Menu
Skills in this repository
SkillsMP has collected 1,033 skills from nexuslinkproductions/yuri-os. Open a skill to review its source and details.
nexuslinkproductions/yuri-osShowing 40 of 1,033 collected skills.
6-perspective adversarial review for high-stakes turns (architecture decisions, refactor planning, deployment review) — fans out architect, adversary (7-vector attack), maintainer, ops, product, and security perspectives in parallel, then consolidates. Use…
Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.
Recall and load the minimal canonical YURI skill set before every substantive YURI task, including implementation, analysis, research, planning, review, or verification. Do not use for trivial acknowledgements or status-only replies.
Turn a gun scan into a handoff-ready custom-gear.ch (René Spatz) holster split-mold, fully inside Blender via blender-mcp. Use when the owner says "make a mold from this scan", "cgs-mold", "turn <gun> scan into a mold", or provides a gun scan + active Blender…
Wave-2 security hardening for Nexus Link — runs the diagnostic tools, dispatches the MURE build, verifies the gates. Invoke for "wave 2", "security hardening", "nexus security", "pre-customer security", "rls audit", "audit chain verify", "antipattern scan".
Edit user-supplied prose to remove generic AI-writing patterns while preserving meaning, evidence, citations, and the writer's own voice. Use when the user asks to humanize, de-slop, polish, or voice-match prose.
Routes any Codex plugin, app connector, MCP tool, or plugin-provided skill through the YURI control plane before external reads, writes, browser actions, design, cloud, or GitHub tools are used. Use this before using any plugin capability inside…
Routes any Codex plugin, app connector, MCP tool, or plugin-provided skill through the YURI control plane before external reads, writes, browser actions, design, cloud, or GitHub tools are used. Use this before using any plugin capability inside…
Use when orchestrating any non-trivial multi-part task with subagents or model lanes — builds, audits, refactors, research sweeps, migrations — or when deciding which model tier handles a unit of work, how wide to fan out, or whether a heavy lane should…
Compatibility redirect — opus-fleet's orchestration doctrine has moved to fleet-economy. This skill is a tombstone: it carries no roster, dispatch template, or execution rule of its own. If invoked by an old trigger (/opus-fleet, opus orchestrates, spawn…
Use when a Claude lane needs help from Codex-developed plugins, plugin-provided skills, app connectors, MCP tools, browser/design/cloud/GitHub capabilities, or Codex-only workflow knowledge inside YURI-OS-MUSUBI.
Continuous background reflection engine that auto-triggers at checkpoints (task completion, context ≥60%, after errors) and runs a full 9-phase pipeline on manual /eot. Use when context is nearing capacity, after completing a major task, after errors, or when…
Run the pure-native MURE Sol MoE dispatch loop — plan/compile a manifest, admit only allowlisted OMP TaskTool spawns from the parent session, adapt pushed <task-result> completions (with transcript evidence), mirror the lifecycle into the shadow ledger, and…
MURE role × model variant matrix. One role, several tuned variants. Seeded from audit; MLP re-ranks. Cheap auto, heavy surfaced.
Tiered per-turn advisor for main session + WhatsApp. Cheap watcher + heavy escalation. Pure annotation, two surfaces.
Use when executing implementation plans with independent tasks in the current session
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Use when creating new skills, editing existing skills, or verifying skills work before deployment
When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform. Also use when the user mentions 'ad copy variations,' 'ad creative,' 'generate headlines,' 'RSA…
Use when verifying completed work, reviewing Claude or Codex output, wiring routes or adapters, relaunching lanes, committing, pushing, or avoiding first-run confidence.
MUST USE when user wants to 调研/research/搜索/search/查/找/look up anything on the internet — e.g. 全网调研 X / 帮我调研一下 X / 查一下 X / 搜搜 X / 看看大家怎么评价 X / X 上有什么讨论 / research this topic。 Also MUST USE when user mentions any platform or shares any URL/链接:…
Source text: Chinese
Orchestrate the 5 Anime DNA superpower skills: Infinity Guard (risk), Pattern Mirror (observation), Clone Orchestrator (parallelism), Domain Core (scope), Failure Evolution (learning). Use when you need to apply any combination of the 5 powers, or when a task…
Research Anthropic managed agents, sessions, events, tools, and skills, then distill the architecture into a portable agent brief. Use when you need a concise reference for agent/session/event design and long-running workflows.
Full Externalize Mode — on CRITICAL complexity tasks, externalizes cognitive state as a structured manifest (goal tree, risk map, evidence chain, failure modes, advisor consensus) before acting. Use when a task reaches CRITICAL complexity and needs full…
Background task router that spawns an agent with run_in_background: true. Use when typing '/bg <task>' or 'ctrl+b' to run a task in the background, or when mentioning 'background task', 'run in background', or 'defer this task'.
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes…
Turn a gun scan into a handoff-ready custom-gear.ch (René Spatz) holster split-mold, fully inside Blender via blender-mcp. Use when the owner says "make a mold from this scan", "cgs-mold", "turn <gun> scan into a mold", or provides a gun scan + active Blender…
Routes reusable Claude output (plans, ideas, findings, reviews, draft artifacts, diff proposals, questions, decisions, evidence packets) for Codex/main inspection. Use when Claude produces structured output that another lane must inspect, or when mentioning…
Turn any codebase into a beautiful, interactive single-page HTML course that teaches how the code works to non-technical people. Use this skill whenever someone wants to create an interactive course, tutorial, or educational walkthrough from a codebase or…
Construct the minimum-viable /compact hint using selective context compression (self-information scoring, perplexity-based pruning, attention-sink preservation). Use when about to call /compact, when context is nearing capacity, or when you need to preserve…
Fuse FTS5 + circuitry-graph + GitNexus + mechanism-spectrum into one confidence-graded retrieval front-door, faster than scanning each surface separately. Use this before broad exploration, grep, or any 'where is / what is this / find the code / what already…
Use when working from Chrome Design Assistant browser selections, pending visual design requests, or the local design-assistant MCP/HTTP bridge.
Turn a design system or design reference into a reusable pack and portable skill. Use when extracting visual language from docs, PDFs, or curated design sources into a build/style/audit workflow.
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Scoped execution environment, task policy, and exit criteria system for Yuri OS / Yuri. Inspired by Domain Expansion, translated into enterprise-safe system behavior. Use when the user says 'scope this task', 'set boundaries', 'define exit criteria', 'create…
Shintai council extraction template. Multi-site inventory pull + adversarial synthesis across diverse model lanes + Codex final arbiter commit. Reusable for any domain: design, research, competitive intel, API surface mapping. Trigger when you need a…
Real failure capture, root-cause analysis, regression design (outputs a runnable-test SPECIFICATION — does not write test files directly), and memory-driven improvement for Yuri OS / Yuri. Inspired by Zenkai / Saiyan Power, translated into enterprise-safe…
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Design skill for external, non-YURI, non-Kagami surfaces. Use when building client work, external products, public-facing sites, or any UI that is NOT YURI HUD or Kagami. Enforces high-end intentional design systems, prevents AI slop. For YURI/Kagami…
One-Shot Constraint Lock — user invokes with a constraint phrase; that constraint becomes absolutely inviolable for the session, visible in the brain block on every turn, not overridable by any advisor. Auto-expires at session end. Single active lock per…