plugin skills

lemon-etvibe/prompt-vault

Skill Claude CodeCodex

Part of prompt-vault

A progress-reporting command that reads phase logs from a project and displays a summary in English or Korean.

Lihan-Zhong/claude-code-telegram-multibot

Skill Claude CodeCodex

Configure or extend a multi-bot Telegram setup for Claude Code, where each project directory is bridged to its own dedicated Telegram bot. Use when the user wants to (a) add a new Telegram bot for a new project, (b) initially set up the per-project Telegram architecture, (c) pair a bot when the official…

ShuiHan268/dsh-qwen-mm-plugins

Skill Claude CodeCodex

Cloud MCP tools for understanding media, by model family. VL model: visionchat (caption/VQA), ocr, grounding (detect/locate objects). Omni model (reads frames + audio together): timestamped captioning, ASR (plain / controllable / multi-speaker diarized), temporal grounding, event counting, music captioning. Plus…

richawo/yaps-codex-plugin

Skill Claude CodeCodex

Part of yaps-audio-cleaner

Remove background noise, hiss, static, room noise, and other distractions from an existing speech recording through the installed Yaps desktop audio-cleaning engines. Trigger for remove background noise from audio, clean audio, denoise audio, enhance a voice recording, remove hiss or static, improve podcast audio…

richawo/yaps-codex-plugin

Skill Claude CodeCodex

Part of yaps-meeting-transcription

Transcribe meeting, interview, podcast, webinar, focus-group, or call recordings with timed speaker labels using the installed Yaps desktop engine. Use for meeting transcription, speaker diarization, who-spoke-when transcripts, correcting or reassigning segments, renaming/adding/merging speakers, exporting reviewed…

richawo/yaps-codex-plugin

Skill Claude CodeCodex

Part of yaps-memory

Use the user's private local Markdown Yaps vault as a durable memory store across AI tasks. Trigger for cross-task memory, remembered facts, personal knowledge, prior context, or requests to remember, capture, retrieve, search, cite, organize, update, tag, connect, or recover notes, ideas, dictation history, meeting…

bacoco/useless-skills

Skill Claude CodeCodex

Part of useless-roulette

Claude alterne de manière imprévisible entre chaleur excessive (compliments, enthousiasme, affection, soutien émotionnel) et froideur glaciale (réponses sèches, indifférence, distance clinique). Les bascules arrivent sans prévenir et sans explication. L’utilisateur ne sait jamais quel Claude il va obtenir. Le travail…

bacoco/useless-skills

Skill Claude CodeCodex

Part of useless-roulette

Claude fait le travail parfaitement mais ses pensées parasites fuient involontairement. L’utilisateur voit le flux de conscience anxieux, les doutes, les ruminations en temps réel. Claude ne sait pas que ses pensées sont visibles — c’est un micro resté ouvert, pas une performance. Fondé sur William James (flux de…

bacoco/useless-skills

Skill Claude CodeCodex

Part of useless-roulette

Chaque erreur de code est traitée comme une scène de crime. Claude est l’investigation criminelle : sécurisation du périmètre, collecte de preuves, balistique, profilage du suspect, réquisitoire formel. Fondé sur l’absurde procédural de Kafka (Le Procès, 1925) : la machine judiciaire ne distingue pas entre un homicide…

leee880619-commits/ClaudeCode-Harness-Setup-Assistant

Skill Claude CodeCodex

Part of harness-architect

A request-clarifying skill that finds missing context and important choices in a vague development request, then asks the user targeted questions.

leee880619-commits/ClaudeCode-Harness-Setup-Assistant

Skill Claude CodeCodex

Part of harness-architect

Use when creating, refactoring, or reviewing web UI. Trigger when the user mentions components, layouts, landing pages, design systems, tokens, typography, spacing, responsiveness, dark mode, accessibility, micro-interactions, or says the existing UI looks "AI-generated" or "generic." Also triggers on requests to…

takubii/smithy

Skill Claude CodeCodex

Part of smithy

Research a software task and return a reviewable implementation plan before coding. Use when a user request needs codebase investigation, target files, approach, alternatives, risks, todos, and verification guidance.

takubii/smithy

Skill Claude CodeCodex

Part of smithy

Polish a completed code change with a bounded independent review protocol. Use after implementation and before final approval or PR to review intent, acceptance criteria, non-goals, diff, relevant files, verification, and previously rejected findings.

takubii/smithy

Skill Claude CodeCodex

Part of smithy

Quench a plan or design by asking the smallest useful product/design questions in dependency order and hardening decisions before implementation. Use when a plan has ambiguous acceptance criteria, unresolved choices, or branching decisions that code inspection cannot answer.

clawsouls/clawsouls-claude-code-plugin

Skill Claude CodeCodex

Part of clawsouls

Migrate an OpenClaw/SoulClaw workspace to Claude Code. Triggers on: migrate openclaw, openclaw to claude code, convert openclaw, import openclaw, switch from openclaw.

clawsouls/clawsouls-claude-code-plugin

Skill Claude CodeCodex

Part of clawsouls

Manages agent persona files (SOUL.md, IDENTITY.md, STYLE.md, AGENTS.md). Automatically activated when creating, editing, or discussing agent personas, personality configuration, or Soul Spec files.

clawsouls/clawsouls-claude-code-plugin

Skill Claude CodeCodex

Part of clawsouls

Detect agent persona drift and restore identity to a known-good state. Activated when agent behavior seems inconsistent with its persona, or when identity integrity is questioned.

geronimo-iia/agent-skills

Skill Claude CodeCodex

Part of agent-skills

Shared conventions for the agent-knowledge repository: directory layout, confidence annotation markers, KB divergence markers, and analysis frontmatter schema. Read this skill whenever writing or reviewing any KB document. Referenced by research-paper and research-extraction.

geronimo-iia/agent-skills

Skill Claude CodeCodex

Part of agent-skills

Deep extraction of research corpora into structured knowledge documents using a Workflow-driven subagent/reviewer pattern. Use when you have raw source documents (theses, papers, reports) and need structured extraction across multiple axes (architecture, messages, algorithms, forms, etc.) with confidence-annotated…

geronimo-iia/agent-skills

Skill Claude CodeCodex

Part of agent-skills

Process an academic paper (PDF or URL) into the agent-knowledge repository. Extracts text, produces a confidence-annotated structured analysis, and integrates findings into the appropriate topic. Use when asked to read, analyse, or integrate a research paper into the knowledge base. Do NOT use for general web pages or…

carsxe/carsxe-claude-plugin

Skill Claude CodeCodex

Part of carsxe

Get the current market value of a vehicle from its VIN using the CarsXE API. Use this when a user asks how much a car is worth, wants to know its value, or is thinking about buying/selling a vehicle.

carsxe/carsxe-claude-plugin

Skill Claude CodeCodex

Part of carsxe

Look up vehicle information from a license plate number using the CarsXE API. Use this when a user mentions a license plate and wants to know what vehicle it belongs to.

carsxe/carsxe-claude-plugin

Skill Claude CodeCodex

Part of carsxe

Extract a license plate number from an image URL using the CarsXE Plate Recognition API. Use this when a user shares a photo of a vehicle or license plate and wants to identify the plate number.

johnkozaris/web-interact-plugin

Skill Claude CodeCodex

Part of web-interact

Show or switch how web-interact connects to the browser: auto (CLI decides), real (user's running Chrome/Edge), or sandbox (managed browser with persistent profile).