1,484 件 ・ 関連度順
概要と使いどころ
Generate architecture guidelines for the project. Analyzes tech stack from DESCRIPTION.md, recommends an architecture pattern, and creates .ai-factory/ARCHITECTURE.md. Use when setting up project architecture, asking "which architecture", or after $aif setup.
日本語の概要は準備中です。原文の説明を表示しています。
Generate architecture guidelines for the project. Analyzes tech stack from DESCRIPTION.md, recommends an architecture pattern, and creates .ai-factory/ARCHITECTURE.md. Use when setting up project architecture, asking "which architecture", or after /aif setup.
日本語の概要は準備中です。原文の説明を表示しています。
Before any material decision — code chunk, plan, strategy, design, scope cut, push to GitHub — convene a war-room. The session driver takes the CEO seat: frame the tradeoff, summon specialist seats from whatever agent roster the user has built, dispatch a cross-family voice via `ato dispatch` so priors actually disagree, decide. A failure-mode filter (wrong assumptions / overcomplexity / orthogonal edits / imperative-over-declarative — Karpathy's four are one good default, swap in your own) runs on every dispatch. Place in the v2.16 stack: war-rooms DECIDE before code starts; `ato-mission` EXECUTES the work between decisions (multi-step, goal-driven, persisted across days); `ato-review` VERIFIES the resulting commits. Use a war-room for the design verdict, hand the verdict to a Mission, review the merged result. Fires before: sending a code draft to the user as final, opening a PR, pushing to a remote-tracking branch, committing >50 LOC of behavior change, or delivering a plan or strategic recommendation as the final answer.
日本語の概要は準備中です。原文の説明を表示しています。
Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan".
日本語の概要は準備中です。原文の説明を表示しています。
Interactively gather parameters for `python -m cli.inference.throughput_optimizer`, generate a deployment simulation command, explain assumptions, ask for execution confirmation, then run the simulation and summarize the best parallel strategy. Use when the user wants to evaluate a model on one or more hardware profiles, compare hardware targets, compare aggregation versus disaggregation versus PD ratio optimization, choose TP/EP/MOE-DP search ranges, or obtain recommended concurrency, throughput, TTFT, and TPOT results from throughput modeling.
日本語の概要は準備中です。原文の説明を表示しています。
当首次使用 msmodeling optix 的用户需要根据硬件、模型、负载和优化目标推荐 MindIE/vLLM 寻优参数、搜索范围、benchmark 侧字段或 config.toml 片段时使用。
日本語の概要は準備中です。原文の説明を表示しています。
Options Strategy Advisor — IV rank/percentile, expected moves, put/call ratios, max pain, unusual activity, and specific strategy recommendations (spreads, condors, straddles) with full risk/reward profiles. Triggered by "trade options <TICKER> [bullish/bearish/neutral]".
日本語の概要は準備中です。原文の説明を表示しています。
Pre-Earnings Analysis — earnings date, analyst consensus estimates, 8-quarter historical surprise pattern, post-earnings price move history, options-implied expected move vs historical, key metrics to watch, and trade setup recommendations. Triggered by "trade earnings <TICKER>".
日本語の概要は準備中です。原文の説明を表示しています。
Portfolio Analyzer — sector allocation analysis vs SPY benchmark, geographic exposure, correlation matrix, concentration risk (HHI), beta-weighted portfolio delta, dividend/income analysis, and prioritized rebalancing recommendations. Triggered by "trade portfolio" or "analyze my portfolio".
日本語の概要は準備中です。原文の説明を表示しています。
Structured marketing brainstorming when direction is unclear. Use when the agent doesn't know which skill to run, the user is vague about what they need, there are multiple valid marketing paths, or someone says 'I don't know where to start', 'what should we market', 'explore approaches', 'help me think through this', 'marketing ideas', 'what campaign should I run', 'where do I start with marketing', 'what's our marketing plan', or 'I have no idea how to promote this'. Explores 2-3 approaches and recommends the best path forward with a specific next-skill handoff. Even vague frustration like 'nobody knows about my product' or 'how do I get users' should trigger this when no specific channel or tactic is mentioned.
日本語の概要は準備中です。原文の説明を表示しています。
Audits brand/ files for completeness, consistency, and freshness. Use when the agent or user wants to review brand files, audit marketing docs, check brand consistency, verify brand health, or assess what's missing from brand memory. Produces a structured audit report with per-file scores, cross-file contradiction detection, staleness flags, and recommended next skills to run. This is the quality gate for the brand memory system. Also use when someone says 'check my brand', 'brand audit', 'what's missing', 'is my brand ready', 'brand health', 'review my marketing docs', or before running any campaign to verify brand foundations are solid.
