candidate-presentation
Skill0 starsChanged 37 days agoMITView on GitHub
Create a factual candidate shortlist or client presentation from authorized candidate records, role criteria, and screening or interview evidence.
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- candidate-outreachSkill
- candidate-screeningSkill
- hiring-scorecardSkill
- interview-invitationSkill
- interview-kitSkill
- job-intakeSkill
- recruitment-workflowSkill
- sourcing-strategySkill
- vitaeSkill
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 13
Use the role brief, scorecard, candidate records, screening/interview evidence, target client audience, and sharing authorization.
- Distinctive: line 21
Remove unnecessary contact details and sensitive information.
- Distinctive: line 38
Check every claim, current logistics, sharing scope, named/anonymized mode, and consistency across candidates.
≈ “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 presentation
Inputs
Use the role brief, scorecard, candidate records, screening/interview evidence, target client audience, and sharing authorization. Confirm whether the presentation is named or anonymized and which details may be disclosed. Candidate interest and permission to represent them must not be assumed from an ATS record.
Procedure
- Resolve the candidate and role identities. Check that facts from different records have not been combined.
- Lead with role relevance: the most useful evidence for the agreed outcomes. Attribute achievements accurately and distinguish verified facts, candidate statements, and recruiter assessments.
- Summarize each criterion with evidence and open questions. Preserve meaningful gaps; do not turn a lack of evidence into either a qualification or a failure.
- Include compensation expectations, availability, location, and work arrangement only when relevant, supplied, current, and authorized for this audience. Do not infer them from personal circumstances.
- Remove unnecessary contact details and sensitive information. For anonymized presentations, also check employer/project combinations and linked documents that could identify the person; explain residual limits rather than promising anonymity.
- For a shortlist, use a consistent structure and comparable evidence. Explain the recruiter's rationale without inventing an overall ranking or treating a match score as a hiring decision.
Output
Return a client-ready summary, evidence table, role-relevant achievements, approved logistics, unresolved questions, and a proposed next step. Include a separate internal sharing checklist and source notes so they are not accidentally sent to the client.
Example
Supported statement: “Alex reports building observability dashboards for three payment services. The interview provided a concrete example of reducing diagnosis time.” Open point: “Ownership of incident prevention across a full service lifecycle still needs assessment.” Unsupported rewrite to avoid: “Alex is a proven reliability leader who will eliminate incidents.”
With Vitae
Use live candidate, resume, job, and interview read tools where available. Do not create public share links, expose a CV, or select a presentation-sharing mode without the recruiter's authorization. If no verified sharing tool is available, return the content and direct the recruiter to Vitae's candidate presentation flow. Do not invent a public profile URL.
Quality check and handoff
Check every claim, current logistics, sharing scope, named/anonymized mode, and consistency across candidates. Draft complete means ready for recruiter review, not sent to the client. Record client feedback and the next agreed action when provided.
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.

