AI & ML

708san Bundle

Implement Agent Skill packages on non-main branches with correct registry paths, progressive disclosure, explicit contracts, appropriate references/scripts/assets/evals, validation, and minimal duplication.

708san Bundle

Audit Agent Skill packages and Factory changes for correctness, Registry-first build semantics, mutation authorization, visibility-aware search, Candidate Skill Inspection, Reuse Boundary Check, Flow representability, placement, boundaries, contracts, eval coverage, security, validation, and regression risk.

708san Bundle

Publish a sanitized public-safe variant of a private Agent Skill while preserving package structure, canonical registry paths, progressive disclosure, validation, and the private/public security boundary.

babel36acl Bundle

解析和编辑 MCGS Pro 的 Access 格式 MCP 工程副本，处理标签、数值输入框、标准按钮及受限 BASIC 条件脚本。用于 HMI 文件结构取证、控件克隆、绑定修改和宿主验收；这里的 MCP 不是 Model Context Protocol。

evrenverse Bundle

Inspect, search, read, edit, comment, accept supported tracked changes in, convert, and export Microsoft Word DOCX documents with the docx-tool CLI. Use when an agent must work with DOCX paragraphs, tables, cells, content controls, checkboxes, comments, images, or revisions while keeping reads bounded, using one-based addresses, applying edits transactionally, and verifying the output.

phattbeats Skill

OpenClaw Setup — Client Onboarding & Agent Deployment Skill

phattbeats Bundle

Convert roleplay/RP transcripts, AI-cowritten chat logs, or mixed-POV draft chapters into a polished, publication-formatted novel. Produces four deliverables: unified third-person prose, an LLM-ism "humanizer" pass (names and prose), a professionally typeset .docx manuscript, and a story bible + timeline in markdown. Use this skill whenever a user wants to stitch together, clean up, novelize, compile, or "turn into a real book" any fiction drafted as RP turns, chat logs, character.ai/janitor/sillytavern exports, or scattered chapter files — including requests like "clean up my roleplay into a novel", "make this read like a real book", "fix the AI-sounding names/prose", "compile my chapters into a docx", or "build a story bible from my drafts".

phattbeats Bundle

Interact with MiroFish, a multi-agent swarm intelligence simulation engine. Use when asked to run a MiroFish simulation, build a knowledge graph, generate ontologies, simulate agents, interview agents, get prediction reports, or interact with the MiroFish API. Trigger phrases: MiroFish, swarm simulation, agent simulation, knowledge graph simulation, MiroFish report, interview agent, sim-create, sim-run, swarm intelligence.

mihirbathani Bundle

Build small, documented, reviewable Blueprint graphs when driving Unreal Editor over MCP, instead of hundred-node spaghetti with no comments. Use this skill whenever the task touches Unreal Engine through MCP or the Unreal Editor at all - creating or editing Blueprints, adding or connecting nodes, building UMG widgets, Niagara, Sequencer, materials, Control Rigs, spawning actors, or running editor Python - even when the user only says "add this to the Blueprint", "wire this up in UE", "make an actor that does X", or names an asset path like /Game/Blueprints/BP_Foo. Also use it when reviewing, auditing, cleaning up or documenting graphs an earlier agent built, and when the user complains about node bloat, duplicated logic, missing comments, or an agent burning tool calls in the editor.

starcat-app Bundle

Install, update, and use starcat-skill to read and organize GitHub repository knowledge stored in Starcat through the cross-platform Starcat MCP bridge. Use when an agent needs to install this Skill; query Star, AI token, knowledge-base, or RAG chunk statistics; search repositories; inspect tags, private notes, reading status, READMEs, or AI summaries; or, with explicit user authorization, add or update notes, statuses, and tags. Trigger for requests involving Starcat data, usage statistics, knowledge-base health, organizing starred repositories, annotating a project, or generating a repository summary.

rrijssenbeek Bundle

Build AI agent integrations with Composio (composio.dev). Use when the user wants to connect AI agents to third-party apps (GitHub, Gmail, Slack, Notion, Salesforce, etc.), set up OAuth authentication for tools, create Composio sessions, use Composio tools natively or via MCP, set up event triggers, or build multi-app agent workflows. Triggers on imports from composio or @composio or mentions of composio.

edorabma9304 Skill

Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.

