See it in action
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptWhere should our analysts look in our repository to find the pre-built layout structure file when creating dashboard wireframes?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Directs users to templates/dashboard_wireframe.md for the wireframe structure. | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md25 lines2 files
Dashboard Playbook Skill
When to Use
- Designing new dashboards or refreshing existing ones for GTM stakeholders.
- Auditing dashboards that suffer from low engagement or unclear narratives.
- Training analysts on consistent storytelling and UX patterns.
Framework
- Audience & Decisions – document persona, cadence, and key decisions.
- Story Arc – headline metric, supporting evidence, drill-downs, and action prompts.
- Layout System – hero tiles, contextual panels, alerts, and annotation space.
- Governance Hooks – data freshness indicator, owner info, and SLA links.
- Adoption Loop – training plans, feedback capture, and iteration cadence.
Templates
- Wireframe Template: See
templates/dashboard_wireframe.md for layout structure.
- Dashboard brief (goals, KPIs, filters, mockups).
- Adoption checklist (enablement, comms, success metrics).
Tips
- Limit hero metrics to 3–5; move detailed tables into drill sections.
- Use consistent color semantics for good vs risk states.
- Pair with
build-exec-dashboard to package specs + rollout plan.
Track record
Benchmark
17 / 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/business-intelligence/skills/dashboard-playbook/SKILL.md
License Apache-2.0Imported 8/3/2026Version v1Bundled 1 file