agentleFS
aksheywaksheyw/career-command-center-template/skills/outreach/SKILL.md

outreach

Skill1 starsChanged 4 months agoMITView on GitHub

Generate the right outreach message for any contact or company. Argument: [person name / company / context — e.g., 'alumni at Google' or 'recruiter at Stripe']

18 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use profile and triage.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • julienamorganSkill

    profile

    Researches the user's market, competitors, and competitive positioning to build a complete ICP profile. Shows findings for user approval before proceeding. Triggers: /profile, "research my market", "who are my competitors". Reads: ./gtm/company.md, ./gtm/icp.md. Writes: updates ./gtm/icp.md with competitive positioning. Standalone: yes (asks for domain if company.md missing).

    Also in 3 projects that use this

  • Google CloudSkill

    triage

    Gather context on a change or bug and plan the implementation.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Read ${CLAUDE_PLUGIN_ROOT}/skills/resume-customizer/references/career-tools.md for the 6 outreach templates and personalization guidance.

    line 10
  2. Distinctive:

    If the context is ambiguous, ask which situation applies before generating.

    line 25
  3. Very specific:

    Before writing anything, read the Contact and Last follow-up columns for this company in ${CLAUDE_PLUGIN_ROOT}/references/applications.md, …

    line 29
  4. Distinctive:

    Never use generic placeholders in the final output — fill them in or explicitly mark what the user needs to fill in manually before sending.

    line 48
  5. Very specific:

    Run the humanizer skill in this plugin on the drafted message before you output it.

    line 52
  6. Distinctive:

    Follow-up timing: [when to follow up if no response]

    line 62

“Common” is measured: kept by at least 6 in 10 of the 18 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

You are generating outreach messages for the user's job search. The user has described the target contact or company.

STEP 1: Read the outreach templates

Read ${CLAUDE_PLUGIN_ROOT}/skills/resume-customizer/references/career-tools.md for the 6 outreach templates and personalization guidance. Read ${CLAUDE_PLUGIN_ROOT}/references/YOUR_PROFILE.md for the user's name, title, phone, LinkedIn, portfolio, and key achievements.

STEP 2: Identify the right template

Select based on the user's input:

SituationTemplate
Cold LinkedIn connection requestTemplate 1 (300 char limit)
LinkedIn InMail to hiring managerTemplate 2
Cold email to recruiterTemplate 3
WhatsApp / direct message to warm contact for referralTemplate 4
Following up after no responseTemplate 5
Thank you after interviewTemplate 6

If the context is ambiguous, ask which situation applies before generating.

STEP 3: Check what was already sent

Before writing anything, read the Contact and Last follow-up columns for this company in ${CLAUDE_PLUGIN_ROOT}/references/applications.md, the tracker the track-application skill keeps. A follow-up that repeats a message already sent costs the relationship. If the row shows a recent touch, say so and confirm with the user before generating. If the tracker does not exist yet, or has no row for this company, say that there is no record of earlier contact and continue. Never treat the rows in applications.example.md as real history.

STEP 4: Personalize the message

Mandatory personalizations:

  • Replace [NAME] with the person's name if provided
  • Replace [COMPANY] with the actual company name
  • Replace [SPECIFIC] with something real about their work or company news if mentioned
  • Replace [ROLE] with the actual role if known
  • For Template 2 (InMail): include a specific company challenge or product reference
  • For Template 4 (warm DM): use first name only, keep casual tone
  • Pull the user's name, title, scope, achievements, phone, and LinkedIn from YOUR_PROFILE.md

Never use generic placeholders in the final output — fill them in or explicitly mark what the user needs to fill in manually before sending.

STEP 5: Voice pass

Run the humanizer skill in this plugin on the drafted message before you output it. An outreach draft that still reads as AI-written is not finished.

STEP 6: Output the message

Output the ready-to-send message clearly formatted, followed by:

  • Channel: [where to send this]
  • Length: [character / word count]
  • What to customize before sending: [any remaining gaps]
  • Follow-up timing: [when to follow up if no response]

For warm outreach, include phone from YOUR_PROFILE.md. For email / InMail, include LinkedIn from YOUR_PROFILE.md.

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.