682 skills · sorted by relevance
Manage YYLO Ledger tasks through its command-line interface while preserving lifecycle rules and change receipts. Create, search, and update tasks, inspect dependencies, and identify available work and an execution order that respects prerequisites.
Create and edit spreadsheet files, clean messy tables, and convert tabular formats. Add formulas, formatting, and charts while following existing template styles, then recalculate formulas and check for errors before delivering the spreadsheet.
Interpret AI-writing flags without treating them as proof of authorship. Separate tool results from editorial observations, consider plausible human explanations, and identify drafts, revision histories, or other process evidence needed for consequential academic, hiring, or publication decisions.
Review and structure Rust backend changes using hexagonal architecture, which separates business rules from external interfaces. Check dependency direction, place authorization policy in domain services, and keep database operations and external clients behind defined interfaces.
Build or correct CSV headers for bulk transaction uploads in TRES Finance. Check exact column names and order, including the optional Fiat Value column, to address errors caused by missing or incorrectly named headers.
Repair navigation between existing Obsidian project notes by improving meaningful links among papers, experiments, results, and writing. Keep references connected to the main note for each subject while avoiding unnecessary extra notes and excessive linking.
Turn reviewer comments into a structured response document. The skill classifies concerns, suggests whether to revise, defend, clarify, or experiment, and drafts evidence-based replies while checking completeness, professional tone, and respectful wording.
Edit English academic papers for international journal submission through three passes covering grammar, readability, and academic precision. Receive polished text and explanations of major changes while preserving the author's substantive arguments and conclusions.
Add a short status line to the end of agent responses so readers can see whether work is finished, a specific follow-up remains, or progress depends on their input.
Manage long-running or parallel agent work around five-hour and weekly usage limits. Check consumption between batches, pause new work at 95 percent, preserve a clear handoff, and check actual usage again before resuming.
Coordinate 15 agents implementing claude-flow v3 across security, core systems, integration, testing, performance, and release work. Provides role assignments, task dependencies, GitHub tracking examples, and a four-phase schedule spanning 14 weeks.
Turn explanations, comparisons, and procedures into a single HTML page with diagrams and tables. A bundled command-line tool handles layout and appearance from a Markdown draft, helping readers see relationships, follow processes, and compare options.
Evaluate code review feedback against the actual code, supported environments, and existing behavior. Clarify uncertain requests, respond with technical evidence, and implement valid changes one at a time with tests for each fix.
Inspect GitHub pull requests, issues, and automated workflow runs using the gh command-line tool. Check PR status, investigate failed jobs, and retrieve structured JSON or API data without opening a browser.
Search the web, images, news, and videos through a local SearXNG instance that combines results from multiple search engines. Filter by language or time range, and retrieve formatted results or JSON for further processing.
Create or refactor SwiftUI screens with practical patterns for tabs, navigation, sheets, layouts, and state ownership. It also guides asynchronous loading, previews, accessibility labels, and build checks while respecting the project's conventions and supported OS versions.
Get a second opinion from Google Gemini on Google Ads, SEO metadata, or code changes. Choose a pass/fail review, a challenge that probes weaknesses, or an open consultation on strategy and implementation.
Solve optimization problems with equality constraints, inequalities, or variable bounds. Guides method selection, symbolic equations, and optimality checks, with SciPy examples for finding numerical solutions that respect the stated constraints.
Investigate LazyCodex and Codex bugs using reproduction results and source code. Identify the responsible repository, then prepare or submit an English GitHub report with evidence, likely causes, fix guidance, and a verification plan.
Package project links, reports, demos, or Codex session summaries into a readable static HTML page. Remove sensitive information, upload the page or existing static files through PinMe, and return the resulting share URL.
Create, edit, analyze, and format Excel, CSV, and TSV files using Python. Preserves existing spreadsheet styles and formulas, checks references, and supports summaries, charts, and readable layouts for new workbooks.
Read, create, and edit .docx documents with python-docx, then render pages for visual inspection. Organize headings, tables, and lists, and check spacing, alignment, pagination, and readability before delivering the finished document.
Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after recipe-runner brings a deployment up (especially disagg/multi-node) to confirm the KV transport is correct; use troubleshoot for diagnosing already-failed pods.
The English summary is being prepared. Showing the original description.
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
The English summary is being prepared. Showing the original description.