集中版控 Claude Code 使用者層級設定(skills / hooks / settings.json / CLAUDE.md),以 symlink 連回家目錄 — 換機或重灌時 git clone + install.sh...
#ai-agents
2957 posts
Advisor-orchestrated build loop. Top model plans and reviews, cheaper models implement.
Agent-era skill suites for Claude Code: engineering lifecycle + distributed systems, gated by the checklist CLI
Stop trusting 'done'. Make AI coding agents prove their work — frozen specs, tamper-detected tests, an independent blind verifier, hard-bloc...
Claude-type skills for institutional equity research — 25 AI agent skills with SEC filings, XBRL financials, earnings calendars, DCF/comps...
Agent skill pack for using CheapTokens: discounted Venice AI credits, OpenAI-compatible API calls, and x402 purchase flows.
Skills published by 5dive — drop-in SKILL.md bundles for Claude Code, openclaw, hermes, and any harness that loads skills.sh-format prompts.
A complete, opinionated, fork-friendly operating system for an AI-instructed company. Three layers — markdown skills (patterns of thought fo...
Skill для AI-агентов (Claude Code, Codex, OpenClaw, Hermes): убирает 32 признака AI-генерации из русского текста - канцелярит, штампы ChatGP...
Decide once. Re-decide never. A Claude Code skill that evaluates skills before installing and persists every decision.
The creation pipeline for Claude Code products — research, create, validate, publish. 13 types, 20 quality patterns, zero coding required.
A collection of AI agent skills focused on medical imaging and healthcare workflows. Built for radiologists, healthcare IT professionals, an...