agentleFS
HimadriTryingHimadriTrying/ai-job-search-agent/.claude/skills/outreach-drafter/SKILL.md

outreach-drafter

Skill1 starsChanged 3 months agoMITView on GitHub

Write a personalized intro-request or outreach message for a specific warm path. Grounded only in real facts; runs the honesty gate. On demand — tone needs human judgment.

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
  1. Distinctive:

    Keep it human. A generic "I'd love to connect" performs worse than nothing.

    line 23
  2. Distinctive:

    Read them before drafting and check the draft against them afterwards:

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

outreach-drafter

Precedent / mapping

The warm-intro half of the gap; Lenny's finding-mentors-sponsors reframed as the warm-intro problem.

Inputs

A specific path from network-mapper, career_facts.yaml, profile/03-writing-style.md, the target role.

Flow

  1. Draft a short, specific message — reference the real connection, the real role, one true reason it fits. No flattery padding.
  2. Honesty gate on the draft (it asserts facts about the user).
  3. Present 1-2 variants. The user sends it — never you.

Keep it human. A generic "I'd love to connect" performs worse than nothing.

The user's own rules

Read them before drafting and check the draft against them afterwards:

python scripts/learned_rules.py brief --scope outreach
python scripts/learned_rules.py check <draft> --scope outreach

Outreach is where a standing "never say that" is most likely to have been stated and most costly to forget, because the message goes to a real person in the user's own network. If they correct a draft, run learn before moving on.

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.