sourcing-strategy
Skill0 starsChanged 38 days agoMITView on GitHub
Translate an agreed hiring brief into candidate search hypotheses, search queries, channels, and a measurable sourcing plan.
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- candidate-outreachSkill
- candidate-presentationSkill
- candidate-screeningSkill
- hiring-scorecardSkill
- interview-invitationSkill
- interview-kitSkill
- job-intakeSkill
- recruitment-workflowSkill
- vitaeSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Use the job brief, scorecard, target geography and work arrangement, recruiter capacity, approved channels, and any spending limit.
- Distinctive: line 18
Search the existing talent pool first when relevant.
≈ “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
Sourcing strategy
Inputs
Use the job brief, scorecard, target geography and work arrangement, recruiter capacity, approved channels, and any spending limit. Distinguish existing ATS candidates from new external discovery. An unspecified budget does not authorize paid enrichment or searches.
Procedure
- Define the capability signals that predict the agreed work outcomes. List equivalent titles, adjacent industries, and transferable experience.
- Search the existing talent pool first when relevant. Separate a prior applicant's current interest from historic status; do not assume availability.
- Build a small set of search hypotheses. For each, record role synonyms, capability terms, geography, channel, and expected tradeoff between recall and precision.
- Draft a broad query and a focused variant using the target channel's supported syntax. Do not invent operators or treat a Boolean query as portable across all services.
- Review an initial sample against the scorecard, documenting false positives and missed profiles. Adjust one major filter at a time. Do not narrow by protected characteristics or convenient proxies.
- Plan outreach capacity, deduplication, contact provenance, and stop conditions. Honor opt-outs and existing contact restrictions. Define success as relevant, contactable prospects, not raw profile counts.
Output
Return search hypotheses, channel-specific query drafts, a sampling checklist, daily capacity, approved spend, deduplication keys, review checkpoints, and assumptions to test. Mark unexecuted queries as plans.
Example
For a backend reliability role, test “backend engineer,” “platform engineer,” and “site reliability engineer” against incident-analysis evidence. A Boolean-capable channel might start with (backend OR platform OR SRE) AND (observability OR incident OR reliability). Verify the channel supports that syntax and use its dedicated geography filter rather than assuming keyword matches prove location.
With Vitae
Use search_ats_candidates for existing records if it appears in the live connector. External sourcing tools may be unavailable even when a description mentions them. If absent, return the search plan for Vitae's Sourcing surface. Never substitute broad ATS search for an external search and claim new prospects were found. Ask before exceeding an authorized search or enrichment budget.
Completion and handoff
Hand evidence-backed profiles and provenance to candidate-screening, along with duplicate checks and unknowns. Do not scrape restricted sources, invent emails, or send messages as part of planning.
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.

