Inputs
Provide these when prompted. The skill asks for anything missing before it runs.
Required
- An ICP or research goal
Optional
- Known good sources
- Geographies to focus on
- Fields you must collect
Agent Skill
Directory Research Planner
Turn an ICP or research goal into a plan for finding and scraping suitable directories.
Version 1.0 Updated June 2026 SKILL.md MIT 6 min read
Overview
What this skill does
The hardest part of building a list is often knowing where to look. Jumping straight into scraping the wrong sources wastes time and credits.
This skill turns your ICP or goal into a concrete sourcing plan: the directory types likely to contain your audience, search queries to find them, the fields to collect, inclusion and exclusion criteria, and a recommended extraction workflow.
When to use it
Best used for
- Planning where to source a new list
- Translating an ICP into search queries
- Choosing the right directory types
- Scoping a scraping project before starting
Know the limits
When not to use this skill
- You already have your source list
- You need the data extracted now (this plans, it does not scrape)
- Your audience is not present in public directories
Outputs
A sourcing plan with a consistent, inspectable schema.
directory_typesKinds of directories to target.
suggested_source_categoriesWhere those directories live.
search_queriesQueries to find sources.
fields_to_collectData to extract from each source.
inclusion_criteriaWhat qualifies a record.
exclusion_criteriaWhat to skip.
recommended_extraction_workflowHow to extract efficiently.
Example
Example
A plan for a niche B2B audience.
Input
ICP: Independent UX agencies in the EU, 5-50 staff.Output
directory_types: Agency directories; design awards; marketplace listings
search_queries: "UX agency directory" + EU country; "design agencies" site lists
fields_to_collect: Agency name, website, size, location, contact page
inclusion_criteria: EU-based, 5-50 staff, UX focus
exclusion_criteria: Freelancers; non-EU; dev-only shops
recommended_extraction_workflow: Scrape directory listings -> dedupe -> enrich sitesInstead of guessing, you get specific directory types, queries, and a clean extraction plan tuned to the ICP.
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
Directory Research Planner
Purpose
Turn an ICP or research goal into a plan for finding and scraping suitable directories.
When to use this skill
- Planning where to source a new list
- Translating an ICP into search queries
- Choosing the right directory types
- Scoping a scraping project before starting
When not to use this skill
- You already have your source list
- You need the data extracted now (this plans, it does not scrape)
- Your audience is not present in public directories
Required inputs
- An ICP or research goal
Optional inputs
- Known good sources
- Geographies to focus on
- Fields you must collect
Rules
- Tie every recommendation to the stated ICP/goal.
- Suggest public, accessible source types.
- Make inclusion and exclusion criteria explicit.
- Recommend an efficient extraction order.
- Note assumptions where the goal is vague.
Process
- Parse the ICP or goal.
- Identify directory and source types.
- Draft search queries.
- Define fields and inclusion/exclusion criteria.
- Recommend an extraction workflow.
Output format
Return a sourcing plan with the following fields:
- directory_types
- suggestedsourcecategories
- search_queries
- fieldstocollect
- inclusion_criteria
- exclusion_criteria
- recommendedextractionworkflow
Validation
- Confirm sources match the ICP.
- Confirm criteria are explicit and testable.
- Confirm the workflow is actionable.
Limitations
- It plans sources; it does not verify they exist.
- Some audiences are not well represented in public directories.
Before you rely on it
Safety and limitations
- It plans sources; it does not verify they exist.
- Some audiences are not well represented in public directories.
- 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 is in the source plan?
A shortlist of suitable directories for your ICP, why each one fits, and the extraction steps to turn them into a lead list — a plan you then execute with a scraper.
Does this scrape the directories?
No. It produces the plan and queries. Use ProfileSpider to run the extraction the plan describes.
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.