S39 · Pipeline skill
Review campaign results
Check visits and action records, compare content results and confirm the next schedule.
Source attribution + performance comparison + human content changes and scheduling
- Pipeline
- 5 steps
- Human review
- 1
- Components
- 9
01Pipeline
Base pipeline
Ordered steps. Each consumes the previous output; review gates hold until a person accepts.
- Starts from
- Published content, permitted analytics and campaign goals
- Delivers
- Schedule, execution records and next review baseline
Review contract
People decide at review gates; components supply data, drafts or review surfaces. Unaccepted outputs do not advance.
Integration note
Attribution, prompt probes and experiments are distinct evidence types; observed changes do not establish causation or returns.
- 01
Link sources and actions
- Input
- Published content, permitted analytics and campaign goals
- Output
- Traceable visit and action table
- Localized affiliate redirects and attributionAllowlisted links with source parameters + redirect attribution
- Attribution and conversion feedbackSource links joined to conversions + feedback into planning
- 02
Check performance and health
- Input
- Traceable visit and action table
- Output
- Content comparisons, data gaps and operational issues
- Growth experiments and performance viewsPerformance and experiment state inspection + human version selection
- Growth health and decision reportingCampaign queue and integration health + checkpoint alerts
- AI-answer visibility probing and content-gap analysisBatched question probes + citation and mention counts
- 03
Draft adjustments
- Input
- Content comparisons, data gaps and operational issues
- Output
- Next-cycle content and channel proposals
- Cross-channel content amplificationHigh-performing content selection + adapted review drafts
- Feedback-driven multilingual growth planningHistory and timing based topic ranking + channel schedules
- 04
Choose the next plan
Human review- Input
- Next-cycle content and channel proposals
- Output
- Human-approved campaign plan
Decided byAssigned reviewer or requesting user
- Editorial review and A/B test managementQueued draft versions + human approval and comparison experiments
- Growth experiments and performance viewsPerformance and experiment state inspection + human version selection
- 05
Schedule and retain history
- Input
- Human-approved campaign plan
- Output
- Schedule, execution records and next review baseline
- Scheduled growth runtime and audit statePeriodic task execution + state snapshots and run history
- Feedback-driven multilingual growth planningHistory and timing based topic ranking + channel schedules
02Industry versions
Industry versions
Media & content Transferable use Align article source links, reading and subscription actions so editors can choose the next topics and channels.
Adaptation Separate reading, subscription and actual payment events; attribution correlation does not establish distribution causality.
- 01
Link sources to subscription actions
- Input
- Published articles, permitted analytics and distribution goals
- Output
- Traceable reading and action table
- Localized affiliate redirects and attributionAllowlisted links with source parameters + redirect attribution
- Attribution and conversion feedbackSource links joined to conversions + feedback into planning
- 02
Check content performance and gaps
- Input
- Traceable reading and action table
- Output
- Content comparisons and analytics gaps
- Growth experiments and performance viewsPerformance and experiment state inspection + human version selection
- Growth health and decision reportingCampaign queue and integration health + checkpoint alerts
- AI-answer visibility probing and content-gap analysisBatched question probes + citation and mention counts
- 03
Suggest topic and channel changes
- Input
- Content comparisons and analytics gaps
- Output
- Next-cycle article and channel suggestions
- Cross-channel content amplificationHigh-performing content selection + adapted review drafts
- Feedback-driven multilingual growth planningHistory and timing based topic ranking + channel schedules
- 04
Editor approves the next plan
Human review- Input
- Next-cycle article and channel suggestions
- Output
- Approved topic and channel plan
Decided byAssigned reviewer or requesting user
- Editorial review and A/B test managementQueued draft versions + human approval and comparison experiments
- Growth experiments and performance viewsPerformance and experiment state inspection + human version selection
- 05
Schedule and retain review baseline
- Input
- Approved topic and channel plan
- Output
- Schedule records and future comparison baseline
- Scheduled growth runtime and audit statePeriodic task execution + state snapshots and run history
- Feedback-driven multilingual growth planningHistory and timing based topic ranking + channel schedules
03Parameters
Parameters
From the pack’s params.schema.json. Choose values to build a synthetic request.
skills/_pipelines/review-campaign-results/params.schema.json
{
"synthetic": true,
"run_id": "synthetic-example",
"locale": "en",
"industry": "base",
"adapter_mode": "local",
"records": [
{
"id": "synthetic-record-1",
"synthetic": true,
"text": "Synthetic observation A: a draft needs review."
},
{
"id": "synthetic-record-2",
"synthetic": true,
"text": "Synthetic observation B: retain the unresolved question."
}
],
"decisions": {}
} 04Member components
Member components
-
Localized affiliate redirects and attribution
Allowlisted links with source parameters + redirect attribution
Working 1 pipeline -
Attribution and conversion feedback
Source links joined to conversions + feedback into planning
Working 1 pipeline -
Growth experiments and performance views
Performance and experiment state inspection + human version selection
Working 1 pipeline -
Growth health and decision reporting
Campaign queue and integration health + checkpoint alerts
Working 1 pipeline -
AI-answer visibility probing and content-gap analysis
Batched question probes + citation and mention counts
Prototype 1 pipeline -
Cross-channel content amplification
High-performing content selection + adapted review drafts
Working 1 pipeline -
Feedback-driven multilingual growth planning
History and timing based topic ranking + channel schedules
Working 1 pipeline -
Editorial review and A/B test management
Queued draft versions + human approval and comparison experiments
Working 2 pipelines -
Scheduled growth runtime and audit state
Periodic task execution + state snapshots and run history
Working 1 pipeline
05Skills pack
Skills pack
Runnable reference on synthetic fixtures with tests. Domain contracts, services and approvals still need integration.
review-campaign-results-1.0.0.zip
Contains SKILL.md, pipeline.json, params.schema.json, runner, tests, fixtures, integration checklist and sources.
Synthetic workflow reference; service integration pending
Download · 19KBSHA-256 fffc602db09758446b9d64ebd77a452cd283180ad8b0c7a67d7564d1f7b2b3d1