Навыки: Продуктивность

Audits how model artifacts are accepted, validated, stored, selected, loaded, executed, monitored, and retired. Use when...

Use when the operator explicitly asks for native Codex model or reasoning-effort routing, including an active standing r...

Decide when to use cheaper, local, or frontier models and how to measure cost tradeoffs. Use for token limits, model rou...

当已经有观测与模型预测（或一份拟合输出）、要判断这个拟合信不信时使用。看残差结构、带不确定度的拟合优度、杠杆值与影响点、信息准则。残差里有结构，说明模型、测量过程或不确定度模型三者之一不完整：必须说出可能是哪一处、用什么检查分辨，而不是加参...

Explicit model-selection preflight only. Budget-minded advice for the whole submitted task; recommend available model/ef...

Explicit model-selection preflight only. Budget-minded advice for the current stage of a justified staged workflow; reco...

Explicit model-selection preflight only. Conservative advice for the whole submitted task; recommend available model/eff...

Explicit model-selection preflight only. Conservative advice for the current stage of a justified staged workflow; recom...

Qualify a Genesis routing model or compare a candidate against an incumbent using the isolated qualification runner, app...

4時間ごとに Moltbook フィードを取得し、投稿/コメント/upvote を実行する（Zvi パターン）

Onchain AI agent marketplace on Base — gigs, tasks, quotes, payments in ETH. Use when user mentions Moltlaunch, gigs, ta...

Maintain development momentum and prevent project stalls through progress tracking, blocker resolution, quick wins ident...

Choose a MonadVault model route and plan token budgets, spend limits, quota posture, retries, and escalation paths. Use...

Create, configure, refine, or audit a MonadVault Monad: its name, purpose, Soul, Spine, voice, boundaries, memory consen...

Research and synthesize documents, images, symbols, dreams, field notes, rituals, contemplative practices, and comparati...

Full Monday morning setup. Creates week folder, pulls carry-forward, and generates briefing in one pass. Use on Monday m...

Automate Monday.com workflows, board management, team collaboration, and cross-board integrations

Monetization strategy for iOS/macOS apps. Covers readiness assessment, pricing model selection, tier structuring, free t...

Agent pipeline - Run full Vibe Coding agent workflow (monggle)

Pipeline trace - Trace execution and debug agent workflow (monggle)

Manages MongoDB Atlas Stream Processing (ASP) workflows. Handles workspace provisioning, data source/sink connections, p...

Always-on contact freshness monitoring service. Runs on a schedule (via

Monitor episodic archiver health and run nightly analysis pipeline. Health dashboard, failure patterns, session aging al...

Use when running or reviewing a month-end close (bank reconciliations, control account reconciliations, accruals and pre...

Use when running, planning or speeding up a month-end (or quarter-end) close — building or reviewing the close checklist...

Monthly review and next-month planning for Obsidian monthly planning files and quarterly OKR notes. Analyze one month’s...

Compile a month-over-month retrospective from Agent Monitor data — sessions, cost, token volumes, completion rate, top p...

Generate a daily founder briefing that turns scattered context into clear execution priorities. Action-first format. Nev...

Daily briefing skill. Use when Codex should synthesize meetings, inbox items, tasks, and risks into a practical start-of...

Run a 15-question interview to capture your role, topics, sources, exclusions, and format preferences — then write a mas...

Full daily sales pipeline execution. Run at 9 AM via cron. Scans for signals, enriches company leads, auto-applies to gi...

Orchestrates a full morning sweep of pending items (email, tasks, Slack, WhatsApp, X). Use when the user asks for a swee...

Routes OpenMOSS/MOSS workflows for local LLM inference, model runtime checks, API or UI serving, and SFT data/fine-tunin...

Operate MotherDuck from a terminal with the MotherDuck CLI. Use when a coding agent or developer needs shell-based authe...

Plan and create original motion videos and motion graphics with OpenMotion. Use for “做一个 motion 视频”、动效视频、动画短片、先构思视频怎么呈现,...

Use when assessing readiness to change, planning behavioral interventions, or matching treatment approach to patient mot...

Support high-altitude and mountainous terrain operations including mobility, sustainment, and weather risk management. U...

ย้ายไฟล์และอัพเดท reference

Requires Python 3 with requests for the helper and a public coupon API (no account or API key); affiliate (CPS) claim li...

Automate Moxie tasks via Rube MCP (Composio). Always search tools first for current schemas.

Automate Moz tasks via Rube MCP (Composio). Always search tools first for current schemas.

Use when you have acquired EI or MS2 library files in MSP format (e.g., from NIST via Lib2NIST export, RIKEN, MoNA, SWGD...

research step of mspec workflow — investigate via subagent and produce research.md

昇腾AscendC算子异常检测工具（msSanitizer）。检测内存越界、内存泄漏、数据竞争、未初始化读取、同步异常等缺陷。触发关键词：mssanitizer、sanitizer、检测工具、内存检测、竞争检测、初始化检测、同步检测

Find the options you missed when stuck on a product or business problem. Takes what the user already tried and their lim...

Instrument multi-agent workflows, handoffs, and parent-child relationships

Enable Claude to orchestrate complex tasks by spawning and managing specialized sub-agents for parallel or sequential de...

Run a gated multi-agent coding workflow for development requests. Use when the user asks Codex to use multiple agents, a...