Tag
Explore by tags
Implements a Manus-style, file-backed planning workflow for AI agents using a three-file Markdown pattern (task_plan.md, findings.md, progress.md) to persist plans, findings and session logs—reducing context drift and enabling session recovery. Adds IDE/CLI hooks to re-read plans and verify completion.
Enables Pi to delegate tasks to focused child agents for code review, parallel audits, background jobs, and saved workflows. Supports foreground and background runs, session artifacts, worktree isolation, and built-in role agents to simplify orchestration.
Collection of modular 'skills' for Claude Code that automate content creation, image/slide/infographic generation, and platform publishing. Provider-agnostic image & AI backends, browser-based publishing adapters (X, WeChat, Weibo), and ClawHub publishing support. Requires Node.js and Claude Code.
Runs a background Letta agent that watches Claude Code sessions, reads the repo, preserves persistent memory, and injects whispered guidance before prompts — a plugin that adds cross-session context and optional tool access to Claude Code.
Provides a desktop app and an MCP endpoint to share AI skills, plugins, and connected services across agents and teams. Includes a local-first workspace for macOS/Windows/Linux, an MCP that integrates with Codex/Claude/Cursor, and an org control plane for publishing capabilities and managing access.
Provides a Claude Code plugin marketplace that supplies modular skills for security research, vulnerability detection, and audit workflows. Includes scanners, analysis skills, and developer tooling to embed LLM-assisted security checks into existing pipelines.
Connects AI assistants to Figma to extract design-system variables and components, create and edit frames, sync tokens bidirectionally to DTCG/CSS, and run WCAG scans. Read-only SSE, Cloud Mode, or NPX modes expose up to 106 tools.
A production-ready performance and tooling system for AI agent harnesses (Claude Code, Codex, Cursor): reusable agents/skills, hooks, memory and security tooling, installer and CI integrations.
Rewrites text to remove common signs of AI-generated writing and produce more natural human prose while preserving source facts. Delivered as a portable agent skill (plain SKILL.md) that runs across agent harnesses, with voice-calibration and a strict no‑fabrication rule.
A collection of role-specific plugins for Claude Cowork and Claude Code that encode skills, slash commands, and connectors so teams can turn process, tools, and company context into reusable, file-based components for knowledge-work workflows.
Provides a manifest-driven marketplace of official Cursor plugins for developer workflows and agent integrations. Each plugin lives in its own directory with a .cursor-plugin manifest; examples include agent skills, PR review canvases, SDK integrations, CI/team tooling, and orchestration for parallel agent work.
A concise, four‑principle guideline (as CLAUDE.md or a Claude Code plugin) that teaches LLMs to: state assumptions, prefer simple solutions, make surgical edits, and use testable success criteria — reducing overcomplication and unwanted changes when an LLM edits code.