candidate-outreach
Skill0 starsChanged 39 days agoMITView on GitHub
Write personalized initial recruiting invitations and follow-ups using verified role and candidate facts, with clear calls to action and respectful stop conditions.
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- candidate-presentationSkill
- 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, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
Use for first contact about an opportunity, follow-up, or re-engagement.
- Distinctive: line 22
Prefer an interest check for cold contact.
- Distinctive: line 45
If this isn't relevant, let me know and I won't follow up.
≈ “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 outreach
Use for first contact about an opportunity, follow-up, or re-engagement. Use interview-invitation once an interview has been agreed.
Inputs
Gather the approved role brief, candidate evidence, sender identity, channel, relationship history, language/tone, and the desired next action. Check existing replies, opt-outs, and duplicate outreach if available. If history is unavailable, say so before proposing a send or sequence.
Procedure
- Identify one specific, job-relevant reason for contact that the evidence supports. Cite that fact in the working notes. Do not imply personal familiarity, knowledge of job-seeking intent, or admiration you cannot substantiate.
- Explain the role's relevant opportunity using confirmed facts. Include compensation and work arrangement when supplied and useful; do not invent a salary, urgency, exclusivity, or client permission to name the company.
- Draft a short subject and a concise body. A useful default is 70–130 words, adjusted to the channel and user's request. Lead with relevance, explain the opportunity, and ask for one easy next step.
- Prefer an interest check for cold contact. Do not demand a CV, application, and booking in the same first message. An existing candidate relationship can justify a more direct request.
- If follow-ups are requested, make each add information rather than repeat “bumping this.” Propose timing as a draft, check existing sequences, and stop on a reply, opt-out, role closure, or the user's stated limit. Never manufacture a prior conversation or use a false
Re:subject. - Review the draft for factual accuracy, relevance, readability, and pressure. Remove flattery, generic AI phrasing, sensitive personal observations, and unsupported claims.
Output
Return the subject, ready-to-review body, factual personalization note, unresolved details, and any requested follow-ups. Clearly label draft status. Provide variants only when useful or requested.
Fictional example
Confirmed inputs: Alex's profile describes building observability for payment services. Northbank is hiring a backend engineer to improve payment reliability; the role is hybrid in London. The sender is Sam, an authorized recruiter.
Subject: Backend reliability role at Northbank
Hi Alex,
Your work on observability for payment services caught my attention. I'm helping Northbank hire a backend engineer to improve reliability across its payments platform, and that experience looks relevant to the work.
The role is hybrid in London, with a focus on incident prevention and service ownership. Would you be open to a short overview so you can decide whether it's worth a conversation?
Best, Sam
If this isn't relevant, let me know and I won't follow up.
Evidence note: the profile supports observability experience; it does not establish that Alex is job seeking or personally led incident response. Salary is not supplied, so no range is asserted.
With Vitae
Use live candidate and job read tools to retrieve authorized context. This skill does not itself provide email delivery. If no verified send/draft-save tool is available, return the copy for the recruiter to use in Vitae. Do not call campaign import or workflow execution as an implicit send substitute. Respect previous explicit send authorization, recipient/sender scope, and server approval controls; never claim delivery without a confirming result.
Completion and handoff
The draft is complete when claims are supported, the next action is clear, and recipient history has been checked or flagged. Record actual reply and send states separately from the copy. A positive response can lead to interview-invitation after the recruiter confirms the next stage.
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.

