JasonColapietro/suede-creator-skills / skills/suede-sms
suede-sms
VerifiedDesign consent-aware SMS/MMS programs: channel fit, welcome, cart recovery, post-purchase and win-back flows, exact copy, segment counts, cadence, quiet hours, platform selection, and measurement. Use when asked to "draft our SMS welcome flow" or audit a text program. Checks current consent, opt-out, and registration requirements. NOT FOR: email (use suede-emails), capture UX (use suede-site-alchemy), legal certification, or sending, scheduling, importing, or registering anything.
| File | Kind | Size |
|---|---|---|
| CARD.md | markdown | 4.4 KB |
| SKILL.md | skill md | 18.7 KB |
| agents/openai.yaml | config | 526 B |
| evals/evals.json | config | 8.4 KB |
| references/compliance.md | markdown | 9.3 KB |
| references/platforms.md | markdown | 9.6 KB |
| references/sequence-templates.md | markdown | 6.8 KB |
| references/worked-handoff.md | markdown | 1.9 KB |
evals/evals.json
View on GitHub{
"skill_name": "suede-sms",
"evals": [
{
"id": 1,
"prompt": "We're a Shopify DTC brand doing $5M/year in skincare. We have 80K email subscribers but no SMS program yet. Where do we start?",
"expected_output": "Should check for product-marketing.md first. Should run Phase 0 compliance check: are they US-based, is A2P 10DLC registration started, is the opt-in mechanism planned. Should recommend Klaviyo SMS or Postscript given Shopify + DTC ecom (Klaviyo if already on Klaviyo email, Postscript for SMS-first depth). Should rank flows by ROI for skincare: (1) abandoned cart sequence first (highest-ROI flow), (2) post-purchase + replenishment (skincare has predictable cycles), (3) welcome opt-in flow with capture incentive, (4) win-back at 60-90 days. Should warn about treating SMS like email (frequency cap, relevance bar, real per-send cost ~$0.0075-$0.04). Should reference compliance.md for opt-in disclosure language and quiet hours.",
"assertions": [
"Checks for product-marketing.md",
"Runs compliance/A2P 10DLC readiness check",
"Recommends Klaviyo SMS or Postscript with rationale",
"Prioritizes abandoned cart as highest-ROI flow",
"Mentions replenishment for skincare specifically",
"Warns about treating SMS like email",
"References compliance.md or opt-in disclosure requirements",
"Mentions per-send cost economics"
],
"files": []
},
{
"id": 2,
"prompt": "Write me an abandoned cart SMS sequence. We sell custom apparel, average order $80.",
"expected_output": "Should output a 3-message sequence following references/sequence-templates.md pattern. Should specify timing: Send 1 at 30 min after abandon (no discount, gentle reminder), Send 2 at 4 hours (soft urgency, no discount), Send 3 at 24 hours (discount allowed). Should include actual SMS copy with character counts (target 160 GSM-7 for 1 segment). Each message must start with sender ID 'From [Brand]:', have a single CTA + short link, and the first message should include 'Reply STOP to opt out' compliance footer. Should warn against discount on first send (trains customers to abandon). Should mention exclusion rules: stop sequence on purchase, opt-out, or 48 hours elapsed. Should recommend UTM tagging for attribution and cross-reference `suede-analytics` for measurement.",
"assertions": [
"Outputs 3-message sequence with timing",
"Send 1 at 30 min, Send 2 at 4 hours, Send 3 at 24 hours",
"No discount on Send 1",
"Each message has sender ID + single CTA + short link",
"Character counts shown, target ~160 GSM-7",
"Compliance footer on first send (STOP to opt out)",
"Warns about discount on first send",
"Mentions exclusion rules",
"Mentions UTM tagging or attribution"
],
"files": []
},
{
"id": 3,
"prompt": "Can I just send SMS without any opt-in if customers gave me their phone number at checkout?",
"expected_output": "Should refuse and explain TCPA requires express written consent for marketing SMS. Should distinguish marketing SMS (requires express written consent) from transactional/account SMS (order updates, auth — implied consent during transaction OK if directly related). Should explain the express written consent requirements: clear disclosure adjacent to the phone field, frequency expectation, msg & data rates notice, STOP/HELP instructions, terms link, electronically captured with timestamp. Should mention penalty exposure: $500-$1,500 per message, class actions reach 7-8 figures. Should recommend implementing a compliant opt-in flow: checkbox + disclosure text, double opt-in optional but cleaner. Should reference compliance.md for the full disclosure template. Should warn that 'customers gave their number at checkout' is NOT sufficient for marketing SMS — it's only sufficient for the specific transaction's communications.",
