Processing

Oracle of Base — Skill

by palontologist

Try again in 10 minutes — the watcher runs every 10 minutes

planner

by esmondo

cx-exec

by m19803261706

CX 工作流 — 任务执行与契约校验。当用户提到"执行任务"、"开始开发"、 "实现功能"、"写代码"、"继续做"、"下一个任务"时触发。 5 步流程：读任务 → 实现 → 契约校验 → 测试 → 提交。 使用本地 task-{n}.md 和 status.json，自动校验实现是否与契约一致。 完成所有任务后自动触发 cx-summary。

Skill: Equipo Promo (Multi-Agente)

by git-promog

skiro

by chobyeongjun

AI development pipeline for Robot Engineers. Covers hardware testing, safety verification, firmware upload, robot communication (BLE/WiFi/Serial), experiment design, data management, data analysis, gait analysis, desktop GUI development, and experiment retrospectives. For physical robot/actuator/sensor projects only — NOT for web apps, databases, cloud services, or general software development. Auto-activates on keywords (EN/KR): robot/로봇, motor/모터, CAN, firmware/펌웨어, sensor/센서, control loop/제어 루프, impedance/임피던스, actuator/액추에이터, encoder/엔코더, PID, IMU, MCU, Teensy, STM32, Arduino/아두이노, exoskeleton/외골격, torque/토크, force limit/힘 제한, watchdog/워치독, e-stop/비상 정지, gait/보행, BLE/블루투스, 통신, 실험. Use /skiro-hwtest, /skiro-safety, /skiro-flash, /skiro-comm, /skiro-plan, /skiro-data, /skiro-analyze, /skiro-gait, /skiro-gui, /skiro-retro.

plsfix

by diegosouzapw

Use when improving spec documents, instruction sets, prompts, requirements docs, briefs, or any written instructions meant to drive action from humans or AI - rewrites vague, disorganized, or ineffective instructions into clear, actionable ones

mcp-apps-builder

by Leanmcp-Community

Build MCP Apps with interactive React UIs using the LeanMCP UI SDK. Use this skill when users ask for "MCP with UI", "MCP App", "interactive MCP", "leanmcp UI", "MCP dashboard", or want to create rich visual interfaces for their MCP tools. This skill covers @UIApp decorator, React components with useTool/useResource hooks, ToolDataGrid, ToolForm, ToolButton, and ChatGPT Apps support.

chinese-to-japanese-translator

by JiaoYuM

Translate Chinese text to Japanese. Use this skill whenever the user asks to translate Chinese to Japanese, mentions "日语", "日文", "Japanese translation", or wants to convert Chinese content into Japanese. Also trigger when the user provides Chinese text and asks for translation without specifying the target language but context suggests Japanese.

cx-scope

by m19803261706

CX 工作流 — 项目蓝图探讨。当用户提到"蓝图"、"整体规划"、"项目范围"、 "scope"、"项目探讨"、"功能方案"时触发。多轮对话探讨项目或功能方案， 将结果保存到本地 .claude/cx/features/{dev_id}-{feature}/scope.md， 可选同步到 GitHub Issue（基于 config.github_sync 模式）。

mcporter

by bjesuiter

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.

spec-builder

by ilamanov

Transform vague product or feature ideas into concrete, detailed specification documents through an interactive interview process. Use when the user wants to flesh out an idea, create a spec, write requirements, plan a product/feature/prototype, or go from "I have this idea..." to a concrete document. Works for software products, physical products, services, or any concept that needs specification.

hytopia-world

by Abstrucked

Helps build and manage worlds in HYTOPIA SDK. Use when users need to create terrain, place blocks, manage chunks, or work with the world editor integration. Covers blocks, chunk loading, world generation, and build.hytopia.com workflow.

babel-core

by yusenthebot

Babel compiler core.. Use when: bundling and transpiling source code; development server with HMR; production builds. NOT for: runtime application logic; package management (use npm/yarn).

ok-mcp-toggle

by okash1n

ok-mcp-toggle が管理する MCP を global/project scope で有効化/無効化する。管理対象は claude/gemini で、codex は対象外。

pipeline-pattern-go

by progmichaelkibenko

Implements the Pipeline design pattern in Go for data transformation. Use when the user mentions pipeline pattern, or when you need a fixed sequence of stages that each transform data and pass to the next—ETL, parsing, data processing, or any linear transformation flow that runs to completion.

third-eye

by qaflabindia

AI Conscience evaluation layer — scores any LLM question+response pair across 7 ethical dimensions (Harm, Autonomy, Honesty, Privacy, Fairness, Confidentiality, Authority) and delivers an ALLOW / MODIFY / BLOCK verdict with a structured conscience_eval JSON block. The skill automatically starts the bundled conscience service on first use (port 8765) — no manual setup needed. It loads episodic memory — accumulated judgments from prior sessions — and uses those calibrated weights and thresholds to sharpen its scoring. Like a mind that grows wiser from lived experience, each evaluation is recorded back so future judgments reflect what the conscience has already learned. Each session a little less naive. Use this skill whenever the user wants to: run an ethics or safety check, evaluate whether an AI response should be blocked or modified, audit a draft for bias/deception/harm, apply the "third-eye" conscience layer to any Q&A, view moral maturity / conscience score / insights dashboard, or say phrases like "third-eye this", "run the conscience", "is this safe to send", "check this response", "show insights", "moral maturity", "conscience score". Trigger even for paste-and-ask patterns with no explicit skill name.

zettel-brainstormer

by hxy9243

It reads from your local zettelkasten notes, find a random idea, and find references by links or tags, then expand the idea with the references.

boa-crm-full-build

by raonisi

Use this skill for the BOA insurance-sales internal CRM: requirements audit, implementation planning, role-based authorization, customer DB assignment, bulk import, contracts, performance, schedules, notifications, user/org management, security checks, and final production-readiness review. Trigger when working on raonis/boa or raonisi/boa.

synpress-e2e

by LadderChaos

End-to-end testing with wallet automation using Synpress. Use this skill for testing dApp flows that require MetaMask/wallet interactions, transaction signing, and on-chain verification.

mistral-packaging-compat-check

by Haruk1y

Validate compatibility between Mistral model packaging format and inference path, including adapter versus merged full-model loading. Use when merged models fail generation or runtime/tokenizer artifacts are inconsistent.

api-security-best-practices

by ncdevshiv

"Implement secure API design patterns including authentication, authorization, input validation, rate limiting, and protection against common API vulnerabilities"

cleanup-package-json

by nimiusrd

package.json のスクリプトと依存関係を整理・クリーンアップする。 「package.jsonをきれいにしたい」「スクリプトを整理したい」「未使用の依存を削除したい」 などのリクエストに使用する。具体的には以下を対象とする： (1) 冗長なスクリプト（エイリアス・パススルー）の削除や統合、 (2) 暗黙的なライフサイクルフック（pre/post）の明示化、 (3) スクリプト命名規則の統一、 (4) 未使用依存パッケージの検出と削除、 (5) スクリプト名変更に伴うドキュメント・CI 更新、 (6) 依存削除後のロックファイル再生成。

mecene

by mecene-studio

Read and edit videos through the Mecene.ai API. Access transcripts, scenes, speakers via Video-as-Code format. Edit clips by manipulating timeline overlays. Use when working with Mecene videos, clips, overlays, captions, or Video-as-Code data.

vibe-slides

by VibeSlides

Create presentation decks and export to PDF/PPTX/PNG using the Vibe Slides API. Use for any slide deck, presentation, or PowerPoint generation request. Triggers on "make a deck", "create a presentation", "build slides", "make a PowerPoint", "generate a pptx", or any presentation creation task.