Interface design with craft and consistency. For dashboards, apps, tools — not marketing sites. Uses Subcog for persistent design memory.

当用户没有简历、想通过对话建立画像时使用。触发条件：用户说'我没有简历/帮我建画像/不知道怎么写简历'，或 CONTEXT 显示无画像 + 用户表达想了解方向。边界：已有画像的用户走其他 skill。

Analyze a project's past Codex sessions, memory files, and existing local skills to recommend the highest-value skills to create or update. Use when a user asks what skills a project needs, wants skill ideas grounded in real project history, wants an audit of current project-local skills, or wants recommendations for updating stale or incomplete skills instead of creating duplicates.

Build SwiftUI views with modern MV architecture, state management, and view composition patterns. Covers @Observable ownership rules, @State/@Bindable/@Environment wiring, view decomposition, custom ViewModifiers, environment values, async data loading with .task, iOS 26+ APIs, Writing Tools, and performance guidelines. Use when structuring a SwiftUI app, managing state with @Observable, composing view hierarchies, or applying SwiftUI best practices.

Persistent session memory for Ethereal. Maintains context between Cowork sessions so nothing gets lost. Updates CLAUDE.md, tracks open tasks, records decisions, and ensures session handoffs are clean. Use at START and END of every session.

>

Configure GSD workflow preferences including model profiles and agent settings. Use when the user says 'settings', 'configure', 'change profile', or wants to adjust workflow parameters. (Codex adapter)

Use this skill whenever the user wants durable context, cross-project memory, shared procedures, audit trails, Obsidian-backed knowledge, or a reusable operating layer across multiple agent sessions. Trigger aggressively on requests to remember decisions, save findings, reuse previous workflows, coordinate several agents, maintain shared organizational context, install or activate MAKOS, or avoid starting from scratch in each conversation.

Diagnose recognition accuracy by aligning expected events (score_structure.json or expectedPerformance fallback) with recognizer output

Expert guidance for building event-driven architectures with Apache Kafka from hello-world prototypes to production-ready systems. Use when working with (1) Kafka producers and consumers, (2) Event streaming and stream processing with Kafka Streams, (3) Data integration with Kafka Connect, (4) Cluster setup and operations, (5) Production deployment and monitoring, (6) Schema management and data contracts, (7) Performance tuning and fault tolerance. Covers Java, Python, Node.js implementations.

Validate UI screens against Lucid Labs design system rules. Use after implementing UI components to verify adherence to brand colors, typography, layout patterns, and service board logic.

Work with PrimePath's distributed computation engine across Metal GPU, CPU NEON, and multi-device networking. Use when modifying GPU shaders, load balancing, Conductor/Carriage networking, Nester Carry Chain math, or the three-gear auto-shifting engine.

Evaluate LLM models for cost/performance ratio. Fetches current pricing and recommends optimal model for your use case. Use during project init or when optimizing costs.

Social graph protocol integration for Copium app using Tapestry API. Use when building social features - profiles, follows, content/posts, comments, likes, activity feeds, identity resolution, or trades. Covers all 41 Tapestry API endpoints.

Guides and best practices for working with Neon Serverless Postgres. Covers setup, local development, connection methods, Neon features, and platform tooling.

Use periodically to check whether AI is actually making you faster. METR's 2025 RCT found developers believed they were 20% faster with AI while actually being slower. This skill enforces measurement over perception.

Build taste through volume of output, deliberate failure, and speed. Taste cannot be developed by watching. It's sharpened by making, failing, and making again. Use when designing practice routines, breaking through creative blocks, or helping someone move from analysis to execution.

Response timing, acknowledgment, and making the interface feel alive. Every action deserves a response at the right speed. Use when designing interactions, evaluating responsiveness, or diagnosing why a product feels sluggish or dead.

The 10-second design audit. Look at any design and name what's working and what's not within seconds. Trains rapid pattern recognition for hierarchy, spacing, type, and color. Use when evaluating designs quickly, giving first-impression feedback, or building perception speed.

p6-earned-value

End-to-end pipeline for scraping Twitter for GTM/DevRel tech startup jobs using Apify, and validating them against an Ideal Customer Profile (ICP) using Gemini's native Google Search Grounding. Use this skill when OpenClaw needs to find developer-first, funded startups actively hiring for GTM, DevRel, or Growth roles.

Operationalize design and copy as a growth lever.

People and company intelligence via the Sixtyfour AI API. AI research agents that read the live web — not static databases — to return structured, confidence-scored profiles. Use when you need to: (1) enrich a lead with full profile data (name, title, email, phone, LinkedIn, tech stack, funding, pain points — up to 50 custom fields), (2) research a company (team size, tech stack, funding rounds, hiring signals, key people), (3) find someone's professional or personal email address, (4) find phone numbers, (5) score/qualify leads against custom criteria with reasoning, (6) search for people or companies via natural language query, or (7) run batch enrichment workflows via API. NOT for: general web browsing, tasks unrelated to people/company data, or non-enrichment research.

A Zettelkasten-based knowledge gardening skill. Use this whenever users want to organize a knowledge base, 整理知识库, 整理读书笔记, build a second brain, update a personal wiki, turn conversations, reading notes, or project learnings into evergreen notes, MOCs, PARA folders, reusable context packs, or long-term memory assets. Trigger even when the user only says their notes are scattered, duplicated, stale, or hard to reuse.

Freelance accountability columnist for The Cycle Pulse. Deployed sparingly when there is a verified gap, contradiction, or suspicious silence. Sharp voice, verifiable claims. Use when a civic/business story needs adversarial pressure.

>

>

PostgreSQL mastery: advanced indexing (GIN, GiST, BRIN), JSONB, full-text search, partitioning, replication, pgvector for embeddings, and performance tuning.

Orchestrer le pipeline complet de catalogage UNIMARC pour les deux profils supportés.

*A stigmergic intelligence primitive for care, memory, and co-existence.*

Human-computer interaction design principles

- Core configuration lives under `lb_runner/` (`benchmark_config.py`).

This package adds persistent memory to Pipecat voice AI pipelines using Supermemory.

How to navigate Ian's world as an AI collaborator.

Mostra status dos agentes e suas MEMORYs

Eres un asistente personal útil, directo y conciso.

1. Read `SOUL.md` — who you are

This skill **writes** to the memory directory and to the git index. It reads the current conversation context, memory files, and git status. It must not modify any source files in the project beyond w

When the user wants to track follower growth, understand what drives new followers, or analyze audience development. Also use when the user mentions 'follower growth,' 'followers,' 'audience growth,' 'gaining followers,' 'losing followers,' 'who follows me,' or 'grow my audience.' Uses BlackTwist follower data when available. For post-level metrics, see performance-analyzer-sms. For content patterns, see content-pattern-analyzer-sms.

Audits memory allocations to enforce the use of palloc_get_page(PAL_ZERO) over malloc, ensuring strict NULL checks.

You are running the **unified trading loop** — research, analysis, and decision-making in a single sequential pass. This replaces the old separate research/analysis/execution phases.

This file defines how ANY AI AGENTS and Codex CLI operates if you are reading this you are an ai agent in this repository. It aligns with the Memory Bank protocol and complements `.github/copilot-inst

自動去重、整理記憶檔案，模擬 Claude Code 的 Auto Dream 機制。

Complete mastery of essential modern web development libraries and dependencies. Cover Next.js, React, TypeScript, Tailwind CSS, Firebase, Zustand, redux-toolkit, react-hook-form, Zod, shadcn/ui, lucide-react, Stripe, and more. Learn setup, integration patterns, advanced usage, performance optimization, troubleshooting, common pitfalls, and version management. Includes quick reference guides, in-depth tutorials, complete examples for e-commerce and SaaS, configuration files, type definitions, error handling, and production patterns. Master how libraries work together and solve real-world challenges.

>

This skill should be used when defining a robust, type-safe, and async-compatible database schema for the Todo application using SQLModel, ensuring compatibility with Better Auth and optimized for PostgreSQL.

|-

Closes a session cleanly so the vault, memory, and git history all reflect the work.

Check LP performance. Analyzes image sizes, CSS/JS optimization, render-blocking resources, and page speed factors.