outbound-recipes
Skill0 starsChanged 4 months agoMITView on GitHub
Composable LeadMagic recipes for building outbound systems — ICP list building, waterfall enrichment, bulk CSV pipelines, hiring-intent trigger sweeps, job-change champion tracking, competitor ad monitoring, lookalike expansion, TAM mapping, and list hygiene. Use when designing or running any multi-step outbound, prospecting, or GTM data workflow with LeadMagic.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- LeadMagic/leadmagic-claude-plugintheir own version, first seen Oct 13, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- LeadMagic/leadmagic-claude-plugin★ 1same 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 repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- llms.txtllms.txt
- ads-intelligenceSkill
- analytics-observabilitySkill
- api-auth-creditsSkill
- bulk-jobsSkill
- company-enrichmentSkill
- company-searchSkill
- connect-leadmagicSkill
- email-enrichmentSkill
- job-searchSkill
- jobs-hiring-intentSkill
- leadmagicSkill
- mcp-integrationSkill
- people-enrichmentSkill
- people-searchSkill
- sheetsSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 42
Cheapest-first: never run a pricier product when a cheaper one satisfies the channel (leadmagic skill has the ladder).
- Very specific: line 45
Close the loop: after a run, report actuals from free /v1/analytics/day/{date} vs the estimate.
- Distinctive: line 46
Never invent emails, phones, funding, ads, or job data.
≈ “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.
Files
LeadMagic — Outbound system recipes
Thirteen credit-aware, composable recipes live in the leadmagic skill's references — read skills/leadmagic/references/outbound-recipes.md for full request bodies and cost models. This skill is the index and the operating rules.
Recipe index
| # | Recipe | Core endpoints | Cost model |
| 1 | ICP list build | /v3/search/stats (free) → /v3/people/search | 1/row (free on Pro/Ultimate) |
| 2 | Account brief | company-search + funding + tech + public jobs research | ~8–12/account |
| 3 | Waterfall contact enrichment | validate → find → profile→email → personal → mobile | 0.25–5, cheapest-first |
| 4 | Bulk CSV enrichment | /bulk/validate → /bulk/submit → poll → download | per successful row |
| 5 | List hygiene | bulk email_validation before every send | 0.25/row max |
| 6 | Hiring-intent trigger sweep | /v3/jobs/search + evidence review | plan-dependent |
| 7 | Decision-maker mapping | role-finder first; /v3/people/employees only for exploratory lists | 2–6/account |
| 8 | Job-change champion loop | job-change-detector → profile → email-finder | 3/contact/sweep |
| 9 | Competitor ads monitor | google/meta/b2b ads search → details | 1/search + 2/detail |
| 10 | Lookalike expansion | /v3/companies/lookalike → filter → rank | 5/seed + 1/row |
| 11 | TAM map | free stats permutations → selective reveal | ~0 to size |
| 12 | Speed-to-lead inbound enrich | validation + company-search + role-finder | ~2–4/lead |
| 13 | Signal-stacked cold sequence | composes 2/3/5/6/7/8/9/10 | budgeted per stage |
Operating rules (every recipe)
- Preflight free:
GET /v1/credits; preview withPOST /v1/batch/preview-costwhen ≥ 500 credits; state projected spend before running. - Plan-aware sizing: on Basic–Growth, size searches with free stats endpoints first; on Professional/Ultimate, v3 searches are credit-free within 5/10 req/s.
- Cheapest-first: never run a pricier product when a cheaper one satisfies the channel (
leadmagicskill has the ladder). - Bulk ≥ 50 rows. Poll ≥45s. Misses are free — retry only changed inputs.
- Hygiene before send (recipe 5) — always.
- Close the loop: after a run, report actuals from free
/v1/analytics/day/{date}vs the estimate. - Never invent emails, phones, funding, ads, or job data; only report endpoint results.
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
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.