“continuation”的搜索结果

读取本地PDF、扫描图像和Office文档，提取可用于摘要与问答的内容。支持分段阅读长文档、搜索已索引资料，并通过页码或区域引用依据。

• 识别扫描PDF中的文字
• 总结Office文档并就内容提问
• 每次阅读长文档中的几页

Find candlestick and chart patterns in previously ingested market data. Classify detections by reversal or continuation, bullish or bearish direction, and reliability score, then rank and store them for later reference.

中文简介正在准备中。当前显示英语简介。

• Finding candlestick patterns for a symbol and period
• Reviewing patterns ranked by reliability
• Organizing bullish and bearish signals

Create a ready-to-paste prompt for another agent or a later session to continue development work. Ground the handoff in current repository evidence, distinguish verified results from hypotheses and blockers, and identify uncommitted files and next steps.

中文简介正在准备中。当前显示英语简介。

• Ending a session with unfinished development work
• Handing a branch over to another agent
• Preparing instructions for a later session

Organize multi-step research and project work in Continue using Markdown files for plans, findings, and progress. When invoked, the skill reads saved planning context to support resuming work and reviewing earlier decisions.

中文简介正在准备中。当前显示英语简介。

• Resuming interrupted work in Continue
• Recording findings during research
• Tracking project phases and decisions

Keep plans, research findings, and progress in Markdown files for multi-step work in Kiro. Read saved project records when resuming a task to recover goals, decisions, and recent actions.

中文简介正在准备中。当前显示英语简介。

• Organizing findings during extended research
• Tracking a refactor across multiple phases
• Resuming work after a long break

Keep plans, research findings, and progress in Markdown files for complex agent work. Separate task plans and automatic planning reminders help the agent recover saved context, track decisions, and identify the next action.

中文简介正在准备中。当前显示英语简介。

• Resuming long research tasks
• Tracking phases and the next action
• Separating plans for concurrent tasks

Organize multi-step research and project work with Markdown files for plans, findings, and progress. Gemini hooks, automatic actions at session events, surface planning context so the agent can resume from saved records.

中文简介正在准备中。当前显示英语简介。

• Resuming research after a break
• Tracking project phases and decisions
• Recording errors and test results

Write a game design document for one system, such as combat, crafting, or dialogue. Work through sections with specialist agent input, check dependencies against existing designs, and save approved sections with progress records for later continuation.

中文简介正在准备中。当前显示英语简介。

• Writing a combat or crafting system design
• Checking dependencies against existing game designs
• Developing specifications with specialist agent input

Design structured summaries for long agent sessions that preserve goals, file changes, decisions, and next actions. Choose compression methods and timing, then test whether the agent can continue accurately without repeatedly retrieving information it already processed.

中文简介正在准备中。当前显示英语简介。

• Summarize long coding sessions for continuation
• Preserve file changes and decision history
• Create durable summaries for task handoffs

Clean up hard-wrapped Markdown and .qmd files by joining mid-sentence line breaks and placing each sentence on its own line. Preserve headings, code blocks, lists, quotes, and YAML metadata while adjusting paragraph whitespace.

中文简介正在准备中。当前显示英语简介。

• Removing mid-sentence line breaks from a README
• Putting each sentence of a .qmd paper on its own line
• Reformatting text while preserving Markdown structure

Set up and inspect periodic prompts that continue a specific Codex thread after idle checks pass. It supports App-native automation and a headless fallback, with controls to inspect status and enable or disable scheduled prompts.

中文简介正在准备中。当前显示英语简介。

• Periodically continuing an idle Codex thread
• Keeping automated prompts visible in Codex App
• Inspecting thread and automation status

Investigate whether a complex function is analytic, meaning it has a local power series representation. The skill guides derivative checks, Cauchy–Riemann equations, power series and convergence radii, plus ways to explore extension beyond the original domain.

