skilld
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.

Ask your Agent

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

This session only. Nothing lands on disk.

referencenps-survey.md

≈339 tokens on demand. Your agent reads this file only when SKILL.md points to it.

NPS Survey Delta

Purpose: Voice NPS instrument, consent, and interpretation contract. Static industry benchmark tables are intentionally excluded because they drift.

Instrument

Ask the standard 0-10 likelihood-to-recommend question with product/audience wording appropriate to the program. Classify 0-6 detractor, 7-8 passive, 9-10 promoter.

NPS = percent_promoters - percent_detractors

Ask after a meaningful experience. Keep the score response separate from optional verbatim feedback and from consent to contact the respondent.

Minimal Record

Store score, derived category, pseudonymous respondent/account key, survey/touchpoint, segment/plan/tenure, timestamp, optional feedback, instrument version, and consent flags. Apply the product's privacy and retention policy.

Analysis Contract

  • Always report response count/rate and uncertainty with the score.
  • Segment only when sample size and sampling design support it.
  • Compare like touchpoints, populations, and time windows.
  • Treat open text as qualitative evidence, not a numeric explanation of NPS.
  • Fetch current external benchmarks from dated primary or clearly identified benchmark sources; never reuse an undated “good/excellent/world-class” scale.

Route themes to Spark/Growth, coding to thematic-coding.md, and instrumentation gaps to Pulse.

Source: SKILL.md on GitHub

Third-party checks

1 warning14d5 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.

  • Socket14d

    No alerts

  • Snyk14d

    Risk: MEDIUM · 1 issue

  • Runlayer6mo

    1/6 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Provenance

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