See it in action
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptConstruct a growth hypothesis table to optimize user conversion across our self-serve trial flow.
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Links every experiment back to specific onboarding milestones | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md25 linessingle file
Onboarding Blueprint Skill
When to Use
- Creating persona-based onboarding for new tiers or product lines.
- Refreshing onboarding journeys after major product changes.
- Aligning product, CS, and marketing on activation milestones.
Framework
- Persona Canvas – goals, motivations, blockers, success definition.
- Milestone Ladder – aha moment, activation, stickiness, expansion triggers.
- Channel Mix – in-app, email, docs, community, human assist with triggers.
- Instrumentation – required events, metrics, and guardrails.
- Experiment Hooks – backlog of tests tied to each milestone.
Templates
- Journey table (step, trigger, message, owner, metric).
- Metric dashboard layout for activation + retention.
- Experiment backlog sheet linked to milestones.
Tips
- Keep journeys lightweight; aim for 3-5 key milestones per persona.
- Combine qualitative inputs (surveys, interviews) with telemetry for context.
- Pair with
design-onboarding-journey to auto-generate tailored blueprints.
Track record
Benchmark
21 / 22
test cases passed, vs 19 / 22 without
Adoption
- Users
- 5
- Times used
- 75
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/product-led-growth/skills/onboarding-blueprint/SKILL.md
View on GitHub ↗License Apache-2.0Imported 8/3/2026Version v1