98 个 · 按相关度排序
Guides fuzz testing for Ruby libraries and gems with Ruzzy, using varied inputs to find failures. Covers pure Ruby and C extensions, including test harnesses, memory error detection, environment setup, and crash reproduction.
中文简介正在准备中。当前显示英语简介。
Set up Atheris to test Python code and C extensions with automatically varied inputs. It guides test harness creation, coverage tracking to explore more code, and AddressSanitizer setup for finding memory errors.
中文简介正在准备中。当前显示英语简介。
Diagnose slow loading, high memory use, and low frame rates in USD 3D scenes. Coordinate scene structure checks, validation, optimization, and before-and-after performance comparisons, then produce a report documenting findings and changes.
中文简介正在准备中。当前显示英语简介。
Audit and improve an entire agentic-development setup, including skills, context, memory, tools, models, permissions, hooks, workflow habits, and secrets hygiene. Invoke for setup reviews, workflow grading, Goblin Mode, or questions about what to improve. Supports shallow, deep, ultra, and yolo modes. Use domain-specific skills for a single model, report, or tenant.
中文简介正在准备中。当前显示原文说明。
Persistent compounding memory for AI agents. 5 default MCP tools: session_start, session_end, remember, recall, check. Full surface: 6 tools with --full (adds check_action); 13 tools with AR_EXTRAS=1 --full. Two-verb model: inhale (session_start) and exhale (session_end). Correction-first memory with decision trail tracking, watch_for warnings, palace rooms with salience scoring, cross-project insight matching, same-day journal merging, ambient recall hooks. Local markdown only. Zero cloud, zero telemetry, Obsidian-compatible. Optional Supabase backend: when configured via `ar setup supabase`, recall() uses pgvector cosine similarity on OpenAI/Voyage embeddings instead of keyword search — same API, semantic understanding. Gracefully degrades to local search if not configured.
中文简介正在准备中。当前显示原文说明。
Persistent compounding memory for AI agents. 5 default MCP tools: session_start, session_end, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (session_start) and exhale (session_end). Correction-first memory with decision trail tracking, watch_for warnings, palace rooms with salience scoring, cross-project insight matching, same-day journal merging, ambient recall hooks. Local markdown only. Zero cloud, zero telemetry, Obsidian-compatible. Optional Supabase backend: when configured via `ar setup supabase`, recall() uses pgvector cosine similarity on OpenAI/Voyage embeddings instead of keyword search — same API, semantic understanding. Gracefully degrades to local search if not configured.
中文简介正在准备中。当前显示原文说明。
Add persistent memory to Claude Code that survives across sessions. Use when: maintaining continuity across Claude Code sessions, building agents with persistent project memory, avoiding repeated context setup. Covers claude-mem (AI-compressed session logs) and Claude Subconscious (Letta-based background agent).
中文简介正在准备中。当前显示原文说明。
Set up Claude Tag for oncall for a team, from that team's standing (public) oncall / monitoring channel. Two things: it sets the channel up for monitoring, so alerts and incident posts here (from a person or another Slack bot) get triaged and acted on automatically, and it finds and sets up the connectors, plugins and skills Claude uses for oncall. A workspace can have several such channels; run once in each, by anyone, and every run adds or updates that team's section in the one oncall memory in shared workspace memory. Use on "set up oncall", "init oncall", "configure Claude for on-call". Surveys the agent connectors an admin configured for Claude, proves one with a read-only pull so access is verified, explores tools, Slack, repos and docs to learn how oncall works here, then recommends what's missing and walks the team through setup. The result goes into the indexed oncall memory every channel reuses; the other skills (incident init, investigation, handoff) pick it up automatically.
中文简介正在准备中。当前显示原文说明。
Deliberate system-improvement loop — audit your own Claude Code setup (rules / memory / skills / MCP / agents / registry), evaluate incoming tools via /vet, adopt the worthwhile ones with discipline (backup → verify), and record every decision. Use when bringing in a tool/idea/collection to improve the setup, or when doing a tooling-improvement pass. Triggers — "upgrade the workflow", "audit our setup", "let's improve the tooling", "evaluate this for us", when handed a post/repo/reel with a tool.
