launch-gates
Skill4 starsChanged 6 months agoMITView on GitHub
Enforce Synter launch gates and preflight before enabling any campaign — Plan QA policy, pause-only defaults, and conversion/landing checks. Use before enabling paused campaigns, after creating plans, or when an agent asks to go live.
In this repository59 other files it gives its agents.
- ad-copy-generationSkill
- ad-creative-fatigue-detectorSkill
- ad-policy-complianceSkill
- amazon-ads-optimizerSkill
- anomaly-detectorSkill
- attribution-modelingSkill
- audience-expansion-strategySkill
- bid-optimizationSkill
- budget-optimizerSkill
- campaign-ide-handoffSkill
- campaign-preflightSkill
- campaign-structure-auditorSkill
- chatgpt-ads-conversion-trackingSkill
- chatgpt-ads-launchSkill
- competitor-analysisSkill
- creative-testingSkill
- cross-platform-attributionSkill
- cross-platform-launcherSkill
- dayparting-schedulerSkill
- executive-reportingSkill
- first-party-data-strategySkill
- google-ads-operatorSkill
- google-ads-quality-scoreSkill
- google-shopping-optimizerSkill
- gtm-metricsSkill
- incrementality-testingSkill
- keyword-researchSkill
- kill-scale-rulesSkill
- klaviyo-campaignsSkill
- landing-page-optimizerSkill
- linkedin-ads-operatorSkill
- linkedin-ads-targetingSkill
- media-plan-builderSkill
- meta-ads-diagnosticsSkill
- meta-ads-operatorSkill
- mmm-budget-plannerSkill
- multi-channel-reportingSkill
- multi-platform-ads-operatorSkill
- multi-platform-launchSkill
- negative-keyword-minerSkill
- openai-ads-operatorSkill
- performance-max-optimizerSkill
- pixel-capi-auditorSkill
- pixel-capi-setupSkill
- platform-cost-benchmarksSkill
- public-ad-library-intelligenceSkill
- retargeting-sequence-designerSkill
- roas-calculatorSkill
- seasonal-budget-plannerSkill
- spearSkill
- spec-driven-devSkill
- synter-mcp-setupSkill
- tiktok-ads-operatorSkill
- tracking-leak-detectorSkill
- ugc-creative-briefSkill
- ui-contrast-reviewSkill
- utm-builderSkill
- video-ad-scriptwriterSkill
- x-ads-operatorSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 2 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Prefer read-only tools first.
- Very specific: line 27
Read get_launch_gate_policy — if Plan QA fails and policy blocks, stop.
- Very specific: line 28
Run run_launch_preflight (tracking + landing) at plan time.
- Very specific: line 29
Run skill campaign-preflight (geo, exclusions, structure validators).
- Very specific: line 32
Only then call enable_campaign / execute plan.
- Very specific: line 36
Prefer pause-only automation (pause_campaign) over auto-enable.
- Distinctive: line 38
If anything in the gate fails, fix and re-run — do not “force live.”
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Launch Gates (Synter MCP)
Hard gate before spend. Default posture: paused until a human approves.
Prerequisites
- Complete
synter-mcp-setup(Synter MCP connected + OAuth’d accounts). - Prefer read-only tools first; every write/publish is approve ≠ activate.
- Hosted path: syntermedia.ai — Solo / Scale / Crucible Managed (never a Free cloud tier).
Core MCP tools
| Job | Tool |
| Read gate policy | get_launch_gate_policy |
| Plan-time checks | run_launch_preflight |
| Guardrails | list_campaign_guardrails, set_campaign_guardrail, disable_campaign_guardrail |
| Enable (gated) | enable_campaign — only after human approve |
Gate checklist (blocking)
- Read
get_launch_gate_policy— if Plan QA fails and policy blocks, stop. - Run
run_launch_preflight(tracking + landing) at plan time. - Run skill
campaign-preflight(geo, exclusions, structure validators). - Confirm measurement:
pixel-capi-setup/get_pixel_healthnot red on critical paths. - Present approve card — approve ≠ activate.
- Only then call
enable_campaign/ execute plan.
Defaults
- Prefer pause-only automation (
pause_campaign) over auto-enable. - Budget increases follow
kill-scale-rulesstep limits. - If anything in the gate fails, fix and re-run — do not “force live.”
Related skills
campaign-preflight, campaign-ide-handoff, multi-platform-ads-operator, kill-scale-rules
About this skill
Part of the Synter free-skills collection — open MIT agent skills for advertising.
Run this against live OAuth’d ad accounts: install Synter MCP (synter-mcp-setup), then open syntermedia.ai (Solo / Scale / Crucible Managed). Skills files are free to clone; hosted Synter is never a Free cloud tier.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.