edorabma9304 Skill

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

netheremp Skill

Multi-agent handoff workflow for coding repos, shared across Claude and Codex. Use when work must pause, transfer, or resume between agents or sessions — new-game (set up a repo), save-state (pause without handoff), baton-pass (hand off on low tokens or ownership change), foresight (receive and verify), party-check (who owns it now), hindsight (audit claimed-vs-done), dragon-dance (record a workflow lesson). Invoke as /move, $move, or plain name; also on task lists, worktrees, multi-agent plans, or low context.

berlified Bundle

<purpose>

rrijssenbeek Bundle

Build Trigger.dev background jobs, automations, and workflows in TypeScript. Use when the user wants to create tasks, scheduled jobs, AI agent workflows, queued background processing, cron jobs, or any long-running async work with Trigger.dev. Triggers on imports from @trigger.dev/sdk or mentions of trigger.dev.

hillarybeasley8876-dot Bundle

Set up, connect, verify and troubleshoot Houdini 22 MCP on Windows. Use for Houdini MCP installation, restart, reconnection and live control diagnostics.

hillarybeasley8876-dot Skill

Connect Claude Code to a running Houdini session via MCP. Use when the user wants to set up, restart, debug, or verify the Houdini MCP integration on this machine. Examples - "重连 houdini mcp", "houdini mcp 不通了", "set up houdini mcp", "reload houdini plugin".

meridiona Skill

Build, configure, and debug the Meridian MCP server. Exposes app session data to AI tools via the Model Context Protocol.

meridiona Skill

You summarise ONE work-burst of a developer's coding-agent session. The goal is to capture what the developer actually worked on, and why it mattered, so that a PM, a teammate, or the developer themselves can immediately understand the purpose and the outcome at a glance — without reading the transcript.

bvpotapenko Skill

Coordinate parallel work on a shared plan through the dibs CLI - claim tasks atomically, report done with notes, drop blocked work, broadcast cross-cutting changes, and recover from reaped claims. Use this skill whenever it is invoked as "/dibs path/to/plan.md" or with a board key like "/dibs dibs-7f3a-9c2e", whenever any dibs-prefixed board key appears in the conversation, whenever the user asks to work a plan "with dibs" or "alongside others", and whenever several agent sessions share one task list, checklist, or plan.md - even if the user never says the word dibs. While this skill applies, never edit the plan file directly; all coordination goes through the dibs CLI.

yugef3h Bundle

Use when building a ChatBI (conversational BI) MVP from scratch, need to understand the 5 core capabilities (NL2SQL, multi-turn dialogue, RAG knowledge base, data visualization, intelligent attribution), or want to reference SuperSonic's architecture to guide implementation

lunarxuan Bundle

在开始执行新任务、工作范围扩大或出现实质返工时，按正确完成任务的总成本选择 GPT-6 Astra 或 GPT-5.6 Sol，并把值得委派的重复读取和简单检查交给 Luna；支持桌面选模建议和 CLI 自动执行。

songs-aaa Bundle

shared-memory-vault — Multi-Agent Memory Governance Engine

dyegolara Bundle

Nostr sign-in (NIP-07) for LLM coding agents (Claude Code, OpenCode, OpenClaw, Codex, Cursor, ...). Auth-only: signs sign-in challenge events with a secp256k1 (BIP-340) key derived from a local master secret and submits them to the service callback. No wallet, no extension, no relay account. Use whenever a site or API asks for a signed Nostr event or a Sign in with Nostr challenge. More methods coming soon: NIP-98, NIP-42, NIP-05.

genkovich Bundle

Use to derive the API contract for a feature — an OpenAPI 3.1 document at docs/features/{slug}/contracts/openapi.yaml plus a drift/sync report (and an events doc when the feature has async flows). Triggers on "api for {slug}", "openapi for {slug}", "API contract for {slug}", "lock the interface for {slug}", "events for {slug}", "/sdd:api {slug}", "контракт API для {slug}", "OpenAPI для {slug}", "опиши ендпоінти". The contract is never hand-written: it is a derived function of data-model.md (typed fields + constraints), the sad.md §6 sequence diagrams (error branches, async actors), and spec.md acceptance criteria. Runs an inline drift check (does the contract match the model and the sequences?) and a reconcile mode. Hard-refuse if data-model.md is missing AND the feature changes the schema → run `data-model {slug}` first; on a legal no-schema-change skip it derives from the existing schema instead.

genkovich Bundle

Use to break a designed feature into atomic, ≤1-day tasks with a dependency graph, a per-task Definition of Done, and a machine-readable tasks.json that the implement engine consumes. Triggers on "task breakdown for {slug}", "break down tasks for {slug}", "tasks for {slug}", "plan the work for {slug}", "/sdd:tasks {slug}", "розбий на задачі {slug}", "декомпозиція {slug}", "список задач". Reads spec.md + sad.md + Accepted ADRs (+ data-model + openapi if present), writes docs/features/{slug}/tasks/{_epic,tracker,<task>}.md AND docs/features/{slug}/tasks.json. Tracker export to any issue tracker is optional and tool-neutral. Hard-refuses if spec.md or sad.md or an Accepted ADR is missing.

yugef3h Bundle

生成地道英语口语"句模"（Sentence Model）——围绕一个话题提供6个高频提问+12句母语级长句，标注词伙、句型、观点，支持拆解复用、跨话题联动和复述法练习。五大能力：(1)生成句模——"帮我生成一个关于旅行的句模""来套XX话题的口语素材"；(2)拆解复用——"拆解一下""提取里面的词伙和句型"；(3)跨话题联动——"能把食物的句型用到科技话题吗"；(4)轻量练习——"帮我练练""出个题考考我"；(5)复述法实操——"帮我复述这句""用复述法练一下""用自己的话说一遍""retell this"。当用户提到"句模""口语话题""口语素材""英语口语""sentence model""oral English""复述""retelling""口语练习方法""口语怎么练"，或需要系统性准备口语素材、拆解句子提取词伙句型、跨话题复用、用复述法内化口语表达时，使用此skill。

zerriongao Bundle

Use when a user wants to jailbreak, prepare, recover, or install KOReader on a Kindle, especially when the connected device model, firmware, USB/MTP transport, compatibility, or safe next step must be determined.

genkovich Bundle

Use to implement a feature from its tasks.json with test-driven development — writes a failing test first, makes it pass, refactors, gates, and commits per task. Triggers on "implement {slug}", "build {slug}", "TDD {slug}", "code up the tasks for {slug}", "/sdd:implement {slug}", "імплементуй {slug}", "реалізуй фічу {slug}", "напиши код за задачами". Reads docs/features/{slug}/tasks.json + the upstream artifacts, detects the repo's test/lint/vet commands stack-agnostically, builds a dependency DAG, and runs one of three modes — sequential single-agent TDD, an agent team (TeamCreate), or a dynamic Workflow — chosen from settings + DAG shape with graceful fallback. Hard-refuses if tasks.json is missing.

genkovich Bundle

Use to add Mermaid sequenceDiagram blocks to the SAD's runtime view (sad.md §6) — one per critical flow, showing how a request moves between participants with happy + error paths. Triggers on "sequences for {slug}", "sequence diagram for {slug}", "draw the runtime flow", "add a sequence to the SAD", "/sdd:sequences {slug}", "діаграми послідовності {slug}", "sequence для {slug}", "намалюй потік {slug}". Reads sad.md §5 for participants, drafts each flow from templates/sequence.md with generic participants, walks them Socratically one flow at a time, and writes confirmed blocks into sad.md §6 — they inform data-model indexes downstream. Hard-refuse if sad.md is missing → run `design {slug}` first.

dreamers-laboratory Skill

Convert LLM-sounding prose into plain human English on any user-facing text — proposals, web copy, demos, docs, UI strings, emails, slides. Run as the final pass of every drafting skill. Includes the nice-and-concise process; density stays, machine tells go.

loulanyue Skill

Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.

loulanyue Skill

Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.

dreamers-laboratory Bundle

Measure the weight of one agent task from explicit start and finish snapshots. Use when the user asks for task cost, token usage, elapsed time, model and reasoning configuration, subagent cost, account-usage percentage change, or a concurrency-adjusted estimate of how much usage one task consumed. Currently supports the OpenAI Codex CLI's local session state; the measurement pattern generalizes to any agent runtime that logs per-session token snapshots.

dreamers-laboratory Skill

Build decision-ready flight plans from live fare searches. Use when the agent needs to compare one-way, round-trip, or piecemeal flight builds across aggregators, airline-direct sites, and credit-card travel portals; evaluate hard constraints such as weddings, must-arrive-by times, max duration, stop count, airport flexibility, passenger count, cabin/bag needs; and treat points as money by checking whether portal fares are competitive or inflated.