How do I install the Job Posting Intent skill?

Run npx skillmds@latest add robomotionio/job-posting-intent in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Job Posting Intent safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Job Posting Intent?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Job Posting Intent free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Job Posting Intent?

robomotionio (@robomotionio) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Job Posting Intent by robomotionio — Agent Skill

Name: Job Posting Intent
Author: robomotionio

Job Posting Intent

Detect buying intent from job postings — when a company posts a role in your problem area they've allocated budget and acknowledged the problem. Finds those companies, aggregates postings into a per-company signal strength, then (agent) qualifies vs. ICP and extracts personalization context + decision-maker suggestions. Outputs leads; does not do outreach.

robomotionio a1a1dda 5 files · 14.0 KB Updated Sep 17, 2026

File contents

Job-Posting Intent

The strongest signal source in signal-detection-pipeline. Source postings for intent titles, aggregate them per company into a transparent signal strength, then qualify and add outreach context.

When to use

"Find companies hiring for [role] — that's a budget signal for us."
"Detect intent from job postings in [problem area]."

How to run

Step 1 — source postings (per intent title)

python3 ${SKILL_DIR}/scripts/jobs.py \
  --query "Data Engineer" --location "United States" \
  --num-results 25 --output ${WORKSPACE}/jobs_de.json
# repeat per intent title, or pass several and merge in-agent

With APIFY_API_TOKEN this uses the LinkedIn/Indeed actors (estimate cost first, cap --num-results); without it, the keyless site: degrade.

Step 2 — aggregate into per-company signals

python3 ${SKILL_DIR}/scripts/aggregate_intent.py \
  --input ${WORKSPACE}/jobs_de.json \
  --intent-titles "data engineer,ml engineer" \
  --output ${WORKSPACE}/companies.json

Signal strength = posting count × intent-title diversity × recency boost, sorted desc. This is a transparent rule you can override.

Step 3 — qualify & contextualize (you, the agent)

For each company in companies.json: set icp_verdict vs. ICP; extract personalization from the posting text; suggest a decision_maker (invoke company-contact-finder with APOLLO_API_KEY); and write an outreach_angle. Then export the qualified set.

Outputs

companies.json — [{company, posting_count, matched_intent_titles, signal_strength, postings[], icp_verdict, decision_maker, outreach_angle, personalization}]. Outputs leads only — no outreach.

Credentials / env

Required: none — jobs.py sources postings keylessly.
Optional: APIFY_API_TOKEN (LinkedIn/Indeed job actors — richer, structured jobs; estimate cost first); APOLLO_API_KEY (decision-maker suggestions via company-contact-finder); ANTHROPIC_API_KEY only if LLM qualification isn't platform-provided.

Notes & edge cases

Always estimate Apify cost before running the actor; cap jobs-per-title.
Signal strength scales with count + recency + title diversity per company.
Dedup companies posting the same role across boards (jobs.py dedups postings).
Outputs leads only — feed qualified companies to outreach skills downstream.

---name: job-posting-intentdescription: Detect buying intent from job postings — when a company posts a role in your problem area they've allocated budget and acknowledged the problem. Finds those companies, aggregates postings into a per-company signal strength, then (agent) qualifies vs. ICP and extracts personalization context + decision-maker suggestions. Outputs leads; does not do outreach.---# Job-Posting IntentThe strongest signal source in `signal-detection-pipeline`. Source postings for intenttitles, aggregate them per company into a transparent signal strength, then qualify andadd outreach context.## When to use- "Find companies hiring for [role] — that's a budget signal for us."- "Detect intent from job postings in [problem area]."## How to run### Step 1 — source postings (per intent title)```bashpython3 ${SKILL_DIR}/scripts/jobs.py \ --query "Data Engineer" --location "United States" \ --num-results 25 --output ${WORKSPACE}/jobs_de.json# repeat per intent title, or pass several and merge in-agent```With `APIFY_API_TOKEN` this uses the LinkedIn/Indeed actors (estimate cost first, cap`--num-results`); without it, the keyless `site:` degrade.### Step 2 — aggregate into per-company signals```bashpython3 ${SKILL_DIR}/scripts/aggregate_intent.py \ --input ${WORKSPACE}/jobs_de.json \ --intent-titles "data engineer,ml engineer" \ --output ${WORKSPACE}/companies.json```Signal strength = posting count × intent-title diversity × recency boost, sorted desc.This is a transparent rule you can override.### Step 3 — qualify & contextualize (you, the agent)For each company in `companies.json`: set `icp_verdict` vs. ICP; extract `personalization`from the posting text; suggest a `decision_maker` (invoke `company-contact-finder` with`APOLLO_API_KEY`); and write an `outreach_angle`. Then export the qualified set.## Outputs`companies.json` — `[{company, posting_count, matched_intent_titles, signal_strength,postings[], icp_verdict, decision_maker, outreach_angle, personalization}]`. Outputs leadsonly — no outreach.## Credentials / env- **Required:** none — `jobs.py` sources postings keylessly.- **Optional:** `APIFY_API_TOKEN` (LinkedIn/Indeed job actors — richer, structured jobs; estimate cost first); `APOLLO_API_KEY` (decision-maker suggestions via `company-contact-finder`); `ANTHROPIC_API_KEY` only if LLM qualification isn't platform-provided.## Notes & edge cases- Always estimate Apify cost before running the actor; cap jobs-per-title.- Signal strength scales with count + recency + title diversity per company.- Dedup companies posting the same role across boards (jobs.py dedups postings).- Outputs leads only — feed qualified companies to outreach skills downstream.

Frequently asked questions