中文简介正在准备中。当前显示英语简介。

• Checking where a complex function is analytic
• Verifying the Cauchy–Riemann equations
• Finding a power series and its convergence radius

Seedance 2.0 video & image generation via LibTV Gateway - AI text-to-video, image-to-video, video continuation, style transfer, and text-to-image using Seedance 2.0 model. Also supports Kling 3.0, Wan 2.6, Midjourney, Seedream 5.0. Trigger phrases: seedance, generate video, make a video, generate image, make an image, draw, libtv, liblib.

中文简介正在准备中。当前显示原文说明。

Build, debug, or review Cloudflare Workers invoked by the Forward action in Gateway HTTP policies, including the GatewayMiddleware entrypoint, Gateway types, context, and continuation.

中文简介正在准备中。当前显示原文说明。

State capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.

中文简介正在准备中。当前显示原文说明。

Comprehensive manuscript review with three modes: single-pass (default), --adversarial critic-fixer loop, and --peer [journal] simulated peer-review pipeline (editor + 2 dispositioned referees + editorial decision, calibrated to a target journal). R&R continuation via --peer --r2/--r3; hostile-editor stress test via --peer --stress; reviewer-disposition variance reporting via --peer --variance N. Auto-invokes /review-r + /audit-reproducibility on referenced scripts unless --no-cross-artifact.

中文简介正在准备中。当前显示原文说明。

AI DevKit · Compact a historical AI coding session with Jev when context is long, work is handed off or resumed, or durable continuation facts and memory candidates need extraction.

中文简介正在准备中。当前显示原文说明。

Entry point for local AI conversation history across Claude Code, Codex and Kimi CLI: routes each request to the reader or continuation skill that owns it and keeps the cross-provider inventory. Use when the platform is unknown or plural ("what was I working on", "we discussed this once") and for any Kimi CLI history. When platform and action are already clear, load that skill directly.

中文简介正在准备中。当前显示原文说明。

Use when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state before completion.

中文简介正在准备中。当前显示原文说明。

Reapply and repair Windows Codex Desktop after Store upgrades, including custom provider models hidden by Statsig available_models filtering, the dependent blue-purple Power slider and its Ultra toggle, Fast Mode request/UI gates, locale i18n, plugin UI gates, Chrome/browser_use gates, Goal command gates, Windows Computer Use availability gates and plugin/runtime repair, phone remote-control pairing under third-party/API-key main app usage, Desktop dynamicTools/inputSchema thread-start schema drift, local conversation visibility recovery after model_provider switches, restored-conversation missing-cwd continuation repair, ASAR integrity repair, signing/installing patched MSIX packages, SDK cleanup, Fast Mode wire verification, local plugin marketplace registration, and optional custom model_instructions_file setup (the bundled system prompt, also called 听话水).

中文简介正在准备中。当前显示原文说明。

Release BaoCut Electron desktop apps through GitHub Actions tags by default; use local/manual packaging only when explicitly requested. Also handles App version bumps, release continuation and portable signing backups; excludes craft skills and legacy standalone CLI releases.

中文简介正在准备中。当前显示原文说明。

Extend / continue a video temporally with Pusa 2.2 in ComfyUI. Temporal flowmatching (the flowmatch_pusa scheduler + WanVideoAddPusaNoise) on the WanVideoWrapper stack with WAN 2.2 T2V A14B (HIGH/LOW) models and the Pusa V1 LoRAs, conditioning on the loaded clip via WanVideoEncode so the existing motion carries into the continuation. Covers the kijai wanvideo_2_2_14B_Pusa_extension graph, model/LoRA slots + downloads, noise/length/scheduler settings, chaining multiple extensions, VRAM tiers, gotchas, and the extend→upscale handoff.

中文简介正在准备中。当前显示原文说明。

Use when the user says m0 handoff, before I compact, end of session, save session state, resume where we left off, or continue in Cursor or Claude Code. Writes or reads a compact_checkpoint so a cold start becomes a continuation.

中文简介正在准备中。当前显示原文说明。

Swift concurrency patterns including Swift 6.2 approachable concurrency, structured concurrency, actors, continuations, and migration. Use when reviewing or building async code, fixing data race errors, or migrating to Swift 6.

中文简介正在准备中。当前显示原文说明。