「nda」の検索結果

Reduza o tamanho de LLMs e acelere a inferência usando técnicas de pruning como Wanda e SparseGPT. Use para comprimir modelos sem retreinamento, alcançando 50% de esparsidade com perda mínima de acurácia, ou ativando inferência mais rápida em aceleradores de hardware. Cobre pruning não estruturado, pruning estruturado, esparsidade N:M, pruning por magnitude e métodos one-shot.

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。

Load this skill whenever the project contains dynamic content updates, status messages, alerts, notifications, loading indicators, or any use of aria-live, role="status", role="alert", or role="log". Under no circumstances add or modify live-region markup without applying these rules. Prioritize correct politeness levels and avoid redundant announcements. Never use a fixed-delay clear-and-reinsert workaround — no standard guarantees it works.

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。

日程待办摘要：编排 calendar +agenda 和 task +get-my-tasks，生成指定日期的日程与未完成任务摘要。适用于了解今天/明天/本周的安排。

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。

Phase 4 Turn 1 of disease-market-sizing-orchestration. Generates report HTML with mandatory citation anchors per fact claim. Reads contract + staging + sources/. Every drug/treatment/stat/recommendation MUST carry [pmid:.../guideline:.../nct:...] anchor that resolves to an actual file in sources/. NEVER hardcode drug names or numerical claims. Use AFTER evidence recall (phase 3), BEFORE content-verification-layer (Turn 2).

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。

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

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, audit, harden, review, or upgrade MCP servers and MCP Apps with revision-aware protocol profiles, explicit HTTP/deployment boundaries, capability-centered validation, bilingual reporting, and reproducible evidence. Use for MCP server architecture, JSON-RPC or Streamable HTTP bugs, security hardening, protocol-version migration, MCP Apps widget boundaries, review reconciliation, test planning, and public engineering evidence.

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。

This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Provides foundational understanding of context engineering for AI agent systems.

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。

Check any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks. Use this skill when: - Evaluating an agent system's security posture before production deployment - Running a compliance check against OWASP ASI 2026 standards - Mapping existing security controls to the 10 agentic risks - Generating a compliance report for security review or audit - Comparing agent framework security features against the standard - Any request like "is my agent OWASP compliant?", "check ASI compliance", or "agentic security audit"

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。

Validate Commodore MPS-801 serial dot matrix printer behavior in EMULATORS, including SerialPrinterMPS801 classes and their MatrixPrinterEmulation and SerialPrinterPeripheralSimulation hierarchy, IEC/KERNAL-trap printer routing, device numbers, secondary addresses, PETSCII/character sets, 6x7 glyphs, double width, graphics mode, reverse field, tab and dot positioning, line/page geometry, PostScript output, and fidelity boundaries. Use when Codex reviews or edits COMMODORE MPS801 printer code, generated printer output, PostScript printer templates, C64/VIC-20/C264 serial-printer behavior, or compares implementation against .codex/docs/MPS801.pdf and historical MPS-801 sources.

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。

Validate Commodore MPS-802 and 1526 serial dot matrix printer behavior in EMULATORS, including SerialPrinterMPS802 classes and their MatrixPrinterEmulation and SerialPrinterPeripheralSimulation hierarchy, IEC/KERNAL-trap printer routing, device numbers, secondary-address functions, PETSCII/character sets, 8x8 glyphs, enhanced width, reverse and paging modes, formatter strings, programmable characters, line/page geometry, PostScript output, and fidelity boundaries. Use when Codex reviews or edits COMMODORE MPS802 printer code, generated printer output, PostScript printer templates, C64/VIC-20/C264 serial-printer behavior, or compares implementation against .codex/docs/MPS802.pdf, the MPS-802 user guide, and 1526/MPS-802/4023 service information.

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。

Mathematical foundations, logical structures, and formal verification guidance. Trigger when: - Designing protocol contracts, formal specifications, verifying state spaces, or using proof assistants. - Tasks involve: TLA+, Alloy, Lean, Coq, model checkers, invariants, temporal logic. - Prompt contains keywords: formal verification, alloy, tla+, lean, coq, invariant, state machine, model checker, liveness, safety.

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。

Volatility-based decomposition review. Trigger when: - Evaluating module boundaries against axes of change and business volatility. - Prompt contains: /lowy, volatility, axis of change, design decomposition, boundary.

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。

SOP for the micro-execution C.O.R.E. phase. Trigger when: - Implementing plan steps, managing code changes at commit boundaries, and verifying incremental progress. - Navigating states: Absorb, Clarify, Plan, Execute. - Prompt contains: /core, core workflow, absorb, clarify, execution invariants, commit boundary, verify assertion.

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。

Observe the harness itself — (WS1) measure context budget as a deterministic, trendable inventory (tokens per CLAUDE.md / skill / agent, lexical redundancy, per-CI cold-write totals; committed history.jsonl), (WS2) reconstruct the real invocation trace (which skills/agents/tools fired and how they nested) from session transcripts, and (WS-A) roll the per-run CI traces up into a committed weekly usage record (per-skill invocation counts; usage.jsonl) — the usage side of the dead-weight join. Use for "context budget", "how big is CLAUDE.md / our skills", "is the harness bloating", "how do our agent loops actually run", "which skills actually get used", "trace this session", "loop station".

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。

Emit a blocking question the owner can read in ~10 seconds and answer in one reply — the scannable, recommendation-first handoff every agent posts when it hits a fork it can't own. Leads with the one decision + a recommendation, carries the 🤖 provenance header, doubles as the

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。

Bounded improvement loop: one artifact, fixed eval score, keep an edit only if strictly better. Use for AR_DESIGN/AR_FUNCTION/AR_ACCEPTANCE stages or standalone bounded iteration.

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。

FOUNDATIONAL SKILL - Analyze every prompt for underlying motivation using Golden Circle (WHY->HOW->WHAT). Runs BEFORE any other skill. No action without understanding WHY.

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。

Comprehensive code review for commits and pull requests. Covers security, TDD, code quality, and documentation standards.

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。

Roblox and Luau game code standards. Writes, reviews, and fixes Script, LocalScript, and ModuleScript code and game systems such as shops, DataStore saves, RemoteEvents, combat, NPCs, and UI. Use when a request involves Luau code or a Roblox Studio project, even when Roblox is never named, when a game bug is reported with no file named, and when the user asks to keep these standards active. Also covers Rojo, Argon, Azul, Script Sync, Studio MCP, and community libraries such as ProfileStore, Knit, Trove, and Fusion. Applies to requests written in any language. Not for plain Lua outside Roblox (Neovim, LOVE, Defold, other engines) or for game design with no Luau to write or review.

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。

プロンプト要望を対話でヒアリングして prompt-brief.json を生成するとき、target_skill と responsibility_id の確定または skill 非紐付け (standalone) の汎用プロンプト要望を構造化するときに使う。

Use to rank the in-flight foundation backlog by insight signal, GHI count and invariants.

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。

Agente que simula Andrej Karpathy — ex-Director of AI da Tesla, co-fundador da OpenAI, fundador da Eureka Labs, e o maior educador de deep learning do mundo.

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。

Detect unauthorized SaaS and cloud service usage (shadow IT) by analyzing proxy logs, DNS query logs, and netflow data using Python pandas for traffic pattern analysis and domain classification.

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。

Performs statistical analysis of Zeek conn.log connection intervals to detect C2 beaconing patterns. Uses the ZAT library to load Zeek logs into Pandas DataFrames, calculates inter-arrival time standard deviation, and flags periodic connections with low jitter. Use when hunting for command-and-control callbacks in network data.

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。