See it in action
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptA growth team wants to launch a new onboarding flow with A/B variants. Which pillar of launch tiering covers feature flagging and split-test tracking?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Categorizes experimentation under the instrumentation pillar | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md25 linessingle file
Launch Tiering Framework Skill
When to Use
- Evaluating upcoming releases to determine Tier 1/2/3 scope.
- Aligning stakeholders on budget, channels, and required deliverables.
- Documenting launch expectations for planning, approvals, and reporting.
Framework
- Impact Criteria – ARR target, product scope, audience reach, competitive urgency.
- Resource Requirements – channels activated, creative/engineering effort, regional needs.
- Governance Level – exec involvement, war-room cadence, risk tolerance.
- Instrumentation – telemetry readiness, reporting complexity, experimentation.
- Compliance & Dependencies – legal/security review, partner commitments, support readiness.
Templates
- Tier scoring matrix (criteria, weights, thresholds, recommended resourcing).
- Tier playbook (required workstreams, artifacts, checkpoints, reporting).
- Approval checklist for tier changes or escalations.
Tips
- Reassess tier mid-cycle if scope or market conditions shift.
- Maintain a historical log of tier decisions for future benchmarking.
- Tie tier definitions to budgeting + staffing models to ensure consistency.
Track record
Benchmark
20 / 22
test cases passed, vs 16 / 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/product-launch-orchestration/skills/launch-tiering/SKILL.md
License Apache-2.0Imported 8/3/2026Version v1