JasonColapietro/suede-creator-skills / skills/suede-marketing-loops
suede-marketing-loops
VerifiedSuede Marketing Loop Skills. recurring marketing workflow design with cadence, action conditions, durable state, dedupe, checkpoints, and stop rules. Use when asked "create a weekly ranking watch" or to turn repeatable marketing work into a complete loop spec. NOT FOR: one-off plans (suede-marketing-plan), experiments (suede-ab-testing), or scheduling without authority.
| File | Kind | Size |
|---|---|---|
| CARD.md | markdown | 4.1 KB |
| SKILL.md | skill md | 10.8 KB |
| agents/openai.yaml | config | 565 B |
| evals/evals.json | config | 7.7 KB |
| references/loop-catalog.md | markdown | 47.7 KB |
| references/loop-guardrails.md | markdown | 4.9 KB |
| references/loop-orchestration.md | markdown | 4.7 KB |
| references/loop-state.md | markdown | 3.7 KB |
| references/loop-template.md | markdown | 5.0 KB |
| references/worked-contract.md | markdown | 2.4 KB |
references/loop-orchestration.md
View on GitHub# Loop Orchestration & Rollout
Loops aren't independent scripts: they compose into a marketing operating system. This reference covers how they fit together and the order to adopt them so you never build the whole catalog at once.
## The system view
Loops fall into four layers. Data flows down and learnings flow back up.
```
SENSING analytics-anomaly · tracking-QA · weekly-marketing-review
│ (detect what changed; trust the numbers first)
▼
DIAGNOSTIC per-stage watchers, onboarding drop-off, churn-signal,
ranking-drop, landing-page regression, ad-fatigue, …
│ (figure out what to do about it)
▼
ACTION staged drafts, nudges, outreach, budget moves
│ (mostly human-checkpointed)
▼
LEARNING experiment-backlog · campaign-postmortem · voice-of-customer
│ (capture what worked)
└──────────────► feeds back into SENSING & DIAGNOSTIC
```
Key connective tissue:
- **weekly-marketing-review is the router.** It reads top-line metrics and dispatches each notable mover to the loop that owns it. It's the one loop that sees the whole board.
- **tracking-QA + analytics-anomaly are the foundation.** Every other loop reads from analytics. If tracking is broken, every downstream loop acts on lies. These come first.
- **experiment-backlog is the sink.** Hypotheses generated by many loops (signup-leak, pricing, onboarding, voice-of-customer) converge here, then hand off to `suede-ab-testing`. Don't let each loop run its own tests.
- **voice-of-customer is a source.** Customer language it mines feeds copy for ad-fatigue, lifecycle-email, landing-page, and pricing loops.
- **campaign-postmortem closes the loop.** Its learnings become next quarter's hypotheses and plan inputs.
Avoid duplicate ownership: when two loops could act on the same signal, one owns the action and the other just flags. (E.g., an at-risk account belongs to churn-signal, not expansion/upsell: never upsell an account that's churning.)
## Rollout path (adopt in this order)
Add a loop only when the loops before it are running and earning their keep. Each stage assumes the previous one is solid.
**Stage 0: Foundation (trust the data + see the board).**
`tracking-QA`, `weekly-marketing-review`.
You cannot run any loop responsibly on untrustworthy data or without a full-funnel pulse. This is non-negotiable and comes first.
**Stage 1: Plug the leaks (highest ROI, protects existing revenue).**
`failed-payment/dunning`, `churn-signal`, `lifecycle-email-refresh`.
Recovering customers you already have is cheaper than acquiring new ones. Dunning alone often pays for the whole system.
**Stage 2: Convert what you already get (fix the bucket before adding water).**
`onboarding drop-off`, `signup-funnel-leak`, `trial-conversion`.
More traffic into a leaky funnel is waste. Seal activation and conversion next.
**Stage 3: Grow the top (now scale acquisition).**
`keyword-gap`, `content-repurposing`, `ad-fatigue`, `social-listening`, `analytics-anomaly`.
With the bucket sealed, turn on demand generation and the safety-net anomaly watcher.
**Stage 4: Optimize monetization.**
`pricing-page-experiment`, `paywall-optimization`, `PQL/upgrade-intent`, `expansion/upsell`.
Once volume is healthy, tune revenue per user, judged on revenue quality, not conversion alone.
**Stage 5: Compounding & advocacy.**
`referral-nudge`, `review-and-UGC-harvest`, `review-site-management`, `case-study-sourcing`, `partner-pipeline`, `brand-mention/reputation`, `experiment-backlog`, `campaign-postmortem`.
The flywheel: happy customers and earned media that feed back into acquisition, plus the learning loops that make everything compound.
The remaining catalog loops (content-decay, internal-linking, programmatic-SEO quality, content-calendar refill, paid-search query-mining, retargeting-hygiene, landing-page regression, community-engagement, competitor-watch, backlink-prospecting, directory-submission, feature-adoption, lead-capture-asset, email-deliverability, voice-of-customer) slot into the stage that matches their function as each channel becomes a priority.
## Rollout rules
- **One at a time.** Prove a loop earns its keep (someone acts on its output, it moves its metric) before adding the next.
- **Foundation before growth.** Acquisition loops before solid tracking + retention = pouring water into a leaky bucket.
- **Cap the total.** If you're running more loops than you can review the output of, you have vanity loops. Retire the ones nobody acts on.
- **Re-audit quarterly.** Recalibrate thresholds, kill dead loops, promote the ones that consistently drive action.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |