agentleFS
sree-datasree-data/job-search-agent/.claude/skills/draft-outreach/SKILL.md

draft-outreach

Skill0 starsChanged 2 months agoMITView on GitHub

Write the LinkedIn connection note, LinkedIn message, and cold email for one contact, in Alex's voice, and log them as drafts. Usage /draft-outreach <contact id>

12 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before writing, read: CLAUDE.md writing rules and audience angles, profile/background.md, profile/resume.md, profile/voice-samples.md, the …

    line 10
  2. Very specific:

    Write three pieces to drafts/<contact-id>-<lastname>.md:

    line 12

“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “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

Draft outreach

Argument: a contact id from pipeline/contacts.csv (or a name if the id is unknown).

Before writing, read: CLAUDE.md writing rules and audience angles, profile/background.md, profile/resume.md, profile/voice-samples.md, the contact's row and its shared_hook, the linked job row, and drafts/research/<company>.md if it exists (run /research-company first if it doesn't).

Write three pieces to drafts/<contact-id>-<lastname>.md:

A. LinkedIn connection note (under 200 characters)

One sentence. The hook, then why you want to connect. No pitch.

B. LinkedIn message (60 to 100 words)

For after they accept, or as an InMail. Structure: hook about them (1 sentence) → one proof point about Alex that matches (1 to 2 sentences) → one small ask (1 sentence). Sign off with just "Alex".

C. Cold email (under 120 words)

Subject line under 7 words, specific. Same structure as B but can carry one extra detail. Include Alex's LinkedIn URL in the signature. Only write this if the contact has a published email or Alex says he has one.

Then, under the drafts, add:

  • Why this angle: two lines on what you anchored to and which proof point you chose.
  • Sponsorship: whether you mentioned it, per targets/criteria.md, and if so where.
  • Send timing: best day and time in the contact's time zone (Tuesday to Thursday, 8 to 10am local is a safe default).

Finally, append one row per piece to pipeline/outreach.csv with touch 1, status draft, and the draft file path.

Self-check before you save. Rewrite if any of these are true:

  • The first sentence is about Alex instead of them.
  • It contains a banned phrase from CLAUDE.md.
  • It claims something not in profile/.
  • It would work unchanged for a different person at a different company. That means it's a template, and templates get ignored.
  • It sounds more polished than the voice samples. Rough and specific beats smooth and generic.

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.