{"id":"b2aee0c9-2120-4840-b6b2-ef82512c87c8","entityType":"agent","slug":"clawhub-leooooooow-inventory-reorder-calculator","name":"Inventory Reorder Calculator","canonicalUrl":"https://www.xpersona.co/agent/clawhub-leooooooow-inventory-reorder-calculator","canonicalPath":"/agent/clawhub-leooooooow-inventory-reorder-calculator","generatedAt":"2026-10-10T09:03:41.054Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-10T07:10:21.731Z","emptyReason":null},"description":"Estimate ecommerce reorder timing and quantity using demand, lead time, and safety stock assumptions so teams can set reorder points and reduce stockout risk... Skill: Inventory Reorder Calculator Owner: leooooooow Summary: Estimate ecommerce reorder timing and quantity using demand, lead time, and safety stock assumptions so teams can set reorder points and reduce stockout risk... Tags: latest:1.1.0 Version history: v1.1.0 | 2026-03-30T11:16:52.109Z | user Major upgrade: Added 3 new reference files (safety-stock-guide, demand-analysis-guide, reorder-checklist). Expanded SKI","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.6K downloads reported by the source. Last updated 10/10/2026.","installCommand":"clawhub skill install s17974h9acjg4h7h5djv1hg51d83hcca:inventory-reorder-calculator","sourceUrl":"https://clawhub.ai/leooooooow/inventory-reorder-calculator","homepage":"https://clawhub.ai/leooooooow/skills/inventory-reorder-calculator","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/leooooooow/inventory-reorder-calculator","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/leooooooow/skills/inventory-reorder-calculator","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":53,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Estimate ecommerce reorder timing and quantity using demand, lead time, and safety stock assumptions so teams can set reorder points and reduce stockout risk..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-10T07:10:21.731Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T07:10:21.731Z","emptyReason":null},"stars":null,"forks":null,"downloads":1600,"packageName":null,"latestVersion":"1.1.0","tractionLabel":"1.6K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T07:10:21.731Z","emptyReason":null},"lastUpdatedAt":"2026-10-10T07:10:21.731Z","lastCrawledAt":"2026-10-10T07:10:21.731Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-11T07:10:21.731Z","lastVerifiedAt":null,"highlights":[{"version":"1.1.0","createdAt":"2026-03-30T11:16:52.109Z","changelog":"Major upgrade: Added 3 new reference files (safety-stock-guide, demand-analysis-guide, reorder-checklist). Expanded SKILL.md with Quick Reference table, 7-step workflow, 2 worked examples, risk scenario framing, and common mistakes. Output template now includes assumptions table with confidence levels, risk scenarios, and action items.","fileCount":7,"zipByteSize":16298},{"version":"1.0.2","createdAt":"2026-03-26T08:33:06.422Z","changelog":"Upgrade skill structure for reorder point, safety stock, and stock-risk decisions.","fileCount":3,"zipByteSize":1872},{"version":"1.0.1","createdAt":"2026-03-18T13:22:24.145Z","changelog":"Add interactive clarification and Python-script workflow guidance","fileCount":3,"zipByteSize":2086},{"version":"1.0.0","createdAt":"2026-03-16T11:09:26.451Z","changelog":"Initial release","fileCount":3,"zipByteSize":1722}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17974h9acjg4h7h5djv1hg51d83hcca:inventory-reorder-calculator","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-leooooooow-inventory-reorder-calculator/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-leooooooow-inventory-reorder-calculator/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-leooooooow-inventory-reorder-calculator/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-leooooooow-inventory-reorder-calculator/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-leooooooow-inventory-reorder-calculator/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-leooooooow-inventory-reorder-calculator/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T09:03:41.053Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-leooooooow-inventory-reorder-calculator/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-leooooooow-inventory-reorder-calculator/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-leooooooow-inventory-reorder-calculator/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-leooooooow-inventory-reorder-calculator/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-10T07:10:21.731Z","emptyReason":null},"readme":"Skill: Inventory Reorder Calculator\n\nOwner: leooooooow\n\nSummary: Estimate ecommerce reorder timing and quantity using demand, lead time, and safety stock assumptions so teams can set reorder points and reduce stockout risk...