video generation prompt", "视频提示词", "动画 prompt", "怎么写更好的提示词", "prompt 方法论", or any task that demands rigor — source verification, multi-perspective structure, weight tuning, priority hierarchy, persuasion-over-accuracy, granularity alignment, or verification checklists.

2799662352 Bundle

用于优化 AI 图生视频/文生视频提示词,解决提示词太长、风格词堆砌、首帧权重被忽视、镜头/光影指令冲突、动作太多导致运动权重稀释、PPT感、动作敷衍等问题。适用于 Seedance/Kling/Hailuo/Sora/Runway 视频提示词优化、首帧霸权、单一主导逻辑、时间线控制、分镜头脚本、运动算力分配。

drmoisan Skill

Converted skill

drmoisan Skill

Converted skill

drmoisan Skill

Converted skill

drmoisan Skill

Converted skill

drmoisan Skill

Converted skill

jcdavis131 Bundle

Behavior for autonomous multi-task execution where the user has delegated the whole plan. Work the task board top-to-bottom, advancing each item to done before the next, and only stop to surface a genuine decision the user must make or a blocker the agent cannot resolve. Integrates addyosmani/agent-skills lifecycle workflows per board item. Use when the user has said "go", "auto", "do the whole thing", "/build auto", or has otherwise delegated the plan rather than a single step.

jcdavis131 Skill

Spawn parallel subject-matter-expert subagents each owning one lane of a complex task, with a fixed output contract, then synthesize. Use when a task spans multiple distinct domains (e.g. security + perf + docs + tests + schema), when a single-agent pass would be shallow across all of them, or when the user asks for a multi-perspective review/report.

majesticlabs-dev Skill

Use when implementing real-time features requiring reliability, especially LLM streaming. Applies AnyCable patterns for message delivery guarantees, presence tracking, and Action Cable migration.

majesticlabs-dev Skill

Verify LLM reasoning using Reverse Chain-of-Thought (RCoT) to detect overlooked conditions.

majesticlabs-dev Bundle

Use when adding polymorphic activity timelines with live Turbo Stream updates to any Rails model. Covers migration, model, concern, shared partials, broadcasting, and optional AI-generated change summaries. Triggers on activity feed, audit trail, timeline, field change tracking, or Turbo Stream broadcasting patterns.

majesticlabs-dev Skill

Patterns for designing multi-agent systems with Claude Code - job description method, shared folder communication, handbook consolidation, context management. Use when building complex agent orchestrations.

openlinksoftware Bundle

Use OPAL Agent2Agent (A2A) clients against OpenLink OPAL A2A endpoints. Trigger when Codex needs to discover an OPAL Agent Card, authenticate with OAuth2 bearer/API key or client-credentials flow, send A2A JSON-RPC tasks, subscribe to streamed task events, fetch task status, attach files, or test OPAL agents/skills exposed through /.well-known/agent.json and /chat/api/a2a. Present recommended endpoints when helpful, but always elicit the target CNAME/base URL/endpoint and credentials before requests.

openlinksoftware Bundle

Intelligent LLM routing informed by a living capability x cost x latency graph. Use when a task (or an agent sub-step) must be routed to the right model — classify the task, map it to a required capability level, apply a cost tier and policy, then pick the Pareto-optimal model with an escalation ladder. Triggers: 'which model should I use for', 'route this task', 'cheapest model that can', 'cost tier', 'Pareto frontier routing', 'model escalation', 'right-size model choice', 'LLM router'. The routing graph is rebuilt from live llm-prices.com feeds + curated seed capability profiles.

openlinksoftware Bundle

Generates Knowledge Graphs from two source types: (A) relational database objects via Virtuoso RDF Views, or (B) documents/text transformed to RDF using schema.org terms. PATH RDBMS — STRICT 5-step workflow: ask local-vs-DSN, enumerate tables, resolve hostname, confirm IRI patterns, generate TBox+ABox+rewrite rules, verify with entity samples. PATH D — 4-step workflow: collect document + {page_url} + format (JSON-LD or Turtle), generate RDF via prompt template, post- generation review (syntax fix, additional Q&A/entity types), save to user-designated folder. TOOL HIERARCHY: read queries use Demo.demo.execute_spasql_query; writes use EXECUTE_SQL_SCRIPT; RDF generation uses chatPromptComplete.

openlinksoftware Bundle

Transforms documents or text into RDF-based Knowledge Graphs using schema.org terms. 4-step workflow: (1) Collect document source, {page_url} as @base, output format (JSON-LD or Turtle by default; others if explicitly stated), and destination folder. (2) Generate RDF via schema.org prompt template using chatPromptComplete. (3) Post-generation review: fix syntax errors, present additional Q&A/defined terms/howtos and entity types for approval, return revised final output if approved. (4) Save approved RDF to designated folder and confirm saved path.

openlinksoftware Bundle

Assemble or exercise OPAL Agents and Skills. Trigger on phrases like 'assemble an agent', 'create an AGENTS.md', 'build a skill', 'exercise an agent', 'test a skill', 'list OPAL agents', 'instantiate an agent', or any request to work with OPAL agents, skills, or function tools.

openlinksoftware Bundle

Configure and manage the OpenLink Request Broker (oplrqb) rule book (oplrqb.ini). Primary use: configure ODBC Agent rules from host DSNs and JDBC Agent rules from discovered JDBC driver JARs. Also covers general Mapping Rules, DB Agent sections (generic_*), Environment sections, broker global settings, alias sections, reinit/restart, log viewing, and version detection. Two modes: (C) www_sv HTTP Admin Assistant on port 8000 — preferred; (A) direct file edit + CLI — fallback. Use when the user asks to configure ODBC or JDBC agents, add or edit mapping rules, view or edit the broker rule book, restart or reinitialize the broker.

ai-creed Bundle

Use when the user asks to lint, audit, test, benchmark, validate, or fix an agent skill — from a single SKILL.md frontmatter check to trigger-accuracy measurement or a corpus-wide audit of installed skills for duplication — driving the shakespii CLI (init, lint --json, test --run, bench) to resolve findings until clean.

ai-creed Bundle

Use when the user asks to create, write, compose, or design a new agent skill — turning an idea, notes, requirement, or repeated workflow into a SKILL.md with eval cases and a trigger set through an interview → draft → critique → refine loop.

thearchitectit Bundle

Context Engineering for AI Agents — 82 MCP tools, 10 read modes, 95+ shell patterns, tree-sitter AST for 26 languages. Compresses LLM context by up to 99%. Use when reading files, running shell commands, searching code, or exploring directories. Auto-installs if not present.

thearchitectit Bundle

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. This skill should be used when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

thearchitectit Bundle

Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior, investigating errors, analyzing tool calls, checking memory operations, or examining agent performance. Automatically fetches recent traces and analyzes execution patterns. Requires langsmith-fetch CLI installed.

hironow Bundle

Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.

hironow Bundle

Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".

hironow Bundle

Protect code paths that have no incoming HTTP request — AI agent tool calls, agent loops, MCP tool handlers, background jobs, queue workers — with Arcjet Guard (`@arcjet/guard` for JS/TS, `arcjet.guard` for Python), covering rate limiting, prompt injection detection, sensitive information blocking, and custom rules. Use when the user says "rate limit my tool calls", "block prompt injection in my agent", "add security to my MCP server", or "protect my queue worker", even without mentioning Arcjet or Guard. Not for HTTP routes, endpoints, forms, or webhooks — that is add-request-protection. Uses the Arcjet CLI (`bunx @arcjet/cli` or `brew install arcjet`) for authentication and site/key setup.

hironow Bundle

日本語の技術文書・書籍原稿の文章規範。整形（一文一行、引用ブロック、脚注、コラム記法）、段落と論証の構成（パラグラフライティング）、論証の厳密さ（ツッコミどころの除去）、読み手の負荷の管理、視点と語り、演出の抑制、LLM っぽい空句の禁止、冗長の排除を定める。日本語で技術書の章、草稿、記事、解説文を書くとき、または推敲・リライトするときに使用する。英語の記事の編集は edit-article。

hironow Bundle

Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling. Do not trigger for general architecture summaries, code review, or non-security design work.

hironow Skill

How to not fool yourself (or be fooled) when verifying work — yours, a reviewer's, a subagent's, or a checker's. Use whenever accepting review findings, grading/judging another agent's output, verifying checksums or pinned versions, interpreting a failing (or suspiciously passing) test or gate, or writing any report that claims something is "done", "green", or "verified". Especially load-bearing when the author and the verifier are the same context — the situation this skill exists to break.

1t1scool Bundle

Set up agent context for a project. Analyzes tech stack, installs relevant skills from skills.sh, generates custom skills, and configures MCP servers. Use when starting new project, setting up AI context, or asking "set up project", "configure AI", "what skills do I need".

1t1scool Bundle

Measure REAL web performance with a budget and regression diff — runs Lighthouse CLI (mobile + desktop) or PageSpeed Insights API against a production URL, checks metrics against a perf-budget, and diffs runs. Never trusts chrome-devtools MCP traces (falsely optimistic). Use when user says "замерь перформанс", "проверь скорость сайта", "lighthouse", "core web vitals", "perf budget", "регрессия скорости", or types /perf-guard.

1t1scool Bundle

Generate professional Agent Skills for AI agents. Creates complete skill packages with SKILL.md, references, scripts, and templates. Use when creating new skills, generating custom slash commands, or building reusable AI capabilities. Validates against Agent Skills specification.

moshe-ship Skill

Arabic LLM benchmarking across 8 quality categories

moshe-ship Skill

Arabic diacritization (tashkeel) via Farasa API, pyarabic, and LLM fallback

moshe-ship Skill

Arabic Siri integration for Hermes — trigger agent tasks via Arabic voice commands through Apple Shortcuts