Results for “formulas”

Create a Chinese interview preparation guide for a focused machine learning or LLM topic, with formula derivations, PyTorch implementations, comparison tables, and 25 questions across three difficulty levels. The workflow reviews the content and renders it as HTML.

• Preparing for an interview on a specific machine learning topic
• Studying formula derivations alongside PyTorch implementations
• Organizing interview questions by difficulty

Clarify the next step in a mathematical research task by identifying what is blocking progress. Select one specialist skill for discovery, derivation, computation, proof, or formal verification, with required inputs and clear stopping conditions.

• Decide where to start with an open mathematical question
• Find the next step when papers, formulas, and code are mixed
• Choose between derivation, computation, proof, and formalization

Analyze waiting, rework, and handoff waste in business processes using the facts provided. It proposes concrete improvements and, when verification is needed, defines measurement formulas and the minimum records required to assess specific issues.

• Reviewing waiting and rework in an existing workflow
• Requesting a fixed number of concrete improvement suggestions
• Defining records to distinguish processing time from waiting

Calculate advertising costs, revenue relative to ad spend, break-even targets, and budget forecasts. The skill makes inputs and formulas explicit, checks inconsistent data, and compares base, downside, and upside scenarios when uncertainty affects the decision.

• Calculating advertising acquisition costs and returns
• Setting break-even targets for advertising
• Comparing budget and revenue forecasts across scenarios

Research employment questions about overtime, breaks, leave, worker classification, and final pay for a specific state or country. Receive an answer with cited legal sources, notes on recent changes, and issues requiring professional judgment.

• Checking overtime and break rules for a specific state
• Reviewing whether a role qualifies for an overtime exemption
• Checking final-pay deadlines and unused leave payouts

Create and edit Obsidian notes, visual canvases, and databases. This skill set handles links between notes, highlighted information blocks, note properties, and database views with filters and formulas, helping preserve the formats used by Obsidian.

• Creating linked notes with highlighted information blocks
• Mapping relationships between people or concepts
• Building a reading list with filters and sorting

Process Excel workbooks and generate PDF or Word documents by running Python scripts directly through run_shell. The skill covers multi-sheet edits, formatting, data transformations, document layout, and error handling for complex tasks that can exceed agent step limits.

• Transform data across multiple Excel sheets
• Apply spreadsheet formulas and formatting
• Generate PDF checklists and reports with tables

Process complex Excel files by running Python scripts directly through run_shell. Use pandas for data transformations and openpyxl for workbook editing, including multiple sheets, formulas, and formatting, with explicit saving and error reporting.

• Processing multiple Excel sheets in one script
• Calculating new columns from spreadsheet data
• Formatting report headers and cells

Find input files in confirmed workspace folders, save outputs to explicit locations, and check the results against task requirements. Useful in restricted execution environments where familiar folders may be missing or inaccessible.

• Finding input files in an unfamiliar workspace
• Checking generated spreadsheet sheets and formulas
• Validating CSV or JSON outputs before delivery

Create and process Excel files, PDF checklists, and structured reports by running Python scripts directly. The skill covers multiple sheets, formulas, formatting, data transformations, and error handling for document workflows with several steps.

• Process and format multiple Excel sheets
• Create PDF checklists
• Turn sales summaries into PDF reports

Gather web information and turn it into an Excel workbook with explicit checks. Handles search failures through delegated research, records sources and missing data, and verifies the saved workbook against requested requirements.

• Compiling competitor prices into a verified Excel workbook
• Organizing market data with sources and collection times
• Continuing research after repeated search failures

Process Excel workbooks by saving Python scripts to files and running them through the shell. Covers multiple sheets, data transformations, formulas, formatting, and error reporting for complex spreadsheet tasks.

• Transform revenue data and save a processed Excel workbook
• Apply calculations across multiple worksheets
• Format report headers with colors and alignment

Recover from failed Excel creation or editing by switching from execute_code_sandbox to shell_agent. It guides clear task descriptions so the agent can install missing libraries, run code, retry errors, and confirm file creation.

• Continuing Excel creation after a sandbox import error
• Creating a sales report with formulas and sample data
• Building multiple sheets with conditional formatting

Audit existing public equity investment models and spreadsheets for formula errors, source support, assumptions, and scenario quality. Receive a readiness verdict, an issue log, and prioritized fixes showing whether the model supports its intended decision.

• Check formulas and controls in an existing investment workbook
• Trace important assumptions to supporting sources
• Review valuation scenarios and downside risks

Retrieve focused information from PubChem, including molecular formulas, molecular weights, compound descriptions, assay summaries, and substance metadata. Get concise Markdown summaries, with the option to save the full response for further use.

• Looking up a compound's molecular formula and weight
• Getting a short description from a compound ID
• Checking an assay summary

Write and troubleshoot n8n expressions, the formulas that pass and transform data between workflow steps. Correct field references, read webhook inputs, format dates and text, and query nested JSON while checking for silently missing results.

• Include webhook form data in Slack messages
• Fix expressions that return null or literal text
• Extract and total values from nested JSON

Turn validated vulnerabilities into clear bug bounty reports for HackerOne, Bugcrowd, Intigriti, or Immunefi. Platform templates help organize demonstrated impact, reproducible steps, supporting evidence, severity reasoning, and concrete fixes in language reviewers can follow.

• Draft a report using a platform-specific template
• Write clear titles and impact summaries
• Organize reproduction steps and supporting evidence

Turn papers and thesis materials into Chinese-first Word reports and PowerPoint presentations. Create editable files, preserve source evidence, match supplied templates, add speaker notes, and check layouts for overflow, overlap, and readability.

• Turn a paper into a Chinese reading report
• Prepare slides for a lab meeting or thesis defense
• Adapt research content to a supplied slide template

Develop and check research code in MATLAB/Octave or Python for signal processing, image analysis, statistics, and simulations. This skill supports reproducible workflows, checks units and assumptions, and prepares figures for papers and presentations.

• Debugging MATLAB signal-processing scripts
• Analyzing sensor time series in Python
• Checking units and assumptions in optical simulations

Create a complete email sequence from the target audience, offer, buying concerns, and brand voice. Get subject line options, preview text, full messages, calls to action, and a timing plan that keeps the tone consistent.

• Writing a welcome email sequence after signup
• Creating follow-up emails that address buying concerns
• Planning a promotional email sequence for an offer

Plan weekly LinkedIn content, draft posts and replies, review wording, and publish after approval. This collection of twelve skills also covers profile improvements, audience analysis, and team posting programs, with manual publishing available without setup.

• Planning a week of LinkedIn content
• Drafting posts, comments, and replies
• Reviewing drafts for formulaic AI wording

Analyze a LinkedIn post to identify its opening formula, body structure, and closing pattern. Get an explanation of its persuasive devices, confidence scores, cautions, and a blank template adapted to your topic.

• Study the structure of a popular post
• Analyze a competitor's opening
• Extract a template for your own topic

Write and debug Python regressions with PyFixest using a reference for model formulas, estimation functions, and standard errors. It also covers extracting results, comparing models, and producing regression tables and plots, including models that account for group differences.

• Write fixed-effects regression code
• Check clustered standard error settings
• Compare models in tables and plots

Read 小红书 / RedNote posts from shared links and summarize captions separately from information inside images. Check the post's identity and image order, then report sources, reading coverage, and claims that remain unverified.

• Summarizing a post from a shared link
• Reading image notes in their original order
• Understanding tables and formulas inside images