Results for “screening”

Turn small-molecule structures into numerical features for similarity searches and models that predict activity or properties. Using Molfeat, the skill covers representation choices, invalid inputs, alignment with experimental labels, and saving feature-generation settings for reuse.

• Prepare molecular features for activity or property prediction
• Choose molecular representations for similarity searches
• Keep experimental labels aligned after rejecting invalid molecules

Plan experiments before collecting data. Helps choose study designs, randomly assign subjects or samples, organize treatment combinations, and generate reproducible schedules while checking for confounding and repeated measurements incorrectly counted as independent samples.

• Create random assignments for subjects or samples
• Screen multiple experimental factors
• Balance conditions across batches, days, or plate positions

Generate candidate positions and orientations for small molecules binding to proteins with DiffDock and DiffDock-L. Prepare single or batch docking runs, organize predicted poses by model confidence, and review validation needs without treating confidence as binding affinity.

• Predicting binding poses for a protein and small molecule
• Preparing and validating batch docking inputs
• Comparing poses across receptor conformations

Plan protein characterization experiments with Adaptyv's cloud laboratory, estimate costs, submit sequences, track progress, and retrieve measured results. Supports binding, thermal stability, expression, fluorescence, and enzyme activity workflows through the API and Python SDK.

• Plan binding screens for candidate protein sequences
• Estimate experiment costs before submission
• Track laboratory progress and retrieve results

Apply a firm's customer verification and anti-money-laundering rules to structured onboarding records. Produce risk ratings, rule-by-rule findings, missing-document lists, and review routing with supporting evidence, while leaving approval to human reviewers.

• Rating onboarding risk under firm rules
• Checking for missing or expired documents
• Recording evidence for each rule outcome

Analyze convertible bonds in China's A-share market through bond value, stock conversion value, and option value. Review conversion-price resets and redemption clauses, then compare candidates using low-price, low-premium screening and periodic portfolio rotation frameworks.

• Compare bond, stock conversion, and option values
• Review conversion-price resets and early redemption risks
• Screen bonds for low prices and low conversion premiums

Screen Chinese A-shares, Hong Kong stocks, and US stocks using valuation ratios, profitability, and financial statement data. Set criteria to identify value or growth candidates, with market-specific guidance on using the results in historical strategy tests.

• Find value stocks using valuation and profitability criteria
• Filter Chinese A-shares using published financial statements
• Build a US or Hong Kong stock universe for strategy testing

Evaluate dividend stocks by checking earnings, cash flow, debt, and dividend history. Assess whether payouts can last, identify high yields driven by falling prices, and consider total returns alongside dividend income.

• Checking whether a dividend is sustainable
• Screening high-yield stocks for payout risks
• Comparing the quality of dividend growth

Set up AI email screening that compares writing style and communication habits to identify impersonation and suspicious payment requests. Connect detection policies to quarantine, warning banners, and analyst review workflows.

• Detecting executive impersonation in emails
• Reviewing vendor payment change requests
• Flagging unusual employee email behavior

Check training data and machine learning models for malicious changes, including backdoors that cause unexpected behavior on specific inputs. Combine data quality checks, model analysis, and file integrity verification, then document findings and retest after remediation.

• Screening third-party data before training
• Checking downloaded model weights before deployment
• Investigating unexpected behavior on specific inputs

Screen AI application inputs and historical logs for prompt injection, where malicious instructions try to redirect the model. Combine pattern matching, text structure scoring, and a DeBERTa classifier to flag suspicious content and produce JSON results.

• Screening chatbot and AI agent inputs
• Checking external text used in retrieval-based AI applications
• Auditing historical interaction logs for injection attempts

Review a resume against a job description to identify missing keywords and formatting that applicant tracking systems may struggle to read. Get a keyword match score and specific suggestions for wording, placement, and layout.

• Check resume formatting before applying
• Compare resume keywords with a job description
• Revise a resume for a career change

Find suitable grants and bidding opportunities, check eligibility before drafting, and prepare applications or responses to requests for proposals using past submissions and actual organizational data. It also tracks submission deadlines and reporting obligations after an award.

• Finding grants your organization qualifies for
• Screening solicitations before deciding to bid
• Drafting applications from past submissions

Screens incoming nondisclosure agreements against an organization's criteria or stated defaults. Classifies each agreement into three review levels and produces a report covering flagged clauses, risks, suggested fixes, and recommended next steps.

• Screen an NDA received by sales or business development
• Check for non-compete and non-solicitation clauses
• Identify missing exceptions to confidentiality obligations

Track candidates from first outreach to offer acceptance, and review time spent at each stage, conversion rates, and recruiting sources. Use these measures to understand hiring progress and where candidates drop out.

• Reviewing candidate progress across hiring stages
• Finding delays and drop-offs in the hiring process
• Comparing recruiting sources and offer acceptance rates

Review marketing copy against brand voice, terminology, style rules, and core messages. Receive findings ranked by severity, concrete before-and-after revisions, and separate flags for unsupported claims, missing disclaimers, and other concerns requiring further review.

• Check a draft against brand guidelines before publication
• Audit terminology and tone across multiple pieces of copy
• Identify unsupported claims and missing disclaimers

Prepare resumes for specific job descriptions using Resume Matcher without an API key. Create a master resume, tailor supported experience, check application screening scores, write cover letters and outreach messages, and export PDFs.

• Create a master resume from existing documents
• Tailor a resume to a specific job
• Draft cover letters and outreach messages

Plan an acquisition or prepare a company for sale using structured checklists and decision frameworks. Examine strategic fit, due diligence—the investigation before a deal—valuation approaches, negotiation terms, and plans for combining operations after acquisition.

• Screening acquisition targets against strategic goals
• Organizing due diligence questions by business area
• Preparing documents before selling a company

Review an outside contributor’s pull request before running its code. Identify concealed behavior, obfuscated code, risky dependencies, and build hooks, with file locations and specific checks for maintainers to follow up.

• Screening an outside contributor’s pull request before execution
• Checking encoded code and unexplained network calls
• Reviewing dependency changes and installation scripts

Find arXiv papers by topic, research category, or paper ID. Retrieve titles, authors, abstracts, and links, check new submissions, and add AlphaXiv's AI-generated overviews when available to help decide which papers to read.

• Checking new AI and machine learning papers
• Finding papers on a specific research topic
• Looking up a paper by its ID or arXiv URL

Screen companies across markets within a chosen industry and narrow the list to three investment candidates. Compare financial health, lasting competitive advantages, valuations, and risks, while recording why other companies were excluded.

• Narrowing an industry's investment candidates to three companies
• Comparing Chinese, Hong Kong, and US stocks using shared criteria
• Reviewing why companies passed or failed the screening

Screen listed companies using seven financial measures covering profitability, cash flow, debt payments, and share dilution, which reduces existing shareholders' ownership. Produce comparison tables showing exclusions, exemptions, borderline results, and missing data to guide further research.

• Screening several listed companies before deeper research
• Comparing financial quality within an industry
• Reviewing index constituents or investment themes

Use Meta's Prompt Guard to detect malicious instructions in user prompts and external data. This skill guides input filtering, batch checks for retrieved documents, detection threshold adjustments, and splitting long text for inspection.

• Detecting attempts to override an LLM's instructions
• Checking API responses for embedded malicious instructions
• Batch screening documents retrieved for RAG

Build safety checks for LLM prompts and responses using Meta's LlamaGuard. This skill covers content classification, batch moderation, serving a moderation API, and connecting checks to NeMo Guardrails.

• Screening user prompts before sending them to an LLM
• Checking generated responses before displaying them
• Building an API for content safety checks