Agent skill · Data & Analytics

find-journalists

Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.

Elvis Sun613★ · +7/wk · 1 repos on radarProfile →
claude-codeMIT
Install
npx skills add elvisun/newsjack --skill find-journalists --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 29 KB
Bundled scripts: none
Path: skills/find-journalists/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 620 · +7 this week
Language: Go
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Guides the agent to build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. It uses the newsjack CLI (preferred) or the Medialyst MCP for search and enrichment, with a best-effort local mode as a last resort. The agent determines how returned data is organized, keeping the working list in local notes or a final Markdown table rather than in Newsjack. The goal is a list where every journalist has a real fit to the angle, not a padded volume.

How it works

The skill outlines a three-path workflow depending on tool availability: CLI mode (preferred), MCP mode (fallback), or Local mode (best effort). It instructs to start with campaign clarity, then perform wide research to find real fits, enriching the entire pool in a single call when possible, and finally score and prune to a tight, justified set. It specifies: check authentication, run a single enrich call for up to 500 URLs, then read the job result with enrich-job. If using MCP, the same fields apply but via MCP commands. It emphasizes not storing or managing hosted media lists and keeping the list locally. It also defines when to ask the user before connecting Medialyst and how to handle non-authenticated or unavailable paths.

When to use it

Use when the user asks to find journalists for a pitch or newsjack angle, to build or refine a journalist/media list, identify real bylines for a topic, or when a prior Newsjack output needs real recipient discovery.

What it can touch

The skill relies on the Newsjack CLI or Medialyst MCP. It references commands such as newsjack auth status, newsjack credits balance, newsjack login, and journalist enrichment workflows like newsjack journalists enrich and journalists enrich-job. It explicitly instructs to keep working lists locally and not to ask Newsjack to manage hosted lists. It mentions enrichment can accept up to 500 URLs in one call and describes passing URLs and a --pitch value, with --wait semantics. It also notes an optional local mode path if neither CLI nor MCP is available.

Caveats

The behavior depends on tool availability and authentication. Local mode is best-effort and requires user consent to connect Medialyst for richer data. The skill cautions against hosting list management by Newsjack and mandates focusing on real-fit journalism rather than raw volume. It does not guarantee deliverability or contact accuracy in local mode and requires use of the official paths for enrichment when possible.

From the SKILL.md

# Find Journalists You are **find-journalists**, the Newsjack skill that turns a story angle into a short, defensible list of journalists to pitch. You are not a contact scraper, a mass-email tool, or a hosted database manager. A media list earns its keep only when every name on it has a real reason to be there. ## Core Boundary Newsjack CLI is a data layer. It can search news and call Medialyst journalist enrichment. It does not create, inspect, update, share, store, or manage media lists. The model owns organization. Keep your working list in your own notes, a local scratch file, or the final Markdown table. Do not ask `newsjack` to make columns, views, share links, table actions, or hosted list IDs. If the user asks you to manage an existing hosted media list, explain that Newsjack does not own hosted media-list management. Ask for an export or the specific rows they want reviewed, then work locally from that evidence. ## Ground Rules Before doing anything, check whether `skills/ETHICS.md` and `skills/WHY-NOT-SPAM.md` exist. If they do, follow them. This skill works with journalist lists, so the anti-spam rules are not optional here. Read those rules for what they actually const

What's inside
Steps it walks through
  1. Core Boundary
  2. Ground Rules
  3. Modes
  4. What You Need To Start
  5. The Workflow: Wide Net, Then Tight Send
  6. 1. Get clear on the campaign
  7. 2. Research wide — pull the thread
  8. 3. Assemble the candidate pool
  9. 4. Enrich the whole pool in one call, then rank
  10. 5. Score each row
  11. 6. Send tight
  12. 7. Prune, then self-audit to saturation
  13. CLI Commands
  14. MCP Mode Commands
Commands it runs
newsjack auth status
newsjack credits balance
newsjack login
More from newsjack
All skills →
About this skill
What does the find-journalists skill do?

Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.

How do I install it?

Run `npx skills add elvisun/newsjack --skill find-journalists --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From elvisun/newsjack, a repository with 620 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going