「orchestrator」の検索結果

Step 2 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the visualization plan from outline.json — render plots and conceptual diagrams from experimental_log.md and idea.md, optionally refine via VLM critique loop, and produce context-aware captions. Runs in parallel with the literature-review-agent. TRIGGER when the orchestrator delegates Step 2 or when the user asks to "generate the figures for my paper" or "render the plots from this experiment log".

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。

Step 3 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the literature search strategy from outline.json — discover candidate papers via web search, verify them through Semantic Scholar (Levenshtein > 70 fuzzy title match, temporal cutoff, dedup by paperId), build a BibTeX file, and draft Introduction + Related Work using ≥90% of the verified pool. Runs in parallel with the plotting-agent. TRIGGER when the orchestrator delegates Step 3 or when the user asks to "find citations for my paper", "draft the related work", or "build the bibliography".

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。

Step 1 of the PaperOrchestra pipeline (arXiv:2604.05018). Convert (idea.md, experimental_log.md, template.tex, conference_guidelines.md) into a strict JSON outline containing a plotting plan, literature search plan (Intro + Related Work), and section-level writing plan with citation hints. TRIGGER when the orchestrator delegates Step 1 or when the user asks to "outline a paper from raw materials" or "generate the paper 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。

Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). Iteratively refine drafts/paper.tex by simulating peer review and applying targeted revisions, with strict accept/revert halt rules. Maintains a worklog and snapshots each iteration so revert is real, not symbolic. TRIGGER when the orchestrator delegates Step 5 or when the user asks to "refine the draft", "iterate on the paper", or "run peer review on this paper".

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。

Used when the user asks to "create slides", "make a presentation", "build a deck", "design slides", "generate a pitch deck", "create a conference talk", "make a keynote", "presentation design", "slide layout", "slide template", "presentation structure", or mentions slides, presentations, decks, or talks in any context. Also triggers when the user wants to plan the content and visual direction of a presentation before generating it. This is the entry-point orchestrator that drives the full slide creation workflow across both HTML and PPTX formats. Examples: "I need to create slides for my conference talk about AI adoption", "can you turn this markdown into a presentation?", "I have a product demo tomorrow and need visual materials", "convert my existing PowerPoint to interactive HTML slides".

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 to spawn specialized OpenAI Codex CLI subagents for code review, debugging, architecture analysis, security audits, refactoring, documentation, comparative evidence adjudication, and autonomous /goal runs. It adds each persona through process-local developer instructions while preserving the project's AGENTS.md chain, including during parallel launches. Supports GPT-6-Astra across low, medium, high, xhigh, max, and ultra reasoning with default or priority service tiers, plus GPT-5.6 and GPT-5.5 models. Triggers on 'delegate to Codex', 'Codex Astra', 'Astra subagent', 'Codex subagent', 'code review agent', 'security audit', 'refactor with Codex', 'goal run', 'autonomous goal', 'have Codex weigh this'.

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 creating, auditing, or maintaining AGENTS.md files and Codex CLI configuration for any project—including initializing AGENTS.md for cross-agent compatibility (Codex, Cursor, Copilot, Devin, Jules, Amp, Gemini CLI), generating config.toml or .rules files, scaffolding .agents/skills/, converting CLAUDE.md to AGENTS.md, or auditing existing agent configs for bloat and staleness. Complementary to codex-orchestrator (which executes subagents; this skill creates the config files they consume).

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。

Coordinate SEO, LLM-readable site architecture, UX, content, monitoring, security, and external authority work as a task-plan-driven sequence. Use this skill when the user asks to plan, execute, validate, or route multi-skill website growth work; asks what to do next across semantic core, URL structure, internal linking, schema, llms.txt, UX journeys, analytics, citation monitoring, or white-hat link placement; or wants a central architect that preserves evidence, alarms, handoffs, and tests.

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。

Selects the active profile from triggering context. Evaluates a rule set against inputs (current time, calendar state, geofence, manual command, custom signals) and returns the profile name that consuming Skills (handoff-trigger-check, critic-gate, future Skills) should apply. Configuration-driven; rule set lives in a router config file conforming to the included schema. Deterministic precedence — manual override beats calendar beats time-window beats default. Required default profile guarantees a routing decision always exists. Use when an orchestrator needs to pick a profile automatically rather than having the caller specify one, when wiring calendar/time/Telegram triggers to gate behavior, or when a Skill's behavior should change with availability mode. Trigger on: "what profile should I use," "route to a profile," "which mode am I in," "auto-select profile," "active mode," "current profile." Do NOT use to evaluate work readiness or review proposed changes. Always returns a profile name.

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。

Direct a claim-driven research experiment project from post-Idea intake through method realization, prioritized evidence collection, Human Gates, and Evidence Freeze. Use for scientific planning, state transitions, queues, budgets, or recovery; not for running code or independently auditing results.

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 2: Generate and discover tests, validate against real library. Only invoke when explicitly requested by the user or by the yoink orchestrator.

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 3: Dependency decomposition. Only invoke when explicitly requested by the user or by the yoink orchestrator.

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。

Scaffold project: clone repo, install real library. Only invoke when explicitly requested by the user or by the yoink orchestrator.

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。

Timebox and coordinate a live three-lane iOS launch sprint from audience idea to tested SwiftUI app, landing page, ASO copy, screenshots, promo video, and privacy report. Use for a 50-minute talk, demo rehearsal, fallback drill, or any request to finish a tiny local iOS product under a hard deadline.

