research-target-person
Skill0 starsChanged 3 months agoMITView on GitHub
Research the likely human owner of a verified opportunity and produce an evidence-backed contact hypothesis without guessing identity or contact details.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/job-agent.mdcCursor rule
- answer-questionsSkill
- claim-checkSkill
- daily-briefSkill
- find-broad-jobsSkill
- find-consulting-opportunitiesSkill
- find-jobsSkill
- record-outcomeSkill
- refresh-candidate-brandSkill
- review-search-performanceSkill
- score-fitSkill
- setup-profileSkill
- tailor-resumeSkill
- write-cover-letterSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Use after an opportunity has already been qualified.
- Distinctive: line 20
Start with the highest-priority target-person role category.
- Distinctive: line 21
Search the company's own leadership/team pages first.
- Distinctive: line 22
Use reputable professional/public sources to confirm current title and company.
- Distinctive: line 25
If no reliable person can be identified, return unresolved rather than guessing.
- Distinctive: line 39
Never infer private email patterns and never fabricate phone numbers or addresses.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
research-target-person
Use after an opportunity has already been qualified.
Inputs
- normalized opportunity record;
- target-person role categories from
target_person_roles; - company name and source evidence.
Workflow
- Start with the highest-priority target-person role category.
- Search the company's own leadership/team pages first.
- Use reputable professional/public sources to confirm current title and company.
- Require at least one source supporting the person's current role.
- Record only contact information that is publicly provided or obtained through an authorized enrichment source.
- If no reliable person can be identified, return unresolved rather than guessing.
Output
Return:
- name;
- exact current title;
- company;
- why this person is relevant to the specific opportunity;
- source URL(s);
- confidence: high / medium / unresolved;
- public/authorized contact fields if actually available;
- suggested next action: apply, ask for intro, LinkedIn connection, email draft, or no action.
Never infer private email patterns and never fabricate phone numbers or addresses.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.