"assertions": [
"Refuses the no-opt-in approach",
"Distinguishes marketing SMS from transactional SMS",
"Lists express written consent requirements",
"Mentions TCPA penalty exposure ($500-$1,500 per message)",
"Mentions class action risk",
"Recommends compliant opt-in flow",
"References compliance.md",
"Clarifies checkout phone capture is not marketing consent"
],
"files": []
},
{
"id": 4,
"prompt": "Our SMS list is 50K subscribers. We send 3 promotional messages per week. Opt-out rate has crept up to 4% per send. What's wrong?",
"expected_output": "Should diagnose likely audience fatigue while checking current account history, consent source, send mix, and applicable carrier or vendor benchmarks before naming a threshold. Should review frequency and relevance, compare segments by engagement, purchase recency, and opt-in source, and calculate the actual subscriber loss implied by the provided opt-out rate. Should recommend a bounded re-engagement test before more broad promotions, cross-reference `suede-analytics`, and keep the principle that every send must justify itself.",
"assertions": [
"Diagnoses as over-sending / audience fatigue",
"Cites healthy benchmark (<2% opt-out per send, <0.5% promotional)",
"Recommends reducing send frequency",
"Recommends segmentation by engagement",
"Suggests reactivation flow for cold subscribers",
"Calculates list erosion impact",
"Mentions 'every send must justify itself' principle"
],
"files": []
},
{
"id": 5,
"prompt": "We just submitted our A2P 10DLC registration and our sends are working. Can we start scaling to 100K+ messages per day?",
"expected_output": "Should ask about phone number type currently in use: 10DLC, toll-free, or short code. Should explain throughput limits: 10DLC standard brand ~4-10 msg/sec, verified brand ~75-100+ msg/sec, toll-free ~3 msg/sec, short code 100+ msg/sec. Should calculate: 100K msgs at 10 msg/sec = ~2.8 hours of continuous send time, may run into quiet hour cutoff. Should recommend short code lease for 100K+/day sustained volume. Should warn about carrier filtering on burst sends — use platform throttling. Should mention that sample message text from A2P registration must match actual sends or carriers will flag. Should recommend monitoring trust score and deliverability dashboards. Should reference platforms.md for short code provisioning details.",
"assertions": [
"Asks about phone number type (10DLC vs toll-free vs short code)",
"Explains throughput limits with specific msg/sec numbers",
"Calculates time-to-send for 100K volume",
"Mentions quiet hour considerations",
"Recommends short code for high sustained volume",
"Warns about carrier filtering / throttling",
"Mentions A2P sample text alignment requirement",
"References platforms.md or trust score monitoring"
],
"files": []
},
{
"id": 6,
"prompt": "Should we put emojis in our SMS messages? Other brands seem to use them a lot.",
"expected_output": "Should explain the cost trade-off: emojis force UCS-2 encoding, which cuts segment size from 160 GSM-7 chars to 70 chars. A 100-char message with one emoji becomes 2 segments billed instead of 1 — effectively doubling the per-send cost. Should advise: 1 emoji per message max, situationally relevant, only when the emoji genuinely earns its segment cost (high-energy promotional, brand-personality fit, etc.). Should warn against emoji clutter — it signals 'mass send' rather than personal. Should note that some accented characters (curly quotes, em dashes) also force UCS-2 — copy-pasting from Word/Google Docs is a common silent cause of doubled costs. Should recommend testing in the platform's preview to verify segment count before scheduling. Should remind that segment count matters at scale: 100K sends at 2 segments instead of 1 = $750-$4,000 in extra cost per campaign.",
"assertions": [
"Explains UCS-2 encoding cost",
"Specifies 160 GSM-7 vs 70 UCS-2 segment sizes",
"Recommends max 1 emoji per message",
"Warns about doubled per-send cost",
"Mentions accented characters / curly quotes also trigger UCS-2",
"Recommends previewing segment count",
"Calculates cost impact at scale"
],
"files": []
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |