pinion05

Use when you completed any task and need to log what was done with timestamps for future audit/review.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

This skill should be used for comprehensive Telegram automation via Telethon API. Use for sending/receiving messages, monitoring chats, running a background daemon that triggers Claude Code sessions, managing channels/groups, and downloading media. Triggers on "telegram daemon", "monitor telegram", "telegram bot", "spawn Claude from telegram", or any Telethon-related request. IMPORTANT: Use `draft` command for "драфт/draft", use `send` for "отправь/send"; if ambiguous, ASK before sending.

Extract YouTube video transcripts with metadata and save as Markdown to Obsidian vault. Use this skill when the user requests downloading YouTube transcripts, converting YouTube videos to text, or extracting video subtitles. Does not download video/audio files, only metadata and subtitles.

This skill should be used when updating ~/Sites/agency-docs meeting documentation after Claude Code lab sessions. Automatically creates/updates meeting MDX files with Fathom links, YouTube embeds, fact-checked summaries using claude-code-guide agent, and presentation content. Auto-detects lab number from filename, finds presentations, commits and pushes changes.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Applies Agency brand colors and typography to artifacts including presentations, SVG graphics, documents, and web interfaces. This skill should be used when brand colors, visual formatting, neobrutalism style, or Agency design standards apply. Keywords - branding, corporate identity, visual identity, styling, brand colors, typography, visual formatting, visual design, neobrutalism.

Query browsing history from all synced devices (iPhone, Mac, iPad, desktop). Supports natural language queries for filtering by date, device, domain, and keywords. Uses LLM classification for content categories. Can output to stdout or save as markdown/JSON to Obsidian vault.

MUST use this skill for any codex-claw request to send or return one local file to the user. NEVER use generic Telegram send commands, Saved Messages, or unrelated Telegram skills for codex-claw file delivery.

MUST use this skill for interactive CLI workflows that require login, approval, prompts, device-code, OAuth, or long-running terminal sessions. Prefer `npx -y agentty-cli` over plain shell execution.

Create or update codex-claw scheduled job definitions under ~/.codex-claw/cronjobs.

Fetch live LLM model rankings and Artificial Analysis composite indices — Intelligence Index, Coding Index, and Agentic Index — plus speed and pricing from https://artificialanalysis.ai/leaderboards/models. Use when the user asks for model benchmarks, "best models", model comparison, leaderboard/ranking, "가장 성능 좋은 모델", "모델 순위", "코딩 잘하는 모델", "에이전트/코딩 점수", Intelligence/Coding/Agentic Index, model speed/latency/pricing, or which model to pick for a task. Returns current (live) data, not cached.

OMX의 실행 전 명확화 discipline과 Superpowers brainstorming, deep-interview의 장점을 합쳐 Discovery → Design → 승인 가능한 spec으로 수렴시키는 통합 skill.

번개장터를 CLI로 검색, 상세조회, 찜, 채팅, 대량수집하는 도구를 사용할 때 참고하는 사용 스킬

Use when investigating which Korean domestic fashion brands currently run sales on their own official stores, especially broad multi-brand sweeps, 공홈 세일/블프/시즌오프 research, or requests that must exclude platform-internal promotions.

Search the web from the shell using curl, grep, sed, and python for research, fact-checking, and data gathering. Activates when the user asks to search, research, look up, investigate, or find information online — especially when structured extraction, multi-source comparison, or automated pipeline-style research is needed. Covers Wikipedia scraping, GitHub API queries, REST API consumption, multi-language comparison, and HTML table parsing.

Use this skill when you need to turn one URL into an LLM context text file for an agent workflow. It runs the llm-page-context-cli package, saves the context text into ./llm-page-context by default, and returns machine-readable JSON containing the absolute file path and token estimate.

Use when a user asks for the token count of a prompt, text snippet, or local file, or wants to estimate whether content will fit inside an OpenAI model context window.

Use when a predefined GEO query bundle must be run through the ChatGPT website and converted into a reusable deep analysis report with portable batch artifacts.

Use when automating a website login and you want Bitwarden autofill to trigger reliably with minimal manual typing.

새 플레이어 PC를 코블몬 서버에 자동 연결. Tailscale + Fabric + Cobblemon 설치.