“code mode”的搜索结果

Set up and run HeartMuLa, the open-source music generation model family (Suno-like). Generates full songs from lyrics + tags with multilingual support.

中文简介正在准备中。当前显示原文说明。

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

中文简介正在准备中。当前显示原文说明。

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

中文简介正在准备中。当前显示原文说明。

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

中文简介正在准备中。当前显示原文说明。

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

中文简介正在准备中。当前显示原文说明。

Delegate coding tasks to Blackbox AI CLI agent. Multi-model agent with built-in judge that runs tasks through multiple LLMs and picks the best result. Requires the blackbox CLI and a Blackbox AI API key.

中文简介正在准备中。当前显示原文说明。

Build, test, and debug Hermes Agent RL environments for Atropos training. Covers the HermesAgentBaseEnv interface, reward functions, agent loop integration, evaluation with tools, wandb logging, and the three CLI modes (serve/process/evaluate). Use when creating, reviewing, or fixing RL environments in the hermes-agent repo.

中文简介正在准备中。当前显示原文说明。

Interact with DeerFlow AI agent platform via its HTTP API. Use this skill when the user wants to send messages or questions to DeerFlow for research/analysis, start a DeerFlow conversation thread, check DeerFlow status or health, list available models/skills/agents in DeerFlow, manage DeerFlow memory, upload files to DeerFlow threads, or delegate complex research tasks to DeerFlow. Also use when the user mentions deerflow, deer flow, or wants to run a deep research task that DeerFlow can handle.

中文简介正在准备中。当前显示原文说明。

Review or refactor an existing SKILL.md and its bundled resources — a smaller always-loaded core, conditional references, preserved behavior, lean/guided consumer profiles, and an A/B protocol to compare a candidate with the previous version. Use when a skill repeats itself, loads references on every run, triggers too broadly or misses legitimate requests, or needs its efficiency measured across models. Do NOT use for writing a new skill from scratch, refactoring application code, translating a skill verbatim, or performing the target skill's own task.

中文简介正在准备中。当前显示原文说明。

Use when the user wants to set up pwdev-feat in a project — 'inicializar o pwdev-feat', 'configurar o feat', 'init feat workspace' — choosing language, model profile and the optional audit trail, and creating the .planning/feat/ workspace. Do NOT use to analyze the codebase (feat-map), to write the project instructions file (feat-setup) or to create plans.

中文简介正在准备中。当前显示原文说明。

Use when the user wants a backend-only action plan — API endpoints, services, models, migrations, jobs and their tests — 'plano de backend para o endpoint X', 'plan the orders API'. Writes .planning/feat/features/{slug}/plan.md with the PWDEVIA method. Do NOT use for UI work (feat-frontend), full features spanning backend and UI (feat-feature), writing code (feat-exec) or quick 1–3 file fixes (feat-quick).

中文简介正在准备中。当前显示原文说明。

Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Proactively suggest when the user says a feature is ready for testing or asks "does this work?". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and a ship-readiness summary. For report-only mode, use /qa-only. (gstack) Voice triggers (speech-to-text aliases): "quality check", "test the app", "run QA".

中文简介正在准备中。当前显示原文说明。

Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use /plan-design-review. Use when asked to "audit the design", "visual QA", "check if it looks good", or "design polish". Proactively suggest when the user mentions visual inconsistencies or wants to polish the look of a live site. (gstack)

中文简介正在准备中。当前显示原文说明。

Static-to-EDS conversion that preserves the original design while making content authorable in Document Authoring. Two modes — page-level (overlay template with slot markers) and block-level (each section becomes an independent EDS block). Use when converting an AI-generated static HTML page (Stardust, Mobirise, Relume, Lovable, v0, Figma-derived hand-coded, etc.) into an Edge Delivery Services page. Triggers on "convert this page to EDS", "static-to-EDS overlay", "convert to EDS blocks", "next experimentation", "next run", "start run", or when a user provides a source URL and asks to make it editable in DA while keeping the original design intact. Do NOT use for canonical EDS block-rewrite migrations — that's the page-import skill.

中文简介正在准备中。当前显示原文说明。

Explain Ponytail's intended tradeoffs and measurement boundary. It does not estimate code, cost, or speed savings for the current repository. One-shot display, not a persistent mode. Trigger: ponytail-gain, "ponytail gain", "what does ponytail save", "show ponytail impact", or "ponytail scoreboard".

中文简介正在准备中。当前显示原文说明。

50 core Rust coding conventions covering naming, data types, strings, error handling, memory, concurrency, async, and modern crate recommendations. Use when reviewing code style or setting up project conventions.