中文简介正在准备中。当前显示原文说明。
通过检查ECC的现有文件，查找适合任务的技能与命令，指导安装、重置和项目配置，并协助调查重复安装及安装位置，明确下一步操作。
利用优选与非优选回答对，对大语言模型进行无需独立参考模型的追加训练。提供不同模型的配置示例，并指导调整训练参数、应对训练不稳定和显存不足。
根据歌词及曲风、乐器标签在本地生成歌曲，指导安装、模型下载、输入整理和节省显存的设置，并协助将生成结果保存为MP3文件。
Customize what claude-mem remembers by defining note categories and reusable tags through a guided conversation. Install and activate the configuration, verify it appears in startup context, and optionally set up Telegram alerts for selected notes.
中文简介正在准备中。当前显示英语简介。
Explain tips shown in senpi or omo by checking the installed tip list, user settings, and implementation code. Learn what a feature actually does, why a tip appears, and which tips your setup can show.
中文简介正在准备中。当前显示英语简介。
Get started with omo through a guided feature tour and workflow introduction. Optional setup migration and past-session analysis connect its features to existing work habits, while memory tools record useful preferences for future sessions.
中文简介正在准备中。当前显示英语简介。
Generate images, video, and music through ComfyUI in OpenMontage. Helps adapt community workflows, select the final output, identify missing models, and choose workflows suited to available GPU memory while recording settings for reproducibility.
中文简介正在准备中。当前显示英语简介。
Set up and maintain MemPalace as a searchable store of project and conversation memories. Configure a private installation, a shared hub, or a hub client, connect agent tools, and audit how stored information is organized.
中文简介正在准备中。当前显示英语简介。
Consult bundled technical documentation to understand and integrate Hindsight, a memory system for AI agents. Find guidance on storing and retrieving memories, API calls, configuration, deployment, SDKs, troubleshooting, and performance.
中文简介正在准备中。当前显示英语简介。
Plan and configure large language model training with OpenRLHF to better match human preferences. Covers training method selection, distributed GPU setup, inference acceleration with vLLM, and troubleshooting memory or training stability issues.
中文简介正在准备中。当前显示英语简介。
Guide large language model training with OpenRLHF using human preference feedback. Covers training method selection, distributed GPU setup, reward model training, and memory tuning, with examples for PPO, GRPO, and DPO.
中文简介正在准备中。当前显示英语简介。
Adapt existing PyTorch training scripts to run across multiple GPUs or machines with Accelerate. This skill covers device setup, distributed training configuration, and mixed precision, which uses lower-precision numbers to reduce memory use.
中文简介正在准备中。当前显示英语简介。
Use when installing, repairing, reusing, inspecting, or verifying readiness of the native NVIDIA Video Codec SDK or PyNvVideoCodec on Jetson, including the one-frame encode/decode smoke test with official samples, and when interpreting what those readiness results, including CPU-buffer and device-memory sample modes, do and do not establish.
中文简介正在准备中。当前显示原文说明。
Use when a Unity 6.3 game is slow or stutters: low fps, frame spikes, hitches when entering areas or on first effects, GC spikes, too many draw calls or SetPass calls, CPU vs GPU bound questions, Profiler, Profile Analyzer, Memory Profiler, Frame Debugger or Project Auditor work, GPU Resident Drawer or SRP Batcher setup, LOD and Mesh LOD, shader warm-up and variants, memory or VRAM budgets, IL2CPP and build size, or proving a fix with numbers from a player.
中文简介正在准备中。当前显示原文说明。
First-time onboarding for new Agentara users. Use when user says "bootstrap", "/bootstrap", "get started", "first time setup", or when memory/USER.md and memory/SOUL.md are empty/missing. Inspired by the movie Her — warm, curious, subtly brilliant. The goal is to make the user feel understood within minutes and want to keep going.
中文简介正在准备中。当前显示原文说明。