Skip to content
SkillMixed1,409 tokens in use

Proactive Helpfulness

Reconciles email, chat and CRM evidence into a ranked list of lead follow-ups and owed promises, with drafts held for approval and a verified funnel report.

3,862 stars on the repository MIT Licenseericosiu/ai-marketing-skills · proactive-helpfulness
npx skills add ericosiu/ai-marketing-skills -s proactive-helpfulness
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Proactive Helpfulness costs

25tokens idle
1,409tokens in use
2,666tokens, 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 Mixed

Script-ledMixedModel-led

Scripts do part of the work and the model's judgement does the rest.

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

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
  • Structure25/25
  • Examples6/15
  • Output10/15
  • Size15/15
  • Resources7/15

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

Proactive Helpfulness walks an agent through an eight-step review of a set of relationships, such as an event’s contacts. It resolves identities, reads the latest conversation across channels, qualifies the real opportunity, ranks next actions and prepares one consolidated batch for the owner to approve.

Success is useful meetings, partnerships and opted-in hires, and the skill grants no authority to send, spend or write to a CRM. An optional offline Node script counts contacted, responded and booked people from normalized event records.

What You Get

  • A short ranked list with person, company, exact need and source, size evidence and unknowns, fit assessment, next action, owner and due date
  • A separate waiting-on-others list and prep notes for booked calls
  • Drafts and one consolidated approval batch with exact recipients, channel and content
  • A private relationship record format that keeps source IDs, promises and who owes whom
  • A funnel of unique people contacted, responded and booked, with coverage limits shown beside the numbers

Common Use Cases

  • Following up with contacts after a conference or event without chasing people who already replied elsewhere
  • Tracking introductions owed to others and owed to you
  • Reporting a campaign funnel with identities resolved across email, chat and meetings

What Makes It Unique

Next-action priority and opportunity confidence stay as two fields, so an owed introduction can come first even when its revenue is unknown. The skill separates prepared, approved, attempted, sent and verified, never retries an uncertain send before a readback, and respects opt-outs across channels. Funnel counts use unique people and verified events, and a zero denominator is reported as undefined.

Under The Hood

The skill is mostly instructions with one reference file and one small Node script that does offline arithmetic on a JSON list of events and reads no accounts. The agent is told to search email, messaging, CRM, calendar and meeting notes that the user has connected, and to read public sources, so it reaches those services through whatever integrations exist. It prepares drafts and records but grants no authority to send, spend, share, write to a CRM or enable automation; those need the user’s approval. When run from the full repository it may call the update-check and telemetry helper scripts, which respect the user’s consent settings.

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