agentleFS
Sign inStart free
LeadMagicLeadMagic/leadmagic-claude-plugin/skills/outbound-recipes/SKILL.md

outbound-recipes

Skill1 starsChanged 9 days agoMITView on GitHub

Composable, credit-aware LeadMagic MCP recipes for outbound — ICP list builds, account briefs, contact waterfalls, bulk hygiene, hiring-intent sweeps, job-change tracking, lookalike expansion, TAM mapping, and local-business lists. Use when designing or running a multi-step prospecting or GTM data workflow.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. LeadMagic/leadmagic-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository9 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 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.

  • 3

    Very specific

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

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

    Preflight for free: Call check_credit_balance first.

    line 12
  2. Very specific:

    More than 5 rows goes to a sheet or a bulk job: Never loop single-record tools per row.

    line 19
  3. Very specific:

    Close the loop: After a run, compare the actual spend from get_account_analytics (free) with the estimate.

    line 22
  4. Distinctive:

    Report only tool results: Never invent emails, phones, funding, ads, or job data.

    line 23

≈ “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

Outbound recipes

Each recipe below is a short chain of hosted MCP tools. Pick the one that matches the goal, and state its projected cost before spending.

Operating rules (every recipe)

  1. Preflight for free. Call check_credit_balance first. Call preview_cost before any composite or paid run, and state the projected spend.
  2. Plan-aware search.
    • On qualifying plans, browse search (search_people, search_companies, search_jobs) is credit-free, within the plan's rate limit and a fair-use cap of about 10M records a month (13,333 searches a day at 25-row pages, or the contract's limit if lower).
    • Elsewhere, browse search is metered.
    • Lookalikes, exports, and contact unlocks are always metered.
    • Details are on leadmagic.io/pricing. Never promise that search has no limit.
  3. Composites over chains. account_intel, enrich_contact, and find_decision_makers replace long chains of single tools.
  4. More than 5 rows goes to a sheet or a bulk job. Never loop single-record tools per row. See the sheets and bulk-enrichment skills.
  5. Confirmation tokens. Paid batch tools answer first with needs_confirmation and a confirmation_token. Show the summary, and resend with the token only after the user agrees.
  6. Cheapest first, stop at the first hit. Misses are usually free; retry only rows whose inputs changed.
  7. Close the loop. After a run, compare the actual spend from get_account_analytics (free) with the estimate.
  8. Report only tool results. Never invent emails, phones, funding, ads, or job data.

Recipes

#RecipeTools, in order
1ICP list buildsmall probe search_people / search_companies → refine filters → cursor-page the segment (market-search skill)
2Account briefpreview_cost → account_intel (switch off unneeded sections)
3Contact waterfall (one person)validate_work_email → find_work_email → b2b_profile_to_work_email → find_personal_email, stopping at the first hit; find_mobile_number only if the user asks for a phone
4Bulk list enrichmentpreview_cost → submit_detected_bulk_job (token) → watch_bulk_job_progress → get_bulk_job_rows / export_bulk_job
5List hygiene before a sendbulk email_validation via submit_detected_bulk_job, or an email_validation sheet column; segment into valid / risky / invalid
6Hiring-intent sweepone search_jobs call with company_domains (up to 25) + titles + posted_within, then get_company_hiring_signals for the shortlist
7Decision-maker mappingfind_decision_makers with 1–5 titles; set include_email_discovery only when emails are wanted
8Job-change champion loop≤5 contacts: detect_job_change; more: bulk job_change or a job_change_detector sheet column → find_work_email at the new domain for confirmed movers
9Lookalike expansionfind_lookalike_companies per seed → dedupe → optional search_companies fit filter → recipe 6 to rank
10TAM mapfilter permutations (industry × size × country) with small probe pages → segment matrix → full pages only for the segments the user picks
11Local-business listfind_local_leads (200 credits per keyword × location, charged up front, after the token) → bulk-job results
12Sheet pipelineget_sheet → add_sheet_columns → one run_sheet_column (sample_size 3 first on big fills) → read_sheet_rows → export_sheet_recipe

Output

  • The recipe used and the tools called
  • Credits: projected vs actual
  • The result set (or a file / sheet / job reference)
  • The next recipe in the chain, if any

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