meditation
Consolidate session learning into permanent architecture — extract patterns into skills, instructions, prompts, or memory
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-10 00:15
Agents & models
26,031 results
llm model selection skill
Choosing the right model for the task — power vs. cost vs. speed.
m365 declarative agent debugging skill
Debug non-functional M365 Copilot declarative agents.
project management skill
Alex+Fabio project management patterns: rapid AI-assisted iteration, meditation-based retrospectives, session-focused work, and safety-first release gates.
rag architecture skill
Build retrieval-augmented generation systems that ground LLMs in your data.
codex-banked-resets
Check live Codex or ChatGPT Codex banked reset credits, reset expiry times, profile usage metadata, and all locally configured Codex accounts with a bundled…
iwsdk-dev
Single entry point for IWSDK development. Invoke first for every IWSDK implementation request. Routes fresh builds to an internal planning playbook and bounded…
live-debugging-mcp
Use this whenever debugging an Android DAT app with local DAT Inspector MCP tools, live device events, Meta AI app/device boundary issues, permissions,…
camera-capture
Capture standalone high-quality photos from connected glasses on iOS
inputs
Receive navigation, button, capture, and drag input events from connected glasses on iOS
motion
Stream accelerometer, gyroscope, magnetometer, and orientation samples from connected wearables on iOS
speech
Recognize speech on connected glasses and consume partial and final transcriptions on iOS
voice-invocations
Launch and activate an iOS app from Hey Meta voice invocations and acknowledge each action
skill-contract-reviewer
Validate an Agent Skill package and choose the right instruction, capability, or lifecycle primitive before implementation.
bauhaus-visual-prompt
Decompose the Bauhaus visual language into medium modules, identify the user's intent, and compile it into a deterministic prompt that can be used directly with image models. Use when the user mentions a Bauhaus-style cover, article illustration, column/event poster, Bauhaus prompt, Bauhaus visual key image, or uploads an interior photo requesting it be changed into a Bauhaus-style studio/space. Output only one finished prompt, without showing the module menu. Not for general design history Q&A or other...
plakatstil-prompt-compiler
Compile text themes, product photos, packaging photos, object photos, or people/service themes into Plakatstil / Sachplakat style prompts. When the user mentions Plakatstil, Sachplakat, German advertising posters, object posters, product advertising posters, vintage advertising, redrawing photos into advertising posters, or asks to judge whether an image looks like Plakatstil…
travel-postcard-agent
Generate complete, directly usable image-model prompts for city travel postcards and city collage posters. This skill should be used when the user mentions city postcards, travel collages, city visual posters, or image-generation prompts, or when the user inputs a city, city + country, holiday, season, or event in a visual-creation context; even if the user only provides a city name, use it when the context clearly indicates visual creation. Do not use it for travel guides, itinerary planning, or ordinary city fact Q&A.
ralph-loop
Spawn isolated claude sessions to iterate on a task until done. Use when user wants to ralph-loop, run an autonomous loop, iterate until tests pass, build…
handover
Compact current work into a next-agent handover. Use when ending a session, the user says handover, transferring work, or preserving continuity.
deliberate
Multi-agent deliberation skill. Forces structured disagreement to surface blind spots. Use when making complex decisions, evaluating trade-offs, or when a…
continue-on-phone
Continue the current coding-agent session on your phone, mobile or any browser — remote access to Claude Code, Codex or OpenCode away from your desk — with…
web-performance-optimization
Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (FCP, LCP, TBT, CLS, Speed Index), identifies render-blocking resources, network…
memory-maintain
Performs periodic housekeeping on ai-context/: archives old changelog entries, separates resolved known-issues, generates an index, and detects CLAUDE.md gaps.…
ccskill-gmail
Companion Gmail skill for Claude Code, complementing the standard Gmail connector. Search, read, create drafts (with attachment support), download attachments,…