All skills
simota avatar

/voice

@c805268
by shingo imotasimota/agent-skills85 stars
15

Collecting user feedback via NPS surveys, review analysis, sentiment analysis, feedback classification, and insight extraction reports. Use when establishing feedback loops.

Use this Skill: https://skilld.dev/gh/simota/agent-skills/voice

This session only. Nothing lands on disk.

referenceexit-survey.md

≈325 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Exit Survey Delta

Purpose: Voice churn-survey data and handoff contract. Generic question lists are model-known.

Collection Rules

  • Trigger after cancellation is confirmed; never block cancellation or require free text.
  • Keep a short product-specific reason taxonomy plus other and prefer_not_to_say.
  • Randomize reason order when ordering bias matters and version the taxonomy.
  • Separate survey response, save-offer behavior, and marketing-contact consent.
  • Do not infer the primary churn cause from a selected reason alone; combine with behavior, billing, support, and follow-up evidence.

Minimal Record

response_id, account/user pseudonymous key, cancellation timestamp,
reason_code, optional verbatim, segment/plan/tenure, touchpoint,
save_offer_shown/accepted, taxonomy_version, consent flags

Apply the product's privacy, retention, and access controls. Avoid storing unnecessary personal text.

Required Output

Report response rate, reason distribution with sample sizes, segment/tenure differences, verbatim themes, save-offer outcomes, missingness, confidence limits, and the distinction between stated and observed causes. Route product themes to Spark, retention mechanisms to Growth, instrumentation gaps to Pulse, and qualitative follow-up to Field.

Source: SKILL.md on GitHub

1 warning13d5 checks · Risk SAFE
  • Gen Agent Trust Hub14d

    The skill is designed for customer feedback analysis and follows industry-standard metrics (NPS, CSAT, CES) while prioritizing data privacy through pseudonymization. It includes security-focused logic to detect synthetic (AI-generated) feedback and bot patterns. However, like any agent that processes external user-supplied text from reviews and support tickets, it possesses an inherent surface area for indirect prompt injection.

  • Socket13d

    No alerts

  • Snyk14d

    Risk: MEDIUM · 1 issue

  • Runlayer6mo

    1/6 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at c805268. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 days ago.

Activeupdated 2 weeks ago

README badge

README badge for simota/agent-skills/voice