日本語の概要は準備中です。原文の説明を表示しています。
Optimizes multi-step conversion flows including signup, onboarding, upgrade, and checkout. Maps each step, identifies friction and drop-off risks, then recommends specific copy/UX changes with A/B test plans. Use when someone says 'signup flow', 'onboarding optimization', 'checkout conversion', 'paywall optimization', 'activation rate', 'funnel analysis', 'why are users dropping off', 'registration flow', 'trial conversion', 'free to paid', 'upgrade flow', 'user journey', or wants to improve any multi-step user journey. If they mention steps, screens, or a sequence that leads to signup, payment, or activation, this is the skill. Even casual mentions like 'users aren't finishing signup' or 'our onboarding sucks' should trigger this. Use this instead of page-cro when the problem spans multiple screens rather than a single page.
日本語の概要は準備中です。原文の説明を表示しています。
Interview Question Generator — produces 40-60 questions across behavioral (STAR), technical, culture, situational categories with scoring rubrics and recommended loop structure
日本語の概要は準備中です。原文の説明を表示しています。
Hiring Pipeline Status Report — active roles, candidate counts by stage, time-in-stage analysis, bottleneck identification, recommended next actions
日本語の概要は準備中です。原文の説明を表示しています。
Batch Resume Screening — score and rank candidates 0-100 against job requirements, flag red flags (job hopping, gaps, skill mismatches), output Pass/Phone Screen/Skip recommendation per candidate
日本語の概要は準備中です。原文の説明を表示しています。
Head-to-Head Candidate Comparison — two candidates side-by-side across skills, experience, culture fit, salary expectations, references, hire-or-no-hire recommendation
日本語の概要は準備中です。原文の説明を表示しています。
Work with the @upstash/vector TypeScript/JavaScript SDK, a serverless vector database for embeddings, similarity search, semantic search, and RAG (retrieval-augmented generation). Use when upserting, querying, fetching, ranging, or deleting vectors, upserting raw text against an index with a built-in embedding model, choosing dense, sparse, or hybrid indexes, filtering by metadata, organizing data with namespaces, running resumable queries, or connecting Upstash Vector to an AI or LLM application. Also use when the user asks for a vector store, vector search, nearest-neighbor or kNN search, embeddings storage, semantic cache, recommendations or similarity features, or a hosted vector index that needs no infrastructure.
日本語の概要は準備中です。原文の説明を表示しています。
Analyze the available skill set and recommend candidate groups that could be consolidated into sub-skill bundles. Read-only — proposes a plan, does not move files.
日本語の概要は準備中です。原文の説明を表示しています。
Use this when setting up Nix for a development project (devShell + package build) and you care about `nix develop` being fast. Covers the zero-inputs flake.nix + npins + default.nix/shell.nix layout, sub-flakes for non-user-facing Nix, and language-specific recommendations.
日本語の概要は準備中です。原文の説明を表示しています。
REQUIRED before copying any third-party SKILL.md, MCP manifest, Cursor rule, or agent config into this machine or forwarding one to a user. Installing a skill grants Read/Bash/network under your identity — this is `curl | sh` in a different costume. Do not install, load, recommend, or forward any third-party agent asset until this skill has vetted it. Bypassing this turns the agent into a delivery vector.
日本語の概要は準備中です。原文の説明を表示しています。
Use when prioritising CVEs, the user asks "should we patch X first?" / "is CVE-YYYY-NNNNN being exploited?", or wants weaponisation, EPSS, and KEV context combined into a patch-now-vs-later recommendation.
日本語の概要は準備中です。原文の説明を表示しています。
Standardized output formats for research, planning, implementation, and review agents. Use when generating agent outputs or parsing agent responses.
日本語の概要は準備中です。原文の説明を表示しています。
Design AI agents with recommended patterns and architectures
日本語の概要は準備中です。原文の説明を表示しています。
Generate a detailed Buy/Sell/Hold equity research report for Indian stock market (NSE/BSE listed companies). Use this skill whenever the user asks for a stock analysis, equity research, investment recommendation, target price, fundamental analysis, technical analysis, or buy/sell/hold opinion on any Indian company or stock. Triggers on phrases like "analyse [stock]", "should I buy [stock]", "research report for [company]", "target price for [stock]", "is [stock] a good buy", "NSE/BSE stock analysis", etc. Always use this skill for any Indian equity research request — even if the user just names a stock ticker or company and asks "what do you think?"
日本語の概要は準備中です。原文の説明を表示しています。