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。

Plan Odylith delegation ownership, bounded fanout, and merge-safe orchestration.

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。

Fix intermittent `{:no_translation, :unicode, :latin1}` crashes in Elixir escript daemons that use length-prefixed framed IPC on stdin/stdout. Use when: (1) daemon worker crashes only on some input files, usually ones with non-ASCII bytes (kanji, cyrillic, emoji); (2) error surfaces as `Protocol error` from daemon's error branch or as garbled frame-length bytes seen by the orchestrator/client side; (3) standalone one-shot mode works fine on the same input but multi-request daemon mode fails; (4) `IO.binread(:stdio, N)` returns `{:error, {:no_translation, :unicode, :latin1}}` despite the "bin" prefix suggesting it should be encoding-agnostic. Root cause is the escript default `:standard_io` encoding — it's `:unicode`, and `IO.binread` still routes through the io_server, which translates bytes to codepoints and errors when raw binary frames contain invalid UTF-8 sequences.

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。

Recover from stale RFDB nodes that survive `commit_batch` cleanup despite having their `file` field listed in `changed_files`. Use when: (1) re-running an enricher/orchestrator step but old data with the same file field stays in the graph, (2) `commit_batch(changed_files=[X], ...)` reports success but a query later still returns nodes with `file = X`, (3) you re-pointed structural nodes (e.g., DIRECTORY/FILE) from a synthetic file path to real file paths and the old synthetic-path nodes won't go away, (4) graph-stream / find_by_type returns a mix of "stale" and "new" nodes for the same logical entity. Root cause: `handle_commit_batch` calls `engine.find_by_attr({file: X})` to enumerate nodes-to-delete, but that query path returns only a PARTIAL set after compaction (L1 segments and the file→nodes index can desync). Workaround: enumerate stale nodes via the TS rfdb client `queryNodes({file: X})` (different code path that finds all of them) and call `deleteNode(id)` per node, then re-commit the intended state. Related: rfdb-manifest-l1-carryforward (same L1 family).

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。

Speed up Rust development iteration when `cargo build --release` takes 10+ minutes even for one-line edits. Use when: (1) every release rebuild takes minutes despite tiny edits, (2) Cargo.toml has `lto = "fat"` and/or `codegen-units = 1` in `[profile.release]`, (3) you want a production- shaped build for testing without paying the LTO cost on every iteration, (4) you suspect cargo is re-linking the whole binary instead of doing incremental work, (5) developing rfdb/grafema-orchestrator/large Rust binaries where full LTO is enabled for shipped builds. Adds a `fast` profile that inherits release but disables LTO, raises codegen-units, enables incremental compilation — first build still slow because it populates a fresh `target/fast/` dep cache, but every subsequent rebuild drops from ~13 min to ~13 s (≈60×).

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。

Launches 5 parallel AI agents to produce a comprehensive restaurant audit with composite Restaurant Health Score (0-100), grade, and prioritized action 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。

End-to-end automated model quantization and accuracy tuning workflow. Use when user asks for automated model quantization and accuracy tuning, e.g. "自动量化", "量化调优", "一键量化", "精度调优", etc. 当用户给出多卡（≥2 卡）卡号时，量化阶段通过 EP 并行适配（msmodelslim-ep-parallel-adaptation）保证多卡 EP 并行，调优主流程仍在本 Skill。

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。

对 DiT（扩散/多模态生成）模型执行 W8A8 动态（data-free）或 W8A8 MXFP8（data-free）量化。覆盖 HunyuanVideo、Wan2.2-T2V/I2V/TI2V、FLUX.1-dev（已迁移）、SD3、Sana、HunyuanDiT、CogViewX 等。YAML apiversion 固定 multimodal_sd_modelslim_v1，统一 MultimodalPipelineInterface 重构路径（不再保留 LegacyMultimodalPipelineInterface）。模板与字段以 msmodelslim/model/hunyuan_video/model_adapter.py（唯一已迁移到重构路径且 lab_practice YAML 已 validated 的 DiT）为参考；其它 DiT 需按各自推理仓的 `parse_args` 调整字段集合。data-free 指不引入外部激活校准数据，spec.dataset（校准集短名，短名如 wan2_2_t2v；enable_dump: false 时不参与 dump）仍必填；精度调优通过下游经验库 L2 §7 + 直接调 `quantization-expert-experience-tuning-rules/scripts/apply_rollback.py`（整层回退）扩展 exclude 列表，闭环由 `quantization-accuracy-tuning-orchestrator` 调度。

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。

在实现适配器前对候选模型做分析。确定模型实现来源（transformers / 模型目录 / diffusers）、结构特征、内存约束下的逐层量化建议（可选）及 MoE 融合权重风险。适用于用户询问模型适配可行性或做适配前分析时使用。识别为 DiT 扩散模型时，索取推理仓路径后回传 `next_step: model-adapt`，由 orchestrator 委派 `msmodelslim-model-adapt`（DiT 扩展节承接）。

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。

Full Stock Analysis Orchestrator — launches 5 parallel subagents via delegate_task for comprehensive multi-dimensional stock analysis with composite Trade Score (0-100). Triggered by "trade analyze <TICKER>" or "analyze <TICKER> stock".

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。

Launches 5 parallel AI agents to produce a comprehensive recruiting and hiring readiness analysis with composite Hiring Readiness Score (0-100), grade, and prioritized action 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。