中文简介正在准备中。当前显示原文说明。

Show ponytail's measured impact as a compact scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display, not a persistent mode, and not a per-repo number. Trigger: /ponytail-gain, "ponytail gain", "what does ponytail save", "show ponytail impact", "ponytail scoreboard".

中文简介正在准备中。当前显示原文说明。

Design, critique, set, create, activate, or run durable Codex goals for persistent or long-running objectives. Use when the user says "set a goal", "start a goal", "activate goal mode", "persistent goal", "long-running objective", "goal tree", or asks for a goal with verifiers, durable state, approval gates, completion proof, bounded delegation, or parent/child subagent goals.

中文简介正在准备中。当前显示原文说明。

Security checks for repository ingestion — scans repos for poisoned examples, dependency and supply-chain attacks, file/path traversal, format-based attacks, and enforces quarantine-before-commit. Load as part of the secure-* skill sequence whenever an agent reads, ingests, or learns from a GitHub repository. Also load when the user asks to check a repo for poisoned code, scan dependencies, verify supply chain safety, check for path traversal, scan repo files for attacks, or audit a repo before ingestion. Covers Issues 3, 4, 7, 8 from the agent security threat model: poisoned training data, dependency attacks, file/path attacks, and format-based attacks.

中文简介正在准备中。当前显示原文说明。

Build, update, and query a persistent project knowledge graph from skills, memory, docs, and code structure — stdlib Python only, no external tools. Dual-mode: skill-library (agent-loom) or application (any consumer repo). Load when the user asks for a knowledge graph, project map, skill relationships, query the graph, update the graph, or trace how components connect. Auto-runs on memory-handoff and project-setup bootstrap. Also triggers on "build the graph", "what connects to X", "map this project".

中文简介正在准备中。当前显示原文说明。

Normalizes and transforms RNA-seq count matrices for DE, visualization, clustering, and ML. Covers between-sample (TMM, TMMwsp, RLE/median-of-ratios, upper quartile), within-sample (TPM, FPKM/RPKM), variance-stabilizing (VST, rlog, log-CPM), GC-content correction (cqn, EDASeq), and single-cell (scran deconvolution, scanpy normalize_total). Encodes the composition-bias rationale, the "most genes not DE" assumption and its catastrophic failure modes (MYC amplification, apoptosis, viral host shutoff, prokaryotic stress), the "lengthScaledTPM is not TPM" naming trap, the "TPM is not for DE" rule, the blind=TRUE vs FALSE decision, ERCC spike-in normalization (SBN), and the single-cell zero-inflation breakdown of TMM/RLE. Use when choosing or applying normalization, debugging shifted-MA-plot diagnostics, handling zero-heavy single-cell data, or correcting GC bias.

中文简介正在准备中。当前显示原文说明。

Download genome assemblies, gene records, and ortholog data from NCBI using the modern Datasets v2 CLI (replaces assembly_summary.txt scraping and many EFetch workflows). Use when bulk-pulling genome assemblies, gene metadata across species, ortholog sets, or BLAST databases; when E-utilities are too slow for genome-scale work; or when automatic checksum verification, parallel download, and clean accession-driven retrieval are required. Encodes the JSON-lines output format, dataformat conversion, --dehydrated for cloud workflows, and when Datasets is/isn't the right tool.

中文简介正在准备中。当前显示原文说明。

Reconstruct ancestral states at internal phylogenetic nodes for sequences (PAML codeml, IQ-TREE --ancestral, GRASP, FastML), discrete traits (corHMM hidden-rate Markov, ape::ace, phytools::make.simmap stochastic mapping, BayesTraits), and continuous traits (phytools::fastAnc, geiger Brownian/OU, RPANDA). Use when designing constructs for ancestral protein resurrection, tracing trait evolution along a tree, performing stochastic character mapping, testing models of trait evolution (BM vs OU vs EB), inferring ancestral genome content via Dollo or DTL reconciliation, or quantifying ancestral-state uncertainty for downstream comparative analyses.

中文简介正在准备中。当前显示原文说明。

Threat-models protocols where authority, scarce resources, bonds, bounties, escrow, reputation, ordering, adjudication, or settlement create strategic incentives. Use to test attack utility, conservation, collusion, Sybil resistance, oracle capture, griefing, custody, liquidity, and residual risk. NOT for choosing payment or bond amounts without evidence, smart-contract code audit, legal or employment classification, DeFi trading, admitting workers, or settling claims.

中文简介正在准备中。当前显示原文说明。