agentleFS
cobusgreylingcobusgreyling/grok-bot-templates/skills/source-talent/SKILL.md

source-talent

Skill14 starsChanged 3 months agoMITView on GitHub

Paste this into Grok Bot after a successful run: Save the process we just used as a skill called “Source Talent”. A useful skill states the six fields from Skills and routines. A named role needs up to twenty evidenced candidates, unsent outreach, and scheduling preparation — with no contact. Every listed candidate has evidence for the must-haves or a skip reason. Drafts are labeled DRAFT. No message, InMail, or invite was sent. Review list of up to 20 candidates…

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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
  1. Distinctive:

    Search only approved sources.

    line 26
  2. Distinctive:

    Stop at 20. If fewer qualify, say so rather than padding unlabeled maybes.

    line 27
  3. Distinctive:

    Every listed candidate has evidence for the must-haves or a skip reason.

    line 33
  4. Distinctive:

    Do not contact anyone. Do not send outreach or connection requests.

    line 43

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Source Talent

Paste this into Grok Bot after a successful run:

Save the process we just used as a skill called “Source Talent”.

A useful skill states the six fields from Skills and routines.

1. When to use it

A named role needs up to twenty evidenced candidates, unsent outreach, and scheduling preparation — with no contact.

2. Required inputs and access

  • Role description and must-have criteria
  • ATS access when connected, for exclusions
  • Approved sourcing tools (LinkedIn and others the owner authorized)
  • Style examples for outreach if attached
  • Calendar free/busy for suggested windows

3. Sequence of work

  1. Confirm the role and must-haves. If they are missing, ask once and stop.
  2. Exclude anyone already in the ATS. If the ATS is unavailable, mark "ATS not checked".
  3. Search only approved sources. Collect matches that meet must-haves.
  4. Stop at 20. If fewer qualify, say so rather than padding unlabeled maybes.
  5. For each match, cite evidence against every must-have.
  6. Draft outreach in the owner's voice. Propose intro windows from free/busy. Do not send or book.

4. How to validate the result

Every listed candidate has evidence for the must-haves or a skip reason. Drafts are labeled DRAFT. No message, InMail, or invite was sent.

5. What to return

Review list of up to 20 candidates with evidence, skips, drafts, and suggested windows. Action log of sources searched.

6. What requires approval

Do not contact anyone. Do not send outreach or connection requests. Do not book interviews. Do not create ATS records unless later named.

Type / in the composer to reference a saved skill. If it does not appear, open Settings → Plugins → Yours and enable it for this Bot.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.