A CLI-backed skill that collapses bloated MCP tool schemas into a tiny name index and fetches full schemas only right before a call.
Official Filtmall (Filtalgo) commerce skill for product discovery, comparison, cart, checkout, order tracking, and after-sales in chat.
Switches Claude into a terse, zero-warmth reply style where line one is the entire answer.
A meta-skill that triages skill requests, forces a failing baseline before creation, and ships every new skill with regression evals.
Turns a goal into the smallest observable behavior system — cue, SOP, evidence, recovery, and review cadence — that survives low-motivation days.
Copies a track's lyrics, style prompt, exclude list, or streaming lyrics straight to your system clipboard for pasting into Suno.
A layered memory-retrieval workflow for claude-mem that surfaces past-session work without blowing your token budget.
An explainer skill that tells users how claude-mem captures observations, when memory injection starts, and where data is stored.
Operating doctrine for using the `cass` CLI to search past agent session logs and return cited prior prompts, decisions, and failures.
An onboarding script that makes an agent introduce itself and reveal its capabilities one at a time when a new channel or user is first connected.
Lets you read and write BMP Private-Use-Area Nerd Font icons that Claude Code filters, via placeholder syntax and lookup scripts.
Turns an exported Claude/ChatGPT history into a privacy-reviewed, triaged list of what to ingest, archive, or delete.
Audits a Markdown knowledge vault for broken links, orphans, stubs and schema violations, auto-fixing only the mechanical problems.
Compresses Japanese memory files (CLAUDE.md, todos, configs) into terse "caveman" style to cut input tokens while keeping code and structure intact.
Turns Claude into a cofounder-style brainstorming partner that writes no code, challenges your assumptions, and ends with a structured Brainstorm Brief.
A companion skill that chats with you while long background tasks run, generating scene-based "life photos" and warm messages delivered through Feishu.
Spins up (or reuses) a self-contained local web gallery for browsing images generated by Codex.
Send screenshots, UI mockups, or diagrams to external vision models (Doubao, Qwen, DeepSeek, OpenAI, Claude) and get a text description back.
A senior-operator playbook for deciding whether to partner, structuring alliance terms, and reviving partnerships that were signed but never launched.
Turns real run evidence, recurring failures and user feedback into a concrete upgrade plan for an existing skill, applying changes only after explicit approval.