Skip to content
SkillModel-led1,953 tokens in use

Event Research Follow-Up

Research events, qualify evidence-backed leads and carry out only approved follow-up, with delivery ledgers, scheduling rules and reply outcome tracking.

3,862 stars on the repository MIT Licenseericosiu/ai-marketing-skills · event-research-follow-up
npx skills add ericosiu/ai-marketing-skills -s event-research-follow-up
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Event Research Follow-Up costs

28tokens idle
1,953tokens in use
7,364tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter8/15
  • Structure17/25
  • Examples6/15
  • Output15/15
  • Size15/15
  • Resources9/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity88
  • Maintenance44
  • Community56
  • Maturity28
  • Momentum40

Event Research Follow-Up guides an agent through the work around business events: screening events and attendee rosters against your scope, grouping people by operating company, qualifying leads on evidence, drafting follow-up that fits the real relationship, and executing outreach only inside an explicit approval.

Five reference files cover lead collection and qualification, durable event state, approved outreach execution across email, LinkedIn and phone, host conversations and expansion tests, and reply and commercial outcome review. The skill grants no authority to send, spend, register, write to a CRM or schedule; those need your approval for the exact cohort, copy, channel and cap.

What You Get

  • An event priority table and a distinct-company shortlist with source and coverage gaps
  • Qualification records with company size ranges, evidence URLs, dates and currencies
  • Follow-up drafts matched to warm or cold relationships, with day +5 and +10 drafts on request
  • An append-only action ledger with scheduled, sent, delivered, read and failed states and receipts
  • A reply category table and an evidence-based outcome ledger
  • A local learning file of misses and corrections

Common Use Cases

  • Screen a directory of upcoming events and pick the ones worth attending
  • Turn photos, notes and a roster from an attended event into qualified leads
  • Schedule approved emails across time zones and verify what was sent
  • Review replies and decide which opportunities are real
  • Run a five-company pilot and measure results before expanding

What Makes It Unique

Its rules are about restraint and proof. Scheduled is never sent, sent is never delivered, an ambiguous send is never a reason to resend, a research approval never authorizes outreach, and a reply is never counted as pipeline or revenue. Costs and credits go in a cumulative spend ledger that stops at the approved cap.

Under The Hood

It is prompt-led with five reference documents and no scripts of its own. Depending on what you approve, the agent reads exports and event pages through your own browser session, may call an enrichment provider or an optional evaluator, and may create email drafts or scheduled sends, LinkedIn connection requests and phone messages through your connected accounts. It writes JSON and CSV records and a learning log to private storage you choose, and it runs the repository’s telemetry helper only when the full repository is present, never enabling remote telemetry.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers