prospect-list-enrichment
starsforks
How to install prospect-list-enrichment?
xuxchloris/export_skills/prospect-list-enrichment
$npx -y skills add Xuxchloris/export_skills --skill prospect-list-enrichmentUse when a trade agent needs to clean, deduplicate, normalize, enrich, or prepare CSV and Excel prospect lists before company research, scoring, or campaign planning
SKILL.md
| 1 | # Prospect List Enrichment |
| 2 | |
| 3 | ## Overview |
| 4 | |
| 5 | Prepare CSV and Excel prospect lists for research and scoring. The core rule is to preserve source evidence while turning inconsistent rows into a reviewable company-level queue. |
| 6 | |
| 7 | Do not create generated company rows. Every enriched row must come from the user's file or a configured collection output. |
| 8 | |
| 9 | ## When to Use |
| 10 | |
| 11 | Use this skill when the user provides a CSV or Excel customer list, asks to remove duplicates, wants missing fields flagged, or needs a batch queue for company research. |
| 12 | |
| 13 | Use `prospect-discovery` first when the user needs a sourcing strategy instead of list processing. |
| 14 | |
| 15 | ## Inputs |
| 16 | |
| 17 | - CSV or Excel prospect list |
| 18 | - Product context from `product-loader` |
| 19 | - Market rules from `MARKET.yaml` |
| 20 | - Optional discovery output from `prospect-discovery` |
| 21 | |
| 22 | ## Outputs |
| 23 | |
| 24 | ```json |
| 25 | { |
| 26 | "input_rows": 0, |
| 27 | "unique_companies": 0, |
| 28 | "duplicate_rows": [], |
| 29 | "ready_for_research": [], |
| 30 | "needs_review": [], |
| 31 | "excluded_rows": [], |
| 32 | "output_columns": [], |
| 33 | "next_steps": ["company-research", "prospect-scoring"] |
| 34 | } |
| 35 | ``` |
| 36 | |
| 37 | ## Procedure |
| 38 | |
| 39 | 1. Run `python tools/batch_prospect_pipeline.py --input <prospects.csv|xlsx> --product <PRODUCT.yaml> --market <MARKET.yaml> --tone <TONE.yaml> --discovery <DISCOVERY.yaml> --output-dir <folder>` when one-step batch output is needed. |
| 40 | 2. If the product file is a catalog and the user names one product, add `--product-query <name>` or `--sku <sku>` instead of editing the catalog. |
| 41 | 3. Read CSV or Excel rows without changing the original file. |
| 42 | 4. Normalize column names and map available values to company name, website, country, business type, source URL, source note, contact email, contact phone, and contact clue. |
| 43 | 5. Normalize websites by domain and deduplicate rows by domain first, then by normalized company name and country. |
| 44 | 6. Preserve all source URLs and merge useful source notes when duplicates are combined. |
| 45 | 7. Mark rows without company name or website as `needs_review`. |
| 46 | 8. Mark rows outside the target market or unrelated to the product category as `excluded_rows` with a reason. |
| 47 | 9. Write `prospects.enriched.xlsx`, `research_reports.json`, `scores.xlsx`, and `email_drafts.xlsx` when using the batch pipeline. |
| 48 | 10. Treat `research_reports.json` as the source of fetched evidence for scoring and emails. |
| 49 | 11. Do not fill missing company facts from assumptions; use `needs_review`, `fetch_failed`, or `no_evidence`. |
| 50 | 12. If the user asks for a different output shape, preserve the same row data and choose the requested export format instead of changing the facts. |
| 51 | 13. Send research-ready rows to `company-research`; send researched rows to `prospect-scoring`. |
| 52 | |
| 53 | ## Verification |
| 54 | |
| 55 | - Original input file remains unchanged. |
| 56 | - Batch output includes `prospects.enriched.xlsx`, `research_reports.json`, `scores.xlsx`, and `email_drafts.xlsx`. |
| 57 | - Duplicate handling preserves source evidence. |
| 58 | - Every ready row includes company name, website, and source URL. |
| 59 | - Enriched rows include `contact_email`, `contact_phone`, `email_result`, and `phone_result`; missing contact values are written as `没有`. |
| 60 | - Missing fields are listed instead of guessed. |
| 61 | - No generated rows appear in output workbooks. |
| 62 | - Scoring and email drafts are based on fetched evidence. |
| 63 | - Research happens before scoring. |
| 64 | - Output format requests are honored without changing row facts. |
| 65 | |
| 66 | ## Common Mistakes |
| 67 | |
| 68 | | Mistake | Fix | |
| 69 | | --- | --- | |
| 70 | | Deduplicating only by display name | Prefer normalized website domain | |
| 71 | | Dropping source URLs during merge | Preserve every useful source record | |
| 72 | | Treating missing fields as empty facts | Mark them for review | |
| 73 | | Scoring raw rows immediately | Run company research first | |
People who liked this also viewed
6 picksType
- seo-auditWhen the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tagSkillsJul 2026
- copywritingWhen the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user sSkillsJul 2026
- marketing-psychologyWhen the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,'SkillsJul 2026
- content-strategyWhen the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "conSkillsJul 2026
- programmatic-seoWhen the user wants to create SEO-driven pages at scale using templates and data. Also use when the user mentions "programmatic SEO," "template pages," "pages at scale," "directory pages," "location pSkillsJul 2026
- marketing-ideasWhen the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growth ideas,' 'how to market,' 'marketing stratSkillsJul 2026
