Route Markdown documents, evidence-backed project facts, conversation history, personal memory, and reusable procedures without double-writing. Use when an Agent must search or write AFS documents, propose or retrieve governed facts, inspect evidence and Timeline, or choose the correct durable store.
Review code or a skill bundle for the patterns that leak credentials and for least-privilege violations. This is a reasoning skill: it sharpens the agent's eye, and it needs no capabilities of its own.
★not rated 0 3mo agoA✓ AI review0 tokens
originalApache-2.0
Orchestrate local ZCode, Kimi, Claude Code, Codex CLI, and Pi agents through Agent Gateway MCP. Use for low-cost routing, multi-agent comparison, failure escalation, visible terminal demos, safe worktree-based parallelism, or maintaining the gateway.
Retrieve, summarize, and cite current trending news and viral stories from India (in both Hindi and English) using the TrendKia connector tools (listrecentarticles, searcharticles, getarticle, listsitemapurls). Use this skill whenever the user asks about Indian or Hindi trending news, viral stories, "what's trending…
Universal Long-Term Memory & Cross-Agent Handoff Protocol for AI Coding Agents. Use to recall past architectural decisions, persist bug fix patterns, and create clean handoff snapshots between Antigravity, Cursor, and Claude Code.
Talk to your human over Beacon while you work. Send non-blocking progress updates (notify), ask a blocking question and wait for the answer (ask), set your status, or read messages the human sent you. Use when running a long task and you want to keep a human in the loop, or need a decision before an…
Call preflightchangeset before merge, deploy, publish, or tool registration when a contract artifact changed (OpenAPI/Swagger, GraphQL, gRPC/protobuf, AsyncAPI, MCP manifest, or agent tool schemas). Send the complete base-to-head change set. Branch on executionaction only. If you already hold a chain receipt and only…
Control the BrowserOS agentic browser (open-source Chromium fork) from a coding agent via its built-in MCP server. Use when the user asks to browse, click, fill forms, scrape/extract data, take screenshots, manage tabs/bookmarks/history, automate a website, do research + write files (Cowork), schedule a recurring…
Coordinate with other AI agents over plain HTTP GETs — shared rooms, durable notes, long-polling. No POST, no sockets, no client libraries, no account; a fetch tool is enough, and an MCP server fronts the same surface. Use when you need to leave a message for another agent, wait for one, or persist state across your…
Top-level Linux computer-use skill with a bundled standalone runtime that bootstraps itself without any local Claude installation, private native modules, or extracted app assets.
Run the shared agent room. Use when the user says "recruit", addresses someone with "@name", asks to "ask the team", wants a "second opinion", says "have them discuss" / "let the team debate" / "thrash this out", asks you to "hire"/"find me a"/"recruit the best" model or role for a job, wants to see or edit a…
Generate images and video using a Google AI Pro subscription via Google Flow (labs.google/flow), driven by browser automation (the google-flow MCP server), to avoid paying per-credit services for what Google already covers. Use when the user asks to generate an image or video and no specific other service is named.…
Condense a document into a short, faithful summary using deterministic extractive logic. Use when a user provides a block of text and asks for a brief summary, the gist, a TL;DR, or a one-line version.
An MCP server that gives AI agents access to a trusted, sanitized library of agent war stories: hard lessons from real sessions, scrubbed clean before they leave the source.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…
Use Fix Memory as cross-window Agent Operating Context and as a verified-fix library. At task start assemble a small Core Context; for real code errors and repeated environment/tool failures use the deeper retrieval gate and fix workflow.
Working inside the exocortex vault (/git/exocortex) — garden passes, writing or editing vault notes, checkpointing decisions. Load whenever touching vault/ markdown; encodes the golden rules, note shape, the gardening routine, and pointers to the standing case law so rulings aren't re-derived.
Run the weekly review of the big-brain second brain: triage the inbox, walk active projects, reschedule or drop overdue tasks, check vault health, and write a review summary. Use when the user types /weekly, or asks for a "weekly review", "review my projects", "clean up my brain", "triage my inbox".
Publish posts on Threads (threads.com) for the user. Use whenever the user wants to write, draft, or publish a Threads post or thread, with or without an attached image, including "post this", "write a post using this image", or a pasted block of raw post text.
Use when Claude Science must obtain an independent OpenAI Codex review, second opinion, reproducibility check, statistical or figure audit, debugging handoff, or delegated implementation.
★not rated 0 2mo agoA43 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: