Shared, manifest-driven skills & settings installer for Codex, Claude, DeepSeek, GitHub Copilot, OpenCode, Antigravity, Grok, Kimi Code, and (fake-root) OpenClaw — cross-platform (Linux/macOS/Windows), with cross-agent delegation, remote-bridge (Zulip/Telegram + OpenClaw /aas adapter), OpenGauss readiness, leak sanitization, and lifecycle/rollback.
Skill Claude CodeCodex
Use when an ask is underspecified, or you catch yourself inferring what the user wants, before any brief, spec, plan, or code. Elicits the real intent one question at a time, each with your best guess attached, until you can predict the user's answers, then restates a confirmed intent for explicit sign-off.
Skill Claude CodeCodex
Use when a research or engineering task needs automatic heavy-compute routing to free Kaggle Kernels through the local broker, with agent-driven push, poll, fetch, and a multi-run resume loop across concurrent kernels; free CPU (quota-free) and GPU under a self-imposed weekly GPU-hour cap.
Skill Claude CodeCodex
Use when preparing optional LeanExplore MCP setup for Lean declaration search and formalization support.
Skill Claude CodeCodex
Use when deciding whether a research claim should enter the optional Lean formalization lane.
Skill Claude CodeCodex
Use when any Lean formalization task starts (reuse Mathlib and the personal research library before proving anything new) and when it ends (gate finished results into the library and flag mathlib-PR candidates, always asking the user first). Also scaffolds and publishes paper artifacts from the personal template.
Skill Claude CodeCodex
Use when checking whether a Lean artifact can safely support a research claim.
Skill Claude CodeCodex
Use when the user wants animated math (handwritten-style equation writing, equation morphing between derivation steps, and emphasis) rendered with Manim, as a silent video clip that can stand alone or be spliced into a slides-to-video deck. The free, optional companion to slides-to-video for math lectures.
Skill Claude CodeCodex
Use when a research or engineering task needs automatic heavy-compute routing through the unified local broker, including Modal-backed remote CPU, high-memory CPU, or GPU execution.
Skill Claude CodeCodex
Use when choosing an appropriate model, reasoning level, and role for subagents or multi-agent research work.
Skill Claude CodeCodex
Use as a metadata and discovery fallback for papers, preprints, citations, DOIs, PMIDs, and open-access signals after local library routing is exhausted or when external paper discovery is explicitly needed.
Skill Claude CodeCodex
Use for review-only requests for papers or books when the user did not explicitly ask for annotation. Handles the normal single-agent review flow.
Skill Claude CodeCodex
Use when the user mentions OpenProse or prose workflows, wants explicit multi-agent research and synthesis, or wants a reusable orchestration pattern. In Codex, emulate OpenClaw OpenProse using spawnagent, structured decomposition, and workspace artifacts.
Skill Claude Code
Cross-target remote control via Zulip (default control) and optional Telegram mobile notify, with mailbox approvals/instructions for autonomous research loops. Not for OpenClaw.
Skill Claude CodeCodex
Use when starting a nontrivial research task to frame scope, success criteria, evidence plan, and the right downstream workflow before expensive browsing or multi-agent work begins.
Skill Claude CodeCodex
Use when the user wants a local research digest from tracked topics or wants to manage tracked research topics.
Skill Claude CodeCodex
Use when a research draft or report exists and needs a pre-final review for unsupported claims, ambiguity, scope drift, or missing evidence before delivery.
Skill Claude CodeCodex
Use immediately before calling a research answer done, final, or complete to verify evidence coverage, dates, remaining gaps, and delivery readiness.
Skill Claude CodeCodex
Use when the user wants RSS-based research/news digests, feed management, or feed health checks.
Skill Claude CodeCodex
Use when the user needs SageMath for graph theory, combinatorics, algebra, spectral computations, or mathematical verification beyond what local Python tools can do.
Skill Claude CodeCodex
Use when a task fails, a user corrects the assistant, a capability is missing, or a recurring better pattern should be logged and considered for canonical ai-agents-skills integration.
Skill Claude Code
Send email over SMTP using only the Python standard library, with plain-text and HTML bodies, file attachments, cc/bcc, reply-to, a dry-run preview, connection verification, and redacted config inspection.
Skill Claude CodeCodex
Use when the user asks about earlier conversations, prior outputs, historical context, or past work that may live in Codex memories, Codex session logs, or optional legacy OpenClaw logs.
Skill Claude CodeCodex
Use when the user wants to turn prepared slides (PNG, PDF, or PPTX) into a narrated, captioned video in a chosen language and presenter role, using only free tools. A three-phase human-in-the-loop flow (analyze, draft transcript, render) gates rendering behind an explicit transcript approval.
Skill Claude CodeCodex
Use before a version- or spec-sensitive decision — framework or library code, a CLI flag, a config schema field, or a named standard/edition — when correctness depends on the exact version. Detect the version, ground the decision in the authoritative source, and cite it; flag the assumption when no source is available.
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: