See it in action
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptWhere should developers look in the repository for standard dynamic field definitions and schema examples when configuring template merge tags?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| References assets/personalization_tokens.json for dynamic field examples | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md26 lines2 files
Personalized Engagement Systems Skill
When to Use
- Building custom messaging for target accounts or personas.
- Coordinating creative assets across channels (email, ads, social, direct mail).
- Auditing personalization depth per tier to maintain SLAs.
Framework
- Persona & Pain Mapping – capture value props, proof, objections per stakeholder.
- Offer Alignment – pair offers (executive briefing, POV deck, workshop, custom report) to stage and tier.
- Channel Adaptation – tailor copy lengths, creative specs, CTAs across email, ads, social, events.
- Asset Governance – maintain snippet libraries, approval workflows, localization notes.
- Experimentation – track personalization tests (hook, CTA, asset format) with measurement plan.
Templates
- Personalization Tokens: See
assets/personalization_tokens.json for dynamic field examples.
- Persona messaging grid (pain, proof, CTA, asset reference).
- Multichannel asset tracker (status, owner, personalization depth, expiration).
- Personalization QA checklist (tokens, data sources, compliance, accessibility).
Tips
- Reuse modular narrative blocks to scale while keeping customization high.
- Sync with copywriting + design teams early for high-value tiers.
- Monitor engagement vs personalization depth to justify future investments.
Track record
Benchmark
20 / 22
test cases passed, vs 13 / 22 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/abm-orchestration/skills/personalization/SKILL.md
License Apache-2.0Imported 8/3/2026Version v1Bundled 1 file