See it in action
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptWho are the primary operational team members intended to use the quick-reference taxonomy cheatsheet during daily operations?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| The response identifies moderators and interviewers as the primary target users. | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md25 linessingle file
Community Insight Taxonomy Skill
When to Use
- Standardizing feedback tagging across forums, events, surveys, and interviews.
- Sharing structured insights with product, marketing, or CS teams.
- Powering dashboards and AI routing for community signals.
Framework
- Persona Dimension – builders, admins, execs, partners, champions, newcomers.
- Journey Stage – onboarding, activation, adoption, expansion, advocacy, lapse.
- Driver Dimension – product, support, education, pricing, community experience, roadmap.
- Sentiment & Urgency – positive/neutral/negative + severity/impact.
- Business Linkage – map to ARR tier, account health, opportunity pipeline, or churn risk.
Templates
- Tag dictionary with definitions, examples, and confidence guidelines.
- Airtable/Sheet schema with validation + automation hooks.
- Quick-reference cheatsheet for moderators/interviewers.
Tips
- Run monthly taxonomy reviews to merge duplicates and add emerging themes.
- Capture "what good looks like" examples to maintain consistency.
- Pair with
run-member-insight-sprint for auto-tagged datasets.
Track record
Benchmark
21 / 23
test cases passed, vs 16 / 23 without
Adoption
- Users
- 0
- Times used
- 0
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
Importedgtmagents / gtm-agents
plugins/community-building/skills/community-insight-taxonomy/SKILL.md
License Apache-2.0Imported 8/3/2026Version v1