138 skills · sorted by relevance
Operational guide for enabling hierarchical context parallelism in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.
The English summary is being prepared. Showing the original description.
Queue processing with fresh context per phase. Processes N tasks from the queue, spawning isolated subagents to prevent context contamination. Supports serial, parallel, batch filter, and dry run modes. Triggers on "/ralph", "/ralph N", "process queue", "run pipeline tasks".
The English summary is being prepared. Showing the original description.
Parallel multi-AI cross-validation research workflow (大版本). Dispatch N internal sub-agents + grok + gemini in parallel, automatically cross-validate findings, tier by confidence (strong consensus / partial / conflict / insufficient), generate tiered action items with arbitration. Use when user says "多 AI 调研", "交叉验证", "独立共识", "三脑调研", "multi-ai research", "parallel research", "cross-validate", or needs deep research that benefits from internal data + external 2026 consensus. NOT for quick factual Q&A, pure code reasoning, or tasks needing deep project context.
The English summary is being prepared. Showing the original description.
Chooses how to launch subagents from Claude Code (the Agent tool, a Workflow script, or headless claude -p children) and runs a headless fan-out from one background command. Use for "fan this out to 50 agents", "run these tasks in parallel", "launch subagents for each file", "should I spawn agents or write a workflow", "batch this through Haiku", "run claude -p in parallel", "dispatch a task list without the launches eating my context", or before any launch of more than a handful of subagents, where the launching itself is the cost. Covers the parent-turn cost of each mechanism, concurrency ceilings, what context and tools each child gets, effort control, output contracts, a cost ledger, and resume after interruption.
The English summary is being prepared. Showing the original description.
Skill-aware orchestration with context routing. Decomposes complex tasks into skill-typed subtasks, extracts targeted context subsets, executes subagents in parallel, and synthesizes results. Self-answers trivial lookups inline. No SDK dependency — uses raw HTTP via httpx. Use when tasks require multiple analytical perspectives, when context is large and subtasks only need portions, or when orchestrating-chat-agents spawns too many redundant subagents.
The English summary is being prepared. Showing the original description.
Use when the user wants a cited, structured read of local documents and project knowledge. Triggers on: "analyze these docs", "scan my project for context", "read the docs folder", "summarize what's in .beagle/concepts/", "extract context from docs/", "what's in this folder", "go read everything in X and tell me what's there". Also invoked programmatically by other beagle skills (prfaq-beagle Ignition, brainstorm-beagle reference points, strategy-interview context grounding) via the companion contract. Does NOT trigger on codebase lookups ("find this function", "search the repo"), web research (use web-research), LLM-as-judge evaluation (use llm-judge), or document editing (use humanize-beagle). Produces a written scan plan, parallel-subagent findings, and a cited synthesis report on disk — never inline prose, never unsourced claims.
The English summary is being prepared. Showing the original description.
Fornece treinamento distribuído de LLM nativo do PyTorch usando torchtitan com paralelismo 4D (FSDP2, TP, PP, CP). Use para fazer pré-treinamento de Llama 3.1, DeepSeek V3 ou modelos customizados em escala de 8 a 512+ GPUs com Float8, torch.compile e checkpoint distribuído.
The English summary is being prepared. Showing the original description.
Treina modelos de linguagem grandes (2B-462B de parâmetros) usando NVIDIA Megatron-Core com estratégias avançadas de paralelismo. Use ao treinar modelos >1B de parâmetros, precisar de máxima eficiência de GPU (47% MFU em H100), ou necessitar de paralelismo tensor/pipeline/sequência/contexto/expert. Framework pronto para produção usado em Nemotron, LLaMA, DeepSeek.
The English summary is being prepared. Showing the original description.
Bootstraps and runs a multi-agent development team with roles (dev, QA, DevOps), parallel work, and sprint plans that survive context resets. Use when kicking off a project with parallel AI agents, writing brainstorm prompts that produce real debate, planning sprints across chats, or recovering from context overflow mid-sprint.
The English summary is being prepared. Showing the original description.
Take implementation work through small, independently mergeable pull requests. Use a separate working directory for each PR, record manual QA evidence, write English review descriptions, resolve CI and review findings, then merge and clean up.
Guides the use of RWKV, a language model architecture that carries information forward in a compact state. Covers streaming text generation, long document processing, fine-tuning, and memory comparisons with Transformers.
Create a detailed chapter-by-chapter reading companion from an EPUB or PDF, connecting the book’s ideas to experiences and words saved in your personal knowledge store. The result highlights parallels without prescribing actions.
Routes GSD project management requests to the appropriate skill for configuration, workspace management, parallel work, pausing and resuming tasks, shipping completed work, and maintenance. It also covers inbox processing, project statistics, and command guidance.
Design workflows where specialized AI agents share recurring product management tasks. Define each agent’s role, required information, handoffs, and human review points, then create monitoring and evaluation plans for the overall workflow.
Add two to four introductory sentences to French and English whitepaper sections that start directly with tables, code, or lists, supplying practical context while keeping additions within defined line limits.
Correct and improve existing MSTest tests using APIs supported by the installed version. Refine assertions and failure messages, update data-driven tests, fix setup and cleanup, and address MSTest diagnostics while preserving the project's established conventions.
Convert NUnit 3 or 4 tests to MSTest v4 while keeping the existing target framework and test runner. The workflow translates assertions, test data, setup, and concurrency settings, then compares test counts and results.
Coordinate complex tasks across multiple agents through planning, execution, review, and revision. Agents save their work to local files and return status summaries, helping the main agent manage limited context while delivering the final result.
Ancient text restoration, attribution, dating, contextualization, and embedding via Aeneas (Latin) / Ithaca (Ancient Greek). Use when asked to "restore", "attribute", "date", "contextualize", "find parallels", "where was it written", "when was it written", "embed", or "analyze" an ancient text, inscription, or epigraphic document, or when the user mentions "Aeneas", or "Ithaca".
The English summary is being prepared. Showing the original description.
Create and manage git worktrees for parallel coding sessions with zero dead time. Use when blocked on tests, builds, wanting to work on multiple branches, context switching, or exploring multiple approaches simultaneously.
The English summary is being prepared. Showing the original description.
Use when working on multiple branches simultaneously, context switching without stashing, reviewing PRs while developing, testing in isolation, or comparing implementations across branches - provides git worktree commands and workflow patterns for parallel development with multiple working directories.
The English summary is being prepared. Showing the original description.
Run independent tasks concurrently across multiple files or targets using parallel sub-agents, with per-task model selection and LLM-as-a-judge verification. Use when tasks do not depend on each other and can run side by side.
The English summary is being prepared. Showing the original description.
Parallelize independent sub-jobs across fresh-context subagents instead of one bloated context. Use when a goal branches into many independent pieces.
The English summary is being prepared. Showing the original description.
Deploy a 2-layer parallel agent hierarchy for large, parallelizable work — big refactors, multi-file migrations, codebase-wide audits, bulk generation. A top-tier commander (Fable or Opus) orchestrates the swarms; the user picks a power level (Max Power / Heavy / Balanced / Economy) that sets the Opus/Sonnet/Haiku model mix per layer. Layer 1 is 3-50+ specialist agents, each with its own full context window; Layer 2 is 2+ sub-agents per member. Includes git safety, tiered sizing, a pre-deploy gate, phantom-completion checks, and multi-wave follow-up.
The English summary is being prepared. Showing the original description.