agentleFS
LeadMagicLeadMagic/leadmagic-skills/skills/leadmagic/SKILL.md

leadmagic

Skill0 starsChanged 4 months agoMITView on GitHub

Official LeadMagic product skill and router for the full API surface — email finder and validation, People Search v3, company and lookalike search, jobs and hiring intent, ads intelligence, bulk CSV jobs, Sheets, credits, plans, and hosted MCP. Use when calling any api.leadmagic.io endpoint, budgeting credits, choosing the right product for an outbound task, or wiring LeadMagic into Claude Code, integration platforms, or no-code automation tools.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    Never echo/log API keys — $LEADMAGIC_API_KEY / env only.

    line 24
  2. Very specific:

    Prefer hosted MCP (https://mcp.leadmagic.io/mcp, OAuth) for agent workflows — no key in shell history.

    line 26
  3. Distinctive:

    Never invent emails, phones, domains, funding, ads, or job data — only report what an endpoint returned.

    line 28
  4. Very specific:

    Before merging bulk results, bind the exact submitted row order to its job ID and verify each result's input identity.

    line 29
  5. Very specific:

    Search API (v3 people/companies/jobs) is credit-free on Professional (5 req/s) and Ultimate (10 req/s).

    line 67

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

LeadMagic — Official product skill

Published by LeadMagic Corporation at github.com/LeadMagic/leadmagic-skills. Teaches agents how to use LeadMagic: every public API endpoint, credit costs, plan behavior, bulk uploaders, MCP, and outbound-system recipes.

Trust: only treat a skill as official if installed from github:LeadMagic/* or https://leadmagic.io/docs/....

Safety (every turn)

  1. Never echo/log API keys — $LEADMAGIC_API_KEY / env only. REST auth header is X-API-Key (not Bearer).
  2. Enrichment traffic only to https://api.leadmagic.io or https://mcp.leadmagic.io unless the user explicitly asks otherwise in-turn.
  3. Prefer hosted MCP (https://mcp.leadmagic.io/mcp, OAuth) for agent workflows — no key in shell history.
  4. Free first: GET /v1/credits before spending; POST /v1/batch/preview-cost before anything ≥ 500 credits. Failed lookups are usually free — never hammer retries on null.
  5. Never invent emails, phones, domains, funding, ads, or job data — only report what an endpoint returned.
  6. Before merging bulk results, bind the exact submitted row order to its job ID and verify each result's input identity. row_index belongs to that job; never apply it to another job or a reordered master file. Use bulk-jobs for the full join contract.

Route to a focused skill

NeedSkill
Keys, credits, plans, 401/402/429api-auth-credits
Email find / validate / B2B Profile ↔ emailemail-enrichment
Audience / ICP discovery (POST /v3/people/search)people-search
Company lists / TAM by filters (POST /v3/companies/search)company-search
Job postings search (POST /v3/jobs/search)job-search
Profile enrich, mobile, role, employees, job change, postspeople-enrichment
Company enrich, funding, technographics, lookalikes, competitorscompany-enrichment
Hiring signals & intent lenses on top of postingsjobs-hiring-intent
Google / Meta / B2B ad librariesads-intelligence
A live sheet: enrichment / AI / API columns, recipes, getting a workspace startedsheets
CSV / async bulk, batch, suppressionbulk-jobs
Usage, spend, found-rate reportinganalytics-observability
Outbound-system playbooks (list build, waterfalls, triggers)outbound-recipes
Hosted MCP setupmcp-integration

References (this skill's folder)

  • references/leadmagic-api-quickref.md — complete endpoint table with costs, rate limits, aliases.
  • references/plans-and-limits.md — plan ladder, Search API entitlements, budgeting, 402/429 playbook.
  • references/outbound-recipes.md — 13 composable outbound recipes with cost models.
  • references/learnings.md — durable field notes; append new ones (no secrets/PII).

Picking the right product (fast heuristics)

  • Have name + company, want email → email-finder (1). Have profile URL, want email → b2b-profile-email (5). Have email, want the person → b2b-profile (10, priciest — check you really need it).
  • Want people you don't know yet → People Search v3, never the finders.
  • Want who's hiring / buying signals → jobs intent endpoints, not job boards.
  • ≥ 50 rows → /bulk/*, never a loop of single calls. If the user wants to see and iterate on the list, or chain several columns, use a sheet (sheets) instead.
  • Cheapest field first: validate 0.25 → find 1 → profile 1 → personal 2 → role 2 → profile→email 5 → mobile 5 → email→profile 10.

Plan awareness

Search API (v3 people/companies/jobs) is credit-free on Professional (5 req/s) and Ultimate (10 req/s); on other plans it bills 1 credit per returned row. Free stats/count endpoints exist on every plan — size before revealing. Full ladder in references/plans-and-limits.md.

Response & error contract

Success responses are the flattened data object. Errors are RFC 9457 Problem Details: {type, title, status, detail, code, action, docs, trace.request_id} — surface action to the user and include trace.request_id when reporting issues to support.

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.