Inputs
Provide these when prompted. The skill asks for anything missing before it runs.
Required
- A research objective
Optional
- Required output fields
- Approved sources
- A comparison framework
Agent Skill
Company Research Workflow Planner
Create a repeatable process for researching and comparing companies.
Version 1.0 Updated June 2026 SKILL.md MIT 6 min read
Overview
What this skill does
Ad hoc company research produces inconsistent notes that are hard to compare and impossible to hand off, so every analyst reinvents the process.
This skill designs a repeatable workflow: research objectives, source types, the fields every profile must contain, the research sequence, validation steps, the output structure, and completion criteria — so research is consistent and reviewable.
When to use it
Best used for
- Standardizing company research across a team
- Building a repeatable account-research playbook
- Defining the fields every profile needs
- Setting completion criteria for research tasks
Know the limits
When not to use this skill
- You want one company researched now (use Company Research)
- You have no research objective
- You need the research executed, not planned
Outputs
A research process with a consistent, inspectable schema.
research_objectivesWhat the research must answer.
source_typesApproved/relevant sources.
required_fieldsFields every profile must contain.
research_sequenceOrdered research steps.
validation_stepsHow to verify findings.
output_structureThe profile/report shape.
completion_criteriaWhen research is done.
Example
Example
A repeatable account-research process.
Input
Objective: Consistent profiles for target accounts before outreach.Output
research_objectives: Confirm fit; surface talking points
source_types: Company site; directories; public profiles
required_fields: Overview, industry, size, offering, fit notes, gaps
research_sequence: Company -> people -> recent signals
validation_steps: Cross-check facts; mark assumptions
output_structure: Company Research schema
completion_criteria: All required fields filled or marked as gapsResearch becomes a repeatable, reviewable process with explicit fields and a clear definition of done.
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
Company Research Workflow Planner
Purpose
Create a repeatable process for researching and comparing companies.
When to use this skill
- Standardizing company research across a team
- Building a repeatable account-research playbook
- Defining the fields every profile needs
- Setting completion criteria for research tasks
When not to use this skill
- You want one company researched now (use Company Research)
- You have no research objective
- You need the research executed, not planned
Required inputs
- A research objective
Optional inputs
- Required output fields
- Approved sources
- A comparison framework
Rules
- Define explicit required fields and completion criteria.
- Sequence research logically.
- Include validation steps.
- Keep the output structure consistent.
- Note assumptions where objectives are broad.
Process
- Parse the research objective.
- Define sources and required fields.
- Order the research sequence.
- Add validation steps.
- Define output structure and completion criteria.
Output format
Return a research process with the following fields:
- research_objectives
- source_types
- required_fields
- research_sequence
- validation_steps
- output_structure
- completion_criteria
Validation
- Confirm required fields cover the objective.
- Confirm validation steps are present.
- Confirm completion criteria are testable.
Limitations
- A process is only as good as the sources it uses.
- Completion criteria may need tuning over time.
Before you rely on it
Safety and limitations
- A process is only as good as the sources it uses.
- Completion criteria may need tuning over time.
- 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 does the process it produces look like?
A repeatable set of steps and fields for researching and comparing companies consistently, so every account is profiled the same way and stays comparable.
How does this pair with Company Research?
This plans the repeatable process; the Company Research skill executes a single profile within that process.
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.