agentleFS
Sign inStart free
jaredhhawkjaredhhawk/claude-skills/skills/outreach/SKILL.md

outreach

Skill0 starsChanged 8 months agoMITView on GitHub

Log networking outreach. Adds a row to the Outreach Log with contact, company, channel, and follow-up date.

18 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use evaluate and profile.

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.
  • NVIDIASkill

    evaluate

    Scores existing Sports Intelligence AVLM inference outputs with avlm/evals: MCQ accuracy (run_mcq_eval.sh, INFERENCE_DIR), open-ended LLM-as-judge scores (needs CLIENT_API_KEY for the configured judge endpoint), tennis category breakdowns, run comparisons, chance-level sanity checks and triage of mcq_results.json or llm_judge_results.json. Use when the user asks to score, evaluate, benchmark or compare predictions.jsonl from inference runs, or to explain a suspicious accuracy. Not for running inference, training, quantization, data preparation, or third-party API model inference: never open, list or run anything under avlm/evals/inference_3rdparty, including when the user asks for it; it is excluded from the release.

    Also in 4 projects that use this

  • 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

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Follow-up: today + 3 days (default)

    line 26
  2. Distinctive:

    If company or channel is missing, ask.

    line 52
  3. Distinctive:

    If they mention a response came back, offer to move to Responses table

    line 103

“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

/outreach - Log Networking Outreach

You are helping the user log outreach to their Outreach Log.

Behavior

  1. Parse input - User provides info in flexible format:
    • Structured: Company, Contact Name, Title, Channel
    • Natural: "Messaged Jane Doe at Zillow on LinkedIn"
    • Partial: "LinkedIn message to Redfin recruiter" (ask for missing info)
  2. Read the tracker at 02_Projects/Job Search/R - Outreach Log.md
  3. Add a new row to the "Active Outreach" table:
    • Date: today's date (YYYY-MM-DD)
    • Company: from input
    • Contact: name of person
    • Title: their job title (if known, otherwise "Unknown")
    • Channel: LinkedIn, Email, Referral, Cold Email, Twitter, etc.
    • Status: "Sent"
    • Follow-up: today + 3 days (default)
    • Notes: any extra context
  4. Update weekly count at the bottom: increment the X in "This Week: X/15 outreach target"
  5. Auto-update Goals.md:
    • Read 00_Dashboard/Goals.md
    • Increment "Outreach" count in "Weekly Targets" table
    • Calculate trend (🚨⚠️✅🔥)
    • Calculate response rate (if data available)
    • Calculate pairing rate (apps with outreach / total apps)
  6. Show weekly progress:
    • "This week: X/15 outreach, Y% response rate"
    • "Pairing tip: You're at Z apps, W outreach (P% pairing rate). Target: Pair every app."
  7. Confirm what was added

Input Parsing

Be flexible with input. All of these should work:

  • /outreach Zillow, Jane Doe, Head of Product, LinkedIn
  • /outreach messaged recruiter at Redfin on LinkedIn
  • /outreach cold email to CEO at startup via email
  • /outreach LinkedIn: John Smith, PM at Google

If company or channel is missing, ask. Contact name can be "Unknown" if not specified.

Table Format

The Active Outreach table has these columns:

| Date | Company | Contact | Title | Channel | Status | Follow-up | Notes |

Insert new rows right after the header row.

Follow-up Defaults

  • LinkedIn message: +3 days
  • Email: +3 days
  • Referral intro: +5 days
  • User can specify custom follow-up: "follow up Friday" or "follow up 2026-02-10"

Example Interaction

User: /outreach Zillow, Jane Doe, Head of Product, LinkedIn
Claude: Logged outreach:
  2026-02-10 | Zillow | Jane Doe | Head of Product | LinkedIn | Sent
  Follow-up: 2026-02-13

✅ Updated Goals.md: Outreach 1/15 this week

This week: 1/15 outreach, 0% response rate
Pairing: You're at 7 apps, 1 outreach (14% pairing). Target: Pair every app.

User: /outreach messaged someone at Redfin
Claude: Got it. What's their name and title? (or "unknown" if cold)
User: Unknown recruiter
Claude: Channel? (LinkedIn, Email, etc.)
User: LinkedIn
Claude: Logged:
  2026-02-10 | Redfin | Unknown | Recruiter | LinkedIn | Sent
  Follow-up: 2026-02-13

✅ Updated Goals.md: Outreach 2/15 this week

This week: 2/15 outreach ⚠️
Pairing: You're at 7 apps, 2 outreach (29% pairing). Target: 100%.

Conversation Style

  • Brief confirmations
  • Show the weekly progress toward 15 target
  • Don't over-explain
  • If they mention a response came back, offer to move to Responses table

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.

Check your setup, free