2.7K skills · sorted by relevance
Hand off OpenRig work through persistent queue items that record the next owner, blockers, and closure reasons. The skill covers notifying recipients, escalating to a human, and keeping supporting evidence accessible across interruptions and missed messages.
Audit TypeScript projects for type-only imports, duplicate imports, missing base class inheritance, and incomplete public exports through index.ts files. Apply targeted fixes in a defined order and check compilation with tsc --noEmit.
Package a completed codebase or project directory into a ZIP deliverable. The skill adds a dedicated final step to check project files, create the archive, verify its existence, size, and contents, and explicitly report completion.
Add a complete dashboard panel in plain TypeScript, from server routes and data services to the visible component and registration. The workflow checks existing routing patterns and includes request failure handling, caching, and saved panel state.
Package a completed codebase or project directory as a ZIP archive in a separate final step. Verify that the archive exists, inspect its contents, and report the file location with a brief contents summary.
Track every required output in a visible checklist, update progress as each is completed, and review the original requirements before finishing. When one output is blocked, try alternatives and continue work on the remaining deliverables.
Define when a file creation task is complete: the deliverable is saved, contains the required content, and uses the correct format and location. Verify those conditions, then report completion without searching for an unnecessary submission tool.
Organize patient visit information into a complete SOAP note: reported symptoms, observed findings, clinical assessment, and care plan. Write all four sections into one file, check required content, and explicitly identify missing information.
Search human genes by name or keyword through Clinical Tables and get concise results with gene IDs, symbols, and descriptions. Select the fields to display and browse results in small pages for autocomplete-style lookup.
Send research questions to a running NVIDIA AI-Q Blueprint backend and receive reports with citations and source URLs preserved. Track longer research jobs, check their progress, and retrieve completed reports after a local interruption.
Query EpiGraphDB for trait classifications, related literature, genetic evidence, and gene–drug relationships. Get concise summaries with limited result counts, or save the complete response when you need the underlying data.
Search BioStudies and ArrayExpress by keywords or retrieve study information using an accession, a study’s registration identifier. Returns concise summaries and can save complete API responses to a file for further inspection.
Look up one genetic variant in BioBank Japan and get a concise summary of its associations with diseases and traits. Accepts rsIDs or genome coordinates, converts the query as needed, and can save complete results.
Model ongoing requests and multi-step agent work to estimate capacity, latency, and cost per completed task. Break execution into stages, account for queues and retries, and produce workload tables with average and peak resource budgets.
Create and manage tasks and task lists in 飞书. Assign people, set deadlines, find unfinished work, mark tasks complete or reopen them, and control list membership for collaboration within your access permissions.
Stop stuck Ouroboros executions or background jobs by ID, or cancel all running and paused executions in the current project. It reports whether cancellation is complete or has been requested, with guidance for checking the final status.
Extract a webpage’s content from its URL and convert it to Markdown, a plain-text format that preserves document structure. Use it to collect articles, blog posts, tutorials, or documentation for reading and further processing.
Collect sold listings from eight eBay marketplaces and organize displayed prices, shipping costs, conditions, sale dates, and seller details. Filter results to research resale values and compare prices across markets, with accepted offers flagged separately.
Develop a confirmed talk angle and title into a five-act script with speaker notes and timing. Receive a slide-by-slide specification and a completed prompt to paste into Kimi for presentation generation.
Read recent releases from CHANGELOG.md and display their version numbers, dates, and complete change sections. Choose how many entries to show, or view the full history while preserving the document’s formatting.
Create a structured Markdown handoff from the current conversation, covering scope, relevant files, discoveries, completed work, status, and next steps so another agent or a later session can resume the task.
Turn repository documentation and images into a complete landing page with features, setup instructions, and FAQs. Generate static HTML, CSS, and JavaScript files, plus a GitHub Actions workflow for publishing on GitHub Pages.
Follow a structured Claude Code curriculum with tracks for different goals. Record concrete evidence from project exercises, unlock modules when prerequisites are complete, and check scheduled reviews while keeping progress data inside the current project.
Guide a development task through requirements research, solution comparison, planning, implementation, optimization, and review. The workflow asks for approval at key stages and saves plans and completed task records in the project.