Potential Project Recommendation and Opportunity Screening for Bids and Tenders
Paste the following prompt into your AI chat to install this skill:
Please refer to https://skillhub.cn/install/skillhub.md to install @org-mbvufw6y/jylj-recommend.
About this skill
Specific Problem It Solves
In the bid and tender market, sales or service teams face information overload: they need to sift through vast announcements to find projects matching their business. Traditional keyword searches often lead to missed opportunities due to vague business descriptions or procurement language differences, overlooking pre-bid projects like upcoming constructions, and manual filtering/scoring is inefficient.
How the Skill Works
This skill converts natural language business descriptions into actionable search profiles, fetches full candidate projects via the Shiboke Technology bidding data API, and applies multi-dimensional scoring based on real evidence. Core capabilities and key steps include:
- Progressive Guidance & Business Profile Construction: Guides users to provide product/service info (e.g., "hospital sewage treatment"), auto-generates a pending business profile extracting direct target words, synonymous procurement terms, application scenario words, demand trigger words, and exclusion words, avoiding overly broad search terms (e.g., standalone "project").
- Full-Page Data Retrieval: Calls
/bid/searchProjectApi(active bids/tenders) and/bid/searchNZJProjectApi(upcoming projects), defaulting to recent 30/90 days with 50-item pages, requesting continuously untilhasNext=false, merging and deduplicating data. - Candidate Filtering & Completion: Excludes projects hitting only broad terms, mismatching exclusion criteria, or already completed; for final recommendations, calls
/bid/getZTBStructreDetail,/bid/getCollectUrletc. to enrich details and source URLs. - Recommendation Scoring & Grading: Scores dimensions like direct business match (40 pts), opportunity stage (20 pts), timeliness (15 pts) normalized to 100, grading into A (80–100, priority follow-up), B (60–79, follow-up after verification), C (<60, observation leads), with evidence confidence levels (high/medium/low).
Applicable Boundaries & Notes
- API Key Dependency: Requires
BBIAO_API_KEYenvironment variable; prompts for acquisition if missing, with secure storage in platform credentials. - Data Coverage: API data is limited by query conditions (e.g., default recent 30 days) and interface constraints; incomplete retrieval is explicitly noted.
- Recommendations Not Guaranteed: Scoring is based on current evidence; low confidence cannot be graded A, and project feasibility isn't guaranteed—manual verification of qualifications, deadlines etc. is needed.
- Dynamic Exclusion Words: Exclusion words inferred from business semantics (e.g., training services don't default to exclude "training"), avoiding mechanical application.
- Interface Anomaly Handling: On pagination failure, retained data is marked, with no simulated complete results.
Use Cases
- After a sales team describes its "hospital sewage treatment equipment" business, it needs to automatically retrieve public bid and competitive consultation announcements related to equipment procurement from the last 30 days, generating a recommendation list scored by business match to allocate sales resources.
- A bid specialist tracking nationwide engineering bids wants to filter projects over 1 million RMB in procurement intent stage; the skill fetches full-page data, supplements purchaser details, and marks registration deadlines.
- When seeking pre-construction matching opportunities, after describing "campus smart security" business, the skill calls the upcoming project API to find projects within 90 days, providing A/B/C recommendation levels based on stage to determine follow-up actions.
- With a preliminary business profile, but results include too many "maintenance" projects, the user provides exclusion term "maintenance"; the skill re-queries and adjusts the recommendation list to show only related equipment procurement or engineering implementation opportunities.
Best For
- Identity: Manufacturing sales director, typical need: monthly identification of high-match equipment procurement projects from vast bidding information, but manual search is time-consuming and prone to missing pre-construction opportunities.
- Identity: Construction company bid project manager, typical need: daily monitoring of bidding platforms to filter qualified public bid projects, requiring automated tools to fetch full data and supplement details for decision-making.
- Identity: IT solution provider marketing specialist, typical need: rapid search for matching projects based on customized needs (e.g., data center construction), but existing channels have scattered data and lack priority scoring.
- Identity: Environmental enterprise business development head, typical need: finding government bidding projects for sewage treatment in specific regions, requiring filtering of unrelated industry noise and focusing on early intervention clues.
Related Skills
AI agent tool for generating HTML proposals for client visit business scenarios, featuring deep research and dynamic mainline mapping.
Bid Proposal Verification Tool is used to verify the consistency between bid proposals and tender documents, checking table of contents, page numbers, attachments, and seals, based on Shibot Technology's bid data API.
An AI engine built on extensive bidding data to precisely search for tender projects and potential clients using natural language or structured criteria.
Automates bid document, response table, and material list generation from bid files and enterprise data using Shibuo Technology API.