See it in action
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptWhat template format should be used to define clear accountability across research and activation workflows involving Product, CS, and Marketing?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Recommends a RACI chart structure. | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md25 linessingle file
Stakeholder Operations Guide Skill
When to Use
- Launching surveys, betas, or listening tours that require multi-team approvals.
- Routing insights to product, CS, marketing, and exec stakeholders with clear accountability.
- Ensuring follow-up communications and governance rituals stay on track.
Framework
- Stakeholder Map – list involved teams, decision rights, and expectations per stage.
- Approval Workflow – define checkpoints (brief sign-off, launch approval, readout review) with timelines.
- Communication Plan – specify audiences, channels, frequency, and owners for updates.
- Action Tracking – set up shared trackers with status, blockers, and success metrics.
- Governance Rituals – outline cadences (weekly syncs, monthly reviews) plus escalation paths.
Templates
- RACI chart for research + activation workflows.
- Approval checklist with required artifacts (brief, QA results, comms plan).
- Meeting agenda + notes template to keep stakeholders aligned.
Tips
- Keep stakeholder rosters fresh; note backups for vacations or org changes.
- Automate reminders linked to due dates via project/workflow tools.
- Pair with
insight-synthesis outputs to ensure narrative consistency.
Track record
Benchmark
20 / 22
test cases passed, vs 14 / 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/customer-feedback-orchestration/skills/stakeholder-ops/SKILL.md
License Apache-2.0Imported 8/3/2026Version v1