candidate-qualification
Skill9 starsChanged 5 months agoMITView on GitHub
Evaluates candidate profiles against a job description and hiring criteria. Use when the user provides candidate profiles plus a role definition and wants consistent screening, matched requirements, and an interview recommendation.
In this repository23 other files it gives its agents.
- account-prioritizationSkill
- b2b-lead-qualificationSkill
- company-data-normalizationSkill
- company-researchSkill
- company-research-workflow-plannerSkill
- company-segmentationSkill
- competitor-researchSkill
- directory-research-plannerSkill
- duplicate-record-reviewSkill
- job-title-normalizationSkill
- lead-list-analysisSkill
- lead-list-segmentationSkill
- lead-research-workflow-plannerSkill
- market-researchSkill
- outreach-brief-generatorSkill
- partner-qualificationSkill
- persona-classificationSkill
- person-researchSkill
- prospect-list-cleanupSkill
- recruiting-sourcing-plannerSkill
- research-gap-analysisSkill
- supplier-qualificationSkill
- territory-segmentationSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 51
Use evidence from the candidate profile.
- Distinctive: line 52
Do not infer health, religion, ethnicity, sexual orientation, political affiliation, or other sensitive personal attributes.
- Distinctive: line 53
Treat missing required items as gaps, not failures, unless the user marks them disqualifying.
≈ “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
Candidate Qualification
Purpose
Evaluate candidate profiles against a job description and hiring criteria with an evidence-based fit score.
When to use this skill
- Screening a sourced shortlist against one role
- Standardizing first-pass candidate review
- Documenting why a candidate advances or not
- Spotting must-have requirements that are missing
When not to use this skill
- You have no structured job description or criteria
- You need to assess protected characteristics (never do this)
- The decision requires information not present in the profile
Required inputs
- A job description
- Required skills
- Candidate profiles
Optional inputs
- Preferred skills
- Seniority expectations
- Location or work-authorization requirements
- Compensation band
Rules
- Score only against the stated job requirements.
- Use evidence from the candidate profile; do not assume unstated experience.
- Do not infer health, religion, ethnicity, sexual orientation, political affiliation, or other sensitive personal attributes.
- Treat missing required items as gaps, not failures, unless the user marks them disqualifying.
- Apply the same criteria to every candidate.
Process
- Parse the job description into required and preferred criteria.
- Map each criterion to evidence in the candidate profile.
- Score required criteria first, then preferred.
- List matched requirements, gaps, and risks.
- Recommend advance, hold, or pass with a reason.
Output format
Return one record per candidate with the following fields:
- candidate_fit_score
- required_criteria_matched
- missing_requirements
- risk_factors
- interview_recommendation
Validation
- Confirm each matched requirement cites profile evidence.
- Confirm no sensitive attributes were inferred.
- Confirm the recommendation follows from the criteria.
Limitations
- A profile is not a full assessment; use the score as a screen, not a decision.
- Self-reported experience may be inaccurate and should be verified.
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.

