CtrlK
BlogDocsLog inGet started
Tessl Logo

write-openers

Use when drafting evidence-backed opening lines or subject lines for an eligible contact.

65

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/write-openers/SKILL.md
SKILL.md
Quality
Evals
Security

Write Openers

Purpose

Draft factual openers and subject lines with an explicit fact-to-copy trace. Preserve account-versus-person boundaries and uncertainty.

Required inputs

  • Independently verified ELIGIBLE status and reason
  • Supplied opt-out or stop-contact status
  • Recipient, channel, and requested option count
  • Approved account or contact facts with date, source type, and citation
  • Approved offer facts, voice rules, and prohibited claims
  • Contactability permission and current channel rules for send readiness

Treat only eligibility and opt-out status as offline-drafting gates. Mark other missing inputs and do not invent them.

Workflow

  1. Check eligibility and opt-out status. Return STOP with no copy for an opt-out, stop request, or ineligible contact. Return NEEDS VERIFICATION with no copy only when either gate is missing or unverified.
  2. Build a fact ledger. Separate account facts from verified personal knowledge and record date, source type, citation, and uncertainty.
  3. Draft the requested number of concise opening lines and subject lines. Describe company activity at the account level unless direct evidence ties it to the recipient.
  4. Reject Re: or Fwd: unless accurately continuing a supplied thread. Reject fake familiarity, praise, urgency, clickbait, unsupported outcomes, vague personalization, and first-person discovery phrases such as "I saw" or "I noticed" without supplied provenance. Use exact dates instead of unsupported relative recency.
  5. Map every material phrase in each option to a fact-ledger entry. Revise or reject any phrase without support.
  6. Assess readiness separately. Missing contactability permission, current channel rules, or human approval requires NOT READY TO SEND but does not suppress offline drafts.

Output format

Return drafting-gate status and reason first. When both gates pass, return:

  • Send readiness and missing items
  • DRAFT FOR HUMAN REVIEW
  • Evidence ledger with IDs, facts, dates, source types, citations, and uncertainty
  • Opening lines with fact IDs and boundary notes
  • Subject lines with fact IDs
  • Rejected options with reasons

For STOP or NEEDS VERIFICATION, return the reason and no copy.

Guardrails

  • Never invent facts, familiarity, discovery provenance, praise, urgency, intent, outcomes, credentials, consent, contactability, citations, or personal involvement.
  • Never use deceptive reply or forwarding prefixes.
  • Never target from protected traits or unnecessary sensitive data.
  • Label all copy DRAFT FOR HUMAN REVIEW; eligibility never proves permission to send.
  • Never browse, send, schedule, use credentials, or mutate an external system.

Quality check

Confirm drafting gates passed; every option traces to supplied evidence; account activity is not attributed to the person; uncertainty and readiness are explicit; no deceptive prefix or unsupported tactic remains; and no external action is implied.

Example invocation

Use write-openers for eligible Avery Lin with supplied no-opt-out status and dated Meridian Forge evidence. Return three traced opener and subject options as offline drafts.

Repository
llaskin/AI-SDR-Skill-Pack
Last updated
First committed

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.