Company Background Checker
Verify partner claims and identify business risks
Company Background Checker
Verify partner claims and identify business risks
Showcase
Description
The Company Background Checker uses a tiered evidence verification method to check the authenticity of partners, suppliers, bidders, and internship providers. It identifies risks such as qualification grafting, data inflation, time anomalies, entity mismatches, metric mixing, performance misattribution, disguised dispatching, and omitted negative facts, producing due diligence conclusions that can be directly reported to leadership and written into contracts. Each conclusion is tagged across two dimensions: evidence nature (A-G: statutory registration, official lists, judicial supervision, annual reports, commercial databases, public web, inference) and source status (original official, official reference, commercially processed, self-reported), strictly distinguishing between disproven, unverified, and lacking evidence. It includes a built-in data source accessibility table and integration tiers. For listed or bond-issuing entities, it first reads disclosures from Cninfo and stock exchanges; for unlisted micro-enterprises, it provides alternative pathways for login walls and an industry metrics exception table. It enforces strict group-to-legal-entity attribution and includes 13 omission checks. Version 2.4 adds a bidding and supplier admission module: distinguishing bidding from winning, verifying performance entity attribution, grading licenses and certifications across four levels, checking three discredited lists according to regulatory standards with one-vote veto, and delivering a one-page conclusion card, evidence request letter, and contract risk clause package, complete with 18 regression self-checks. Version 2.5 adds an educational scenario module for reviewing school-enterprise partners, internship providers, and employment agencies, incorporating admission criteria and red lines based on vocational school internship regulations, using five criteria to identify disguised dispatching, prohibiting intermediary involvement and proxy fee collection, mandating tripartite agreements and internship liability insurance, and noting that these regulations serve as references for general undergraduate institutions. Version 2.5.1 introduces a final delivery gate with six-item skip-step consistency checks, an evidence chain self-verification table, a single-screen five-piece delivery set, anti-patterns, and a channel fact cold-start table. It disables commercial database inferred fields like enterprise scale or ratings. It supports four modes: basic risk overview from company name alone, targeted verification with company name and claims, page-level verification of uploaded materials, and integration consulting. It triggers when users mention background checks, due diligence, partner or supplier reviews, bidding qualifications, internship provider checks, school-enterprise reliability, cross-validation, or requests to verify specific companies. It is not suitable for legally binding due diligence requiring a law firm or classified military qualification reviews.
Recommended by
Dancang
Why we love this skill
It refuses to label missing data as zero risk. Instead, it anchors on unified social credit codes and gathers tiered evidence from official registrations, licenses, judicial records, and public filings. Its unique evidence boundaries and gap disclosures make due diligence conclusions truly verifiable.
Related Skills
View all
Fact Check
Hand any opinion, conclusion, data point, or proposal to an AI fact-checker: online source tracing, five-level credibility ratings, and reasoning-chain analysis—followed by a fact-check report you can share directly. 【What it does】Paste any claim, and the skill completes three checks automatically: 🔍 Break it down—separates the claim into “verifiable facts / inferred conclusions / value judgments,” keeping positions distinct from facts 🌐 Trace sources online—verifies sources, samples, statistical definitions, dates, and full context point by point, with cross-checking across multiple channels 🧩 Check the reasoning chain—identifies hidden assumptions, correlation-versus-causation errors, omitted alternative explanations, and the conditions under which the conclusion holds or fails 【Why choose it】 ✅ Five-level credibility ratings: Confirmed / Generally sound but should be narrowed / Contested / Insufficient evidence / Clearly false, with source links for every item ✅ Four-part report: Reliable facts and corrections / The most critical flaws in the reasoning chain / The strongest revised version / How much you can trust it ✅ No made-up answers: When a claim cannot be verified, it is honestly marked “Insufficient evidence” instead of being passed off as “possibly true” ✅ Report-ready output: Share it directly with readers, clients, or your community 【Who it’s for】Independent media and content creators, investors and analysts, students and researchers, and anyone who needs to quickly decide whether a statement can be trusted. 【How to use it】Paste the claim you want checked—anything from one sentence to a paragraph. For example, enter “People with Hashimoto’s thyroiditis often have low energy” to get a source-backed, tiered fact-check report. ⚠️ For medical, legal, investment, and other professional questions, use this for information verification only and rely on qualified professionals for advice.
