Inputs
Provide these when prompted. The skill asks for anything missing before it runs.
Required
- A prospect or lead list
Optional
- A target column schema
- Formatting conventions (casing, phone format)
- Fields that are mandatory
Agent Skill
Prospect List Cleanup
Normalize and improve the consistency of prospect-list data before outreach or import.
Version 1.0 Updated June 2026 SKILL.md MIT 6 min read
Overview
What this skill does
Exported prospect lists arrive messy: mixed casing, inconsistent company names, partial rows, and stray duplicates that break CRM imports and personalization.
This skill standardizes the records, flags incomplete rows and suspected errors instead of silently editing them, and returns a clear cleanup summary so you can trust what changed and what still needs a human.
When to use it
Best used for
- Preparing an export for CRM or outreach import
- Standardizing names, casing, and formats
- Flagging incomplete or broken rows
- Producing a defensible cleanup audit
Know the limits
When not to use this skill
- You need verified emails or enrichment, not cleanup
- The file has no consistent columns to normalize
- You want hard de-duplication (use Duplicate Record Review)
Outputs
The cleaned list plus a summary with a consistent, inspectable schema.
standardized_recordsRecords normalized to a consistent format.
incomplete_recordsRows missing mandatory fields.
suspected_errorsLikely typos or malformed values.
normalization_notesWhat was changed and why.
cleanup_summaryCounts and an overall summary.
Example
Example
Two rows normalized.
Input
name,company,email
maria chen,LUMEN ROBOTICS inc,maria@lumen
james,Northwind,Output
standardized_records: Maria Chen | Lumen Robotics | maria@lumenrobotics.com (email domain incomplete, flagged)
incomplete_records: Row 2 (James) missing last name and email
suspected_errors: Row 1 email missing TLD
normalization_notes: Title-cased names; trimmed company suffix
cleanup_summary: 2 rows; 1 standardized, 1 incomplete, 1 suspected errorThe skill fixes casing and company form, but it flags rather than fabricates the broken email and the missing fields, leaving the judgment calls to you.
Setup
How to use the skill
General steps first, then notes for specific clients where verified.
- 1Download the file using the button below, or copy the Markdown.
- 2Place it in a directory named after the skill (e.g. skill-name/).
- 3Make sure the filename stays exactly SKILL.md.
- 4Add any references or assets included with the package.
- 5Load the skill into a compatible agent and provide the required inputs.
Claude Code
- 1Create a folder for the skill and save SKILL.md inside it.
- 2Place the folder where your project's skills are discovered.
- 3Reference the skill when you want it applied to your data.
Other compatible clients
- 1Confirm the client supports the open Agent Skills format.
- 2Load the SKILL.md file as instructed by that client.
- 3If skills are not auto-loaded, paste the Markdown as instructions.
Source
Full SKILL.md source
Read the rendered skill or copy the complete Markdown. The download is generated from this exact source.
Version 1.0 SKILL.md ~2 KB MIT
Prospect List Cleanup
Purpose
Normalize and improve the consistency of prospect-list data before outreach or import.
When to use this skill
- Preparing an export for CRM or outreach import
- Standardizing names, casing, and formats
- Flagging incomplete or broken rows
- Producing a defensible cleanup audit
When not to use this skill
- You need verified emails or enrichment, not cleanup
- The file has no consistent columns to normalize
- You want hard de-duplication (use Duplicate Record Review)
Required inputs
- A prospect or lead list
Optional inputs
- A target column schema
- Formatting conventions (casing, phone format)
- Fields that are mandatory
Rules
- Standardize formatting; do not invent missing values.
- Flag incomplete and suspect rows rather than deleting them.
- Record every change in normalization notes.
- Preserve the original value when flagging an error.
- Apply the same conventions to every row.
Process
- Profile the columns and detect formats.
- Normalize casing, names, companies, and formats.
- Flag incomplete and suspected-error rows.
- Record normalization notes.
- Produce a cleanup summary with counts.
Output format
Return the cleaned list plus a summary with the following fields:
- standardized_records
- incomplete_records
- suspected_errors
- normalization_notes
- cleanup_summary
Validation
- Confirm no values were invented.
- Confirm flagged rows retain their original data.
- Confirm the summary counts match the records.
Limitations
- It standardizes formatting, not factual accuracy.
- Suspected errors are heuristics and should be reviewed.
Before you rely on it
Safety and limitations
- It standardizes formatting, not factual accuracy.
- Suspected errors are heuristics and should be reviewed.
- Review the output before acting on it.
- Do not upload confidential datasets to an external model without authorization.
- Outputs depend on the model and the source data and are not guaranteed to be accurate.
History
Changelog
- v1.0June 2026
- Initial release.
Questions
Agent Skill FAQ
What fields does it standardize?
Formatting and consistency across names, companies, titles, locations, and similar fields. It normalizes values and reports what changed; it does not invent missing data.
Will it delete duplicate rows?
No. It flags suspected issues but leaves de-duplication to Duplicate Record Review so you stay in control of merges.
Do I need ProfileSpider to use this skill?
No. The skill works on any compatible data. ProfileSpider is one convenient way to produce that structured input.
Does running this skill send data to ProfileSpider?
No. Downloading or copying the file does not send any data to ProfileSpider. What happens afterward depends on the AI service you load it into.
Are Agent Skills the same as prompts?
No. A skill is a structured, reusable package — task, inputs, rules, process, and output format — so the workflow runs consistently and can be shared, versioned, and edited.