From openclix
Proposes pause/resume/add/delete/update operations for OpenClix campaigns from performance analytics, generates openclix-config.next.json, and applies after user confirmation.
npx claudepluginhub openclix/openclix --plugin openclixThis skill uses the workspace's default tool permissions.
Operate campaigns from measured outcomes, not intuition.
Designs OpenClix campaign configurations from product goals and app events, producing schema-valid openclix-config.json, app profiles, and runtime integration setup for notifications and retention flows.
Analyzes drupal-workflow plugin's autopilot effectiveness from session data and proposes tunings to policies, thresholds, and classifiers. Use when interventions are too noisy, quiet, ignored, or misclassified.
Displays campaign autopilot dashboard with health scores, recent auto-corrections, guardrail config, attention flags, and automation savings. Use for operational checks on active marketing campaigns.
Share bugs, ideas, or general feedback.
Operate campaigns from measured outcomes, not intuition.
This skill consumes openclix-analytics outputs and generates safe, reviewable campaign updates.
.openclix/campaigns/openclix-config.next.json without mutating the active config.propose_then_apply..openclix/campaigns/openclix-config.json before user confirmation.openclix_campaign_id) with conservative sampling.openclix-design-campaigns..openclix/**, ensure .openclix/ exists in .gitignore.Required:
.openclix/analytics/impact-metrics.json.openclix/campaigns/openclix-config.jsonOptional:
.openclix/analytics/campaign-metrics.json.openclix/campaigns/app-profile.json.openclix/campaigns/update-history.json.openclix/campaigns/update-recommendations.json.openclix/campaigns/openclix-config.next.json.openclix/campaigns/update-history.json.openclix/ is ignored by git when .openclix/** outputs are created.Run:
bash skills/openclix-update-campaigns/scripts/detect_delivery_mode.sh --root <target-project-root>
Priority:
--mode) if providedReturned mode is one of:
bundlehosted_httpdualunknownIf mode is unknown, stop and ask the user to choose bundle or hosted HTTP.
If .openclix/analytics/campaign-metrics.json is missing:
status: insufficient_data.no_change decisions.Run:
bash skills/openclix-update-campaigns/scripts/evaluate_campaigns.sh --root <target-project-root>
Decision defaults:
d7_retention_delta_ppopen_rate, fail_rate, cancel_ratedelivered >= 200 and opened >= 20Action rules are documented in references/decision-rules.md.
The evaluator must output:
update-recommendations.json with action list, reason codes, and proposed patchesopenclix-config.next.json with draft changes onlyupdate-history.jsonShow the recommendation summary and ask for confirmation. Do not apply to active config until confirmation.
bundle: sync updated source config to bundled runtime resource path and verify local load + OpenClixCampaignManager.replaceConfig(...) path.hosted_http: publish updated config to user-owned HTTPS host and verify URL health.dual: update both hosted primary and local fallback paths consistently.Run platform checks and report:
For multi-agent retention review loops, run:
bash scripts/retention_ops_automation.sh \
--root <target-project-root> \
--agent all \
--delivery-mode auto \
--dry-run
The helper executes delivery mode detection + evaluator orchestration and writes:
.openclix/automation/run-summary.json.openclix/automation/prompts/openclaw.md.openclix/automation/prompts/claude-code.md.openclix/automation/prompts/codex.mdFailure codes from helper script:
10: prerequisite command or required script missing20: no supported PA provider detected21: OpenClix integration not detected30: required input artifact missing31: delivery mode unresolved (unknown)40: evaluator failedreferences/decision-rules.mdreferences/delivery-mode-detection.mdreferences/campaign-metrics-contract.mdreferences/provider-campaign-query-recipes.md../openclix-design-campaigns/SKILL.md../openclix-analytics/SKILL.md