Research Review Assistant
An expert assistant for university-level research project reviews. Provide the materials for N projects in a given category. Each project includes three types of files: a proposal, a form-check summary or interim review form, and supporting evidence. File names may be scrambled, mismatched, or changed, and files may be DOCX, XLSX, PDF, or image files. Supporting evidence may be bundled into one file or provided as multiple separate files. This Skill then completes the following steps: ① Content-anchor alignment—extracts the project or center name, principal investigator, affiliated school, and project period from within the documents; matches the three-part file set for each project; and flags items requiring review when file names do not match their contents. ② Evidence normalization—whether bundled or separate, breaks materials into “atomic evidence items” and creates a coded ledger for each item with one of four status labels: complete, needs verification, missing, or questionable. This avoids judging the strength of the evidence by file count. ③ Three-dimensional item-by-item audit—evaluates each piece of evidence for relevance, authenticity, and completeness, then reconciles it against the commitments in the proposal and the self-reported results in the interim review form. ④ Dual-track scoring and comparative ranking—uses the five weighted criteria in Appendix 2 as the reporting standard and the five dimensions of the interim review as a reference standard. The two systems remain independent and are not combined, and all projects are ranked and grouped into tiers. ⑤ Delivers a structured review draft with “score + review comments” that can be pasted directly into the official form, and can generate an interactive scoring webpage when needed. Huali’s current standards are used by default. Users can confirm or revise the criteria, weights, and reference materials before work begins, or upload replacements. There are two confirmation checkpoints: first for alignment and the evidence ledger, then for scoring and ranking. When materials cannot be identified, the user is prompted to confirm. For project completion reviews, two additional hard requirements apply: first, the correspondence between the proposal’s expected outcomes and the documented evidence must be verified. If the evidence does not include an expected outcome listed in the proposal, the project automatically fails. Second, template issues are distinguished between using the completely wrong template, which results in failure, and partial formatting inconsistencies, which result in only a small deduction.
Data Cleaning & Prep Expert
Data cleaning and organization skill for structured tables and unstructured text, images, and audio. Use when you need to clean data, fix messy spreadsheets, remove duplicates, fill missing values, standardize formats, flatten multi-level headers or cross-tabulations, merge sheets, process survey exports, organize ledgers, run data quality health checks, resolve pivot table mismatches, fix zero sums or numbers stored as text, handle mixed full-width/half-width characters, fix GBK encoding errors, convert wide-to-long tables, split multi-select columns, handle merged cells, reconcile mismatched keys, unify field definitions, standardize tables, or write cleaning steps and formulas. Also covers unstructured scenarios such as cleaning chat logs or interview transcripts, deduplicating and desensitizing text, removing phone numbers and ID cards from materials, checking image libraries, finding duplicate photos, cleaning EXIF privacy and location data, organizing recordings, and auditing audio archives. Covers the full workflow of structural diagnosis, tidy reconstruction, cleaning decisions and execution, conservation verification, and audit trail delivery for Excel, CSV, and TSV files (delivering a clean sheet, backup, log, and exclusion details). For unstructured data, delivers health reports and decision lists, while text workflows execute deduplication and desensitization with dual conservation checks for row and character counts. Ideal for Chinese practical scenarios in government, industrial parks, enterprise ledgers, survey exports, business reports, chat or transcription corpora, and image/audio asset libraries. Not suitable for machine learning feature engineering (missing value imputation serves analysis rather than modeling), and does not perform audio transcription or noise reduction.
Information
- Version
- v23
- Last updated
- Runtime credits
- Usage-based
- Models
- Auto
