跳到正文
cccskills

“fallback”的搜索结果

858 个 · 按相关度排序

Monitor machine learning training through WandB or training logs. Check for invalid numbers, worsening metrics, and stalled improvement, then report whether to continue, wait, or stop, preserving evidence and notes when stopping a run.

中文简介正在准备中。当前显示英语简介。

  • Monitoring loss and evaluation metrics during training
  • Investigating invalid numbers or diverging training
  • Assessing whether stalled training should continue
wanshuiyin/Auto-claude-code-research-in-sleep1.8万2026年10月20日 更新

alphaxiv

免费

Understand a single arXiv paper through an AlphaXiv summary, with full text and LaTeX source available when needed. Use it to identify key findings or ask specific questions about methods, experiments, and equations.

中文简介正在准备中。当前显示英语简介。

  • Get a quick overview of a paper from its URL
  • Check a paper's methods and experimental results
  • Ask about equations, proofs, or appendix details
wanshuiyin/Auto-claude-code-research-in-sleep1.8万2026年10月20日 更新

Draft patent claims from invention disclosures, prior art reports, and novelty assessments. Create broad independent claims and narrower dependent claims, check their support in the specification, and adapt separate claim sets for China, the United States, or Europe.

中文简介正在准备中。当前显示英语简介。

  • Drafting claims from an invention disclosure
  • Preparing separate claim sets for China, the US, and Europe
  • Adding narrower claims as fallback positions
wanshuiyin/Auto-claude-code-research-in-sleep1.8万2026年10月20日 更新

Style materials to match the OpenAI and Codex look using specified colors and fonts. Apply distinct formatting to headings, body text, code, and shapes, with fallback fonts when the preferred ones are unavailable.

中文简介正在准备中。当前显示英语简介。

  • Match material colors to the OpenAI and Codex look
  • Apply consistent fonts to headings and body text
  • Style code snippets with a monospace font
composio-community/awesome-codex-skills1.7万2026年7月26日 更新

Improve MNN's Vulkan backend by separating CPU scheduling bottlenecks from GPU computation costs. It guides operator and shader changes, new feature integration with compatibility fallbacks, and device testing to verify both correctness and end-to-end performance.

中文简介正在准备中。当前显示英语简介。

  • Finding CPU or GPU bottlenecks in Vulkan inference
  • Optimizing a specific operator or shader
  • Integrating cooperative matrix or subgroup features
alibaba/MNN1.6万2026年10月21日 更新

wiki-cli

免费

Check whether the official Obsidian command-line interface is ready, then use it to read and search a selected vault. Access supported backlinks and tags, with direct file reading as a fallback when the interface is unavailable.

中文简介正在准备中。当前显示英语简介。

  • Check whether the Obsidian CLI is usable
  • Read and search notes in a selected vault
  • Inspect supported backlinks and tags
AgriciDaniel/claude-obsidian1.6万2026年10月19日 更新

Creates original-language, translated, and bilingual SRT subtitle files from YouTube links, local videos, or other supported media. Uses platform captions when available, falls back to Whisper transcription, and provides subtitle output for short vertical videos.

中文简介正在准备中。当前显示英语简介。

  • Creating translated subtitles from a YouTube video
  • Transcribing a local video into subtitles
  • Producing bilingual SRT files
krillinai/OpenCreator1.4万2026年10月21日 更新

vendor-ai-review

Claude 官方免费

Review AI vendor contracts against your organization's policies. Identify gaps in data training rights, liability, model changes, and other terms, then prepare targeted contract edits and escalation options for issues outside agreed limits.

中文简介正在准备中。当前显示英语简介。

  • Reviewing an AI vendor's agreement before adoption
  • Checking whether inputs may be used for model training
  • Comparing contract terms with internal AI policies
anthropics/claude-for-legal97602026年10月21日 更新

vendor-agreement-review

Claude 官方免费

Review supplier agreements against your team's contract guidelines. Produce a memo explaining deviations, legal risks, business impact, specific wording changes, fallback positions, and required approvers, so a lawyer can decide how to proceed.

中文简介正在准备中。当前显示英语简介。

  • Reviewing supplier contracts against internal guidelines
  • Examining liability limits and their exceptions
  • Preparing specific wording changes for negotiation
anthropics/claude-for-legal97602026年10月21日 更新

customize

Claude 官方免费

Adjust an existing commercial contracts profile through a guided conversation. Update risk preferences, approvers, contract positions, or review formats one change at a time, with an explanation of how each update affects later work.

中文简介正在准备中。当前显示英语简介。

  • Changing liability cap fallback positions
  • Updating escalation contacts and approvers
  • Adjusting contract review formats
anthropics/claude-for-legal97602026年10月21日 更新

vercel-cli

OpenClaw 官方免费

Deploy and operate Vercel projects from the command line. Manage environment variables and domains, investigate build failures with logs and metrics, and handle platform settings while checking which project and team each operation targets.

中文简介正在准备中。当前显示英语简介。

  • Deploy preview and production versions
  • Manage environment variables, domains, and DNS
  • Investigate build failures and performance issues
openclaw/clawhub95242026年10月21日 更新

Create a single-column HTML email for a product launch, with a centered brand wordmark, hero image block, headline, copy, action button, specifications, and footer. Table-based layout and inline colors support compatibility with email clients.

中文简介正在准备中。当前显示英语简介。

  • Creating an email to announce a new product
  • Combining product specifications and an action button
  • Building a branded HTML newsletter
nexu-io/html-anything92022026年10月13日 更新

doc-parse

免费

Convert PDF, PowerPoint, Excel, and Word documents into structured Markdown for search and information extraction. Outputs include document metadata, a parsing confidence score, and the parser used, with fallback parsers available when earlier attempts fail.

中文简介正在准备中。当前显示英语简介。

  • Preparing documents for a searchable knowledge base
  • Structuring contract text for information extraction
  • Checking parsing confidence before manual review
anbeime/skill84722026年10月20日 更新

Plan and verify OpenRig startup, shutdown, and recovery. Compare reported status with actual running sessions, distinguish recovery outcomes, and define reboot tests that expose partial failures instead of hiding them behind a fresh launch.

中文简介正在准备中。当前显示英语简介。

  • Checking rig status after a host reboot
  • Designing recovery tests across runtimes
  • Investigating partially restored agent sessions
mvschwarz/openrig80462026年10月21日 更新

Review fiction for problems in structure, characters, prose, and consistency. Receive prioritized suggestions supported by passages from the text, using multiple reviewers when available or a single reviewer when the required setup is unavailable.

中文简介正在准备中。当前显示英语简介。

  • Reviewing a chapter before publication
  • Checking character motivations and setting consistency
  • Prioritizing revisions across several chapters
zenstory-ai/oh-story-claudecode78412026年10月18日 更新

Add thumbnails, colored badges, and data-driven styling to TypeScript lists, cards, and panels. Coordinate component logic with CSS, include fallbacks for missing data, and check how the updated display handles empty lists and long text.

中文简介正在准备中。当前显示英语简介。

  • Adding category or source badges to lists
  • Displaying thumbnails with placeholders for missing images
  • Changing colors and styles based on item data
HKUDS/OpenSpace77662026年8月13日 更新

Recover failed writes of large files or code containing special characters by placing content in a temporary Python script. Use raw strings or Base64 encoding, then check that the output file exists and has content.

中文简介正在准备中。当前显示英语简介。

  • Retrying writes that fail with unknown errors
  • Writing TypeScript or TSX containing template literals
  • Saving long text with Unicode or special characters
HKUDS/OpenSpace77662026年8月13日 更新

Save large text files when write_file or shell_agent encounters payload size limits. Create the parent directory first, write the content with Python through run_shell, and verify the resulting file.

中文简介正在准备中。当前显示英语简介。

  • Saving large source files after write errors
  • Writing files into new nested directories
  • Saving long JSON or Markdown content
HKUDS/OpenSpace77662026年8月13日 更新

Validate spreadsheet sources before running Python scripts to transform data, update multiple sheets, or apply formatting. Check required data first, try backup sources when needed, and report errors clearly if processing cannot proceed.

中文简介正在准备中。当前显示英语简介。

  • Checking required columns before processing Excel files
  • Transforming data and saving a new workbook
  • Updating formatting across multiple sheets
HKUDS/OpenSpace77662026年8月13日 更新

Recover failed Python tasks by saving the code as a script and running it through the system shell. The workflow covers spreadsheet generation, data processing, output verification, and troubleshooting missing packages, paths, or permissions.

中文简介正在准备中。当前显示英语简介。

  • Retry spreadsheet generation after a sandbox failure
  • Rerun data processing that timed out
  • Run scripts with system-installed Python libraries
HKUDS/OpenSpace77662026年8月13日 更新

Create documents when several research or execution tools fail. Delegate PDFs and complex layouts to shell_agent, a separate agent, or save Markdown directly, while distinguishing verified facts from general guidance and checking the output.

中文简介正在准备中。当前显示英语简介。

  • Drafting reports when several data retrieval tools fail
  • Delegating PDF templates and complex document layouts
  • Saving Markdown drafts with clear information limitations
HKUDS/OpenSpace77662026年8月13日 更新

Recover from failed automated file creation with an explicit shell workflow. The skill guides agents through checking folders, writing and running scripts, and inspecting output files to confirm that deliverables were actually created.

中文简介正在准备中。当前显示英语简介。

  • Recovering from repeated automated execution failures
  • Checking where output files were saved
  • Verifying generated PDF and Word files
HKUDS/OpenSpace77662026年8月13日 更新

Hand complex document generation or data processing to shell_agent when direct tools repeatedly fail. Define the required output, let the tool choose libraries and recover from errors, then verify the resulting files and content.

中文简介正在准备中。当前显示英语简介。

  • Resuming work after repeated tool failures
  • Delegating PDF or DOCX document generation
  • Handing off multi-step data processing
HKUDS/OpenSpace77662026年8月13日 更新

Create a structured Markdown report when multiple retrieval tools fail. Using available domain knowledge, the workflow separates verified facts from general guidance, marks missing data, and saves a document with limitations and practical next steps.

中文简介正在准备中。当前显示英语简介。

  • Drafting a report when search and file reading fail
  • Organizing general guidance into a structured document
  • Marking missing data for later completion
HKUDS/OpenSpace77662026年8月13日 更新