Reads your own outreach log across a few runs: messages, replies, calls and job orders split by reason, channel and warm versus cold. It names what beat or missed expectations, what is too early to tell, and one change to test on the next run. No invented benchmarks.
Pipeline and ATScategory
No scriptsinstructions only, sends nothing
Any AI appupload, or copy and paste
Free, no signup
Upload the file to Claude, ChatGPT Business or Gemini Enterprise. On ChatGPT Plus, the free Gemini app or Grok, copy and paste it instead.
---
name: outreach-review
description: Reviews a few runs of outreach using only the recruiter's own counts: replies and calls by reason, channel and warm versus cold, what worked against what was expected, and one change to test on the next run, so the desk learns instead of changing five things at once. Use when a recruiter says "what's working", "review my outreach", "reply rates", "my BD isn't working", or after three or four runs.
license: MIT
metadata:
author: Work Insiders
version: "1.0"
pack: recruiter-outreach-pack
---
# Outreach review
You cannot improve outreach you do not count. You help a recruiter read their own numbers honestly and pick one thing to change.
## Input
The recruiter's own log for the last three or more runs: who was contacted, the reason used, channel, warm or cold, reply (yes, no, positive, negative), call booked, job order or candidate submitted. An export from their CRM, ATS or sequencing tool is fine.
## Count
Using only their data:
- Messages sent, replies, positive replies, calls booked, job orders or submittals.
- Split by reason type (open role signal, funding, candidate in hand, warm intro, other), by channel, and by warm versus cold.
- Note small numbers plainly: "3 replies from 12 is not a pattern yet".
## Read it
1. **What worked better than expected,** and the likely reason, as a guess to test, not a fact.
2. **What worked worse.**
3. **What you cannot tell yet** because the numbers are too small.
## One change
Pick one change for the next run: a reason type, a channel, a time of day, more warm intros, shorter messages. Say what you expect, what to count, and how many runs before looking again. Keep everything else the same.
## Output
```
OUTREACH REVIEW | runs [dates] | [n] messages
| Split | Sent | Replies | Positive | Calls | Job orders / submittals |
Better than expected: [ ]
Worse than expected: [ ]
Too early to tell: [ ]
Next run test: change [one thing]; expect [ ]; count [ ]; review after [n] runs
```
## Rules
- No industry benchmarks, invented averages or "typical reply rates". Use only the recruiter's own numbers.
- Never judge individual people who did not reply. Count messages, not persons.
- One change at a time.
The agency profile it reads (fill this in so it uses your real details)
# Agency profile
Fill this in once. Every skill in the pack reads it, so every output comes out in your agency's voice with your real terms. Delete any line you do not want the AI to use. Leave a line blank rather than guessing.
## Who we are
- Agency name:
- Recruiter name and title (for sign-offs):
- Phone:
- Mailing address (needed for US commercial email):
- Years in business:
- Specialties (roles we fill):
- Markets (cities, regions or "US remote"):
- Industries we know best:
## Terms
- Direct hire fee basis (e.g. % of first-year base):
- Guarantee period and type (free replacement / pro-rata refund / credit; conditions, e.g. fee paid within terms):
- Contract markup or bill rate approach:
- Exclusive or retained options:
- Payment terms (e.g. net 30 from start date):
- Introduction period (how long a candidate we introduce stays ours):
- Contract-to-hire conversion fee:
- Concessions we allow, and their limits:
## Proof points we can share
- Placements, time to fill, or retention figures we are happy to quote:
- Client names we may mention (only with permission):
## How we work
- ATS:
- Do we text candidates? (yes/no):
- Name the client in first candidate messages? (yes/no):
- Blind profiles: always / new clients only / never:
- Include pay expectation in submittals? (yes/no):
- Job post apply instructions:
- EEO statement:
## Words we never use
-
Yes. It is part of the free Work Insiders Recruiter Outreach Pack, MIT licensed, so you can edit and share it.
Does Outreach Review work in Gemini?
Yes. Upload it in Gemini Enterprise or drop the folder into Gemini CLI's skills folder. In the regular Gemini app, paste its instructions into a Gem.
Can I trust it with my data?
It has no scripts and sends nothing anywhere. Whatever you paste goes only to your AI assistant, under that assistant's own data terms, so remove candidate details you do not need first. It can still steer how the assistant answers, so read it before you use it.
Written by Work Insiders for agency recruiters. Fill in the agency profile before you use it so it never invents fees or proof points. How we make money.
