See it in action
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptAn experiment idea has received initial review and has an assigned owner, but engineering has not started building it. What status should it hold?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Assigns the status stage of scoped | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md25 linessingle file
Hypothesis Library Skill
When to Use
- Capturing new experiment ideas with consistent metadata.
- Referencing past wins/losses before prioritizing the backlog.
- Sharing reusable learnings across pods and channels.
Framework
- Metadata Schema – hypothesis ID, theme, persona, funnel stage, metrics.
- Assumptions Matrix – belief statements, supporting evidence, confidence rating.
- Status Tracking – idea → scoped → running → decided → archived.
- Learning Tags – impact summary, guardrail notes, follow-up ideas.
- Governance Hooks – approvals, owners, review cadence.
Templates
- Intake form for new hypotheses.
- Learning card format (context, result, recommendation).
- Portfolio dashboard summarizing mix by theme/metric.
Tips
- Require at least one supporting data point before moving to prioritization.
- Use consistent tagging so search/filtering works across teams.
- Link to
synthesize-learnings outputs to keep narratives fresh.
Track record
Benchmark
19 / 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/growth-experiments/skills/hypothesis-library/SKILL.md
License Apache-2.0Imported 8/3/2026Version v1