---
name: jd-and-sourcing-brief
description: Draft the job description and sourcing brief from past successful hires, not a blank page. Use this skill when: New req opened — Hiring manager submits the intake form.
---

# Draft a calibrated JD and sourcing brief

Goal: draft a calibrated JD and sourcing brief from past-hire signal, not a blank page.

Connected tools this skill uses: notion, googlesheets, gmail, slack.

## When to use

- New req opened — Hiring manager submits the intake form.
- Or when the user asks directly to draft a calibrated JD and sourcing brief from past-hire signal, not a blank page.

## Method

Draft the job description and sourcing brief for the {{role}} req.

1. Read the intake form for {{role}}: level, team, must-haves, and the
   hiring manager's notes.
2. Pull the last {{lookback_hires}} successful hires at this level or role
   from {{ats_or_sheet}} and note what their JDs and sourcing criteria had
   in common.
3. Draft the JD: outcomes-based responsibilities, must-have vs. nice-to-have,
   leveled against comparable roles.
4. Run the JD through the bias-language check: flag and rewrite any
   gendered, exclusionary, or unnecessarily jargon-heavy phrasing before it
   ships.
5. Draft the sourcing brief: 2-3 target company or profile archetypes,
   channels to search, and a starter Boolean string.
6. Post the JD and sourcing brief to {{delivery_channel}} for the hiring
   manager's sign-off and save both to `hiring/{{role}}-{{date}}/`.

Never post the JD to a job board or send the sourcing brief to a sourcer
until the hiring manager approves it in {{delivery_channel}}.

## Past-hire calibration

Pull the JD text and sourcing criteria from the last successful hires in this role before any draft starts.

## Method
1. Read the intake form for the open role: level, team, and must-haves.
2. Query {{ats_or_sheet}} for the last {{lookback_hires}} successful hires at this level or role.
3. Pull each hire's final JD text and the sourcing criteria used to find them.
4. Extract the responsibilities, must-haves, and channels that repeat across those hires.
5. Flag anything that changed since the last calibration, such as a new must-have or level bar.
6. Write a short calibration note per role family and save it to memory.
7. Hand the note to the JD and sourcing-brief drafting steps.

## Rules
- Draw only from closed, successful hires — never an open req or a rejected candidate.
- Default lookback is {{lookback_hires}} hires (set on first run, then stored in memory).
- Refresh the calibration note every time a new hire closes in this role family.
- If the ATS record for a past hire is incomplete, flag the gap instead of guessing its content.

## Output
A calibration note: a short bullet list of common responsibilities, must-haves, and sourcing channels, with the source hires it drew from.

## Bias-language check

Screen a drafted job description for language that narrows or discourages qualified candidates, and fix it — don't just flag it.

## Method
1. Read the full JD draft before it goes anywhere else.
2. Scan for gendered terms, such as "rockstar," "he/she," or aggressive competitive language.
3. Scan for unnecessary requirements: a degree, a years-of-experience minimum, or a tool not actually needed day one.
4. Scan for jargon walls — internal acronyms or insider phrasing an outside candidate can't parse.
5. Rewrite every flagged instance in place with neutral, outcomes-based language.
6. Re-read the rewritten draft once to confirm no flagged pattern remains.
7. Return the clean draft, plus a short list of what was changed and why.

## Rules
- Rewrite every flag before the JD ships — never hand back a flag-only list for someone else to fix.
- Treat the three categories (gendered terms, unnecessary requirements, jargon walls) as the minimum scan, not the ceiling.
- Keep the role's genuine must-haves; cut only what isn't actually required for day one.
- Never soften a real requirement to pass the check — flag it as a policy question instead of silently dropping it.

## Output
The rewritten JD text, plus a change log: each flagged phrase, its category, and its replacement.

## Sourcing brief format

Turn the calibrated JD into target profiles, channels, and search strings for a sourcer.

## Method
1. Read the finished JD and the past-hire calibration note for this role.
2. Draft 2-3 target profile archetypes: company type, title, and years of relevant experience.
3. List the channels most likely to surface each archetype, such as LinkedIn, niche boards, or the referral pool.
4. Write a starter Boolean search string per archetype, using the JD's must-haves as keywords.
5. Note any deliberate exclusion, such as a competitor to avoid poaching from, if the hiring manager flagged one.
6. Package the brief as one page, mapped one section per archetype.
7. Attach the brief to the JD for the same sign-off pass.

## Rules
- Ground every archetype in the past-hire calibration note, not a generic persona.
- Keep the brief to one page — a sourcer should not need to read past it to start.
- Never send the brief to a sourcer before the hiring manager signs off in {{delivery_channel}}.
- Update the Boolean strings if the JD changes after sign-off.

## Output
A one-page sourcing brief: 2-3 target archetypes, their channels, and a starter Boolean string per archetype.

## Recurring jobs

This skill pairs with scheduled jobs. Offer to set each one up; only create the ones the user approves:

- New req intake watch (Daily poll of the intake form for newly opened reqs) — https://eluu.ai/cookbook/jd-and-sourcing-brief/jobs-setup/new-req-intake-watch.md