\n\nTags: latest:1.1.0\n\nVersion history:\n\nv1.1.0 | 2026-03-30T11:16:52.109Z | user\n\nMajor upgrade: Added 3 new reference files (safety-stock-guide, demand-analysis-guide, reorder-checklist). Expanded SKILL.md with Quick Reference table, 7-step workflow, 2 worked examples, risk scenario framing, and common mistakes. Output template now includes assumptions table with confidence levels, risk scenarios, and action items.\n\nv1.0.2 | 2026-03-26T08:33:06.422Z | user\n\nUpgrade skill structure for reorder point, safety stock, and stock-risk decisions.\n\nv1.0.1 | 2026-03-18T13:22:24.145Z | user\n\nAdd interactive clarification and Python-script workflow guidance\n\nv1.0.0 | 2026-03-16T11:09:26.451Z | user\n\nInitial release\n\nArchive index:\n\nArchive v1.1.0: 7 files, 16298 bytes\n\nFiles: assets/reorder-checklist.md (2832b), references/demand-analysis-guide.md (4987b), references/output-template.md (4653b), references/safety-stock-guide.md (5195b), skill-card.md (2398b), SKILL.md (14235b), _meta.json (147b)\n\nFile v1.1.0:SKILL.md\n\n---\nname: inventory-reorder-calculator\ndescription: Estimate ecommerce reorder timing and quantity using demand, lead time, and safety stock assumptions so teams can set reorder points and reduce stockout risk with less guesswork.\n---\n\n# Inventory Reorder Calculator\n\nEstimate when to reorder and how much to buy before stock risk turns into lost revenue or excess inventory.\n\nThis skill goes beyond plugging numbers into a formula. It applies a structured inventory-planning workflow — demand analysis, lead-time modeling, safety stock calibration, and cash-vs-stockout tradeoff framing — to produce reorder recommendations operators can actually act on.\n\n---\n\n## Quick Reference\n\n| Decision | Key Signal | Strong | Acceptable | Weak |\n|---|---|---|---|---|\n| Demand estimation | Historical vs assumed | Uses actual sales data + trend/seasonality | Reasonable assumption documented | Made-up round number |\n| Safety stock | Risk calibration | Service-level-based (z-score × σ) | Days-of-cover heuristic | No safety stock or arbitrary buffer |\n| Lead time | Supplier reliability | Avg + variability modeled | Single estimate documented | Ignored or assumed instant |\n| Reorder point | Formula clarity | ROP = LT demand + safety stock, shown | Calculated but not explained | Just a number with no breakdown |\n| Order quantity | Constraint-aware | Accounts for MOQ, carton multiples, cash | Basic EOQ or demand × days | Arbitrary round number |\n| Risk framing | Actionable tradeoffs | Stockout cost vs carrying cost quantified | Risks named qualitatively | No risk discussion |\n\n---\n\n## Solves\n\nMost ecommerce teams get reorder planning wrong not because they lack data, but because:\n\n- **Gut-feel ordering** — buying \"about the same as last time\" without modeling demand changes\n- **Ignoring lead-time variability** — treating supplier lead time as fixed when it fluctuates 20–50%\n- **No safety stock logic** — either zero buffer (stockouts) or massive buffer (cash drag)\n- **Formula without context** — calculating ROP without explaining what drives it or when it breaks\n- **Missing constraints** — ignoring MOQs, carton multiples, storage limits, or cash flow\n- **No risk framing** — presenting a single number without showing the stockout vs overstock tradeoff\n- **Static calculations** — one-time number with no guidance on when to recalculate\n\nGoal: **Produce a reorder recommendation that an ops lead, buyer, or founder can act on today — with the math shown, assumptions visible, and risks framed.**\n\n---\n\n## Use when\n\n- You need a practical reorder point for a SKU or product group\n- Demand is growing, volatile, or seasonal\n- Lead time is long or unreliable\n- You want to reduce stockouts without overbuying cash-intensive inventory\n- A team needs to explain reorder logic to a buyer, founder, or ops lead\n- You're setting up initial reorder rules for a new product or supplier\n- Transitioning from gut-feel ordering to data-informed replenishment\n\n## Do not use when\n\n- You need a full supply-chain planning system or ERP implementation\n- Historical demand is too weak to support even rough assumptions\n- Supplier constraints are unknown and nobody can estimate them\n- The task is warehouse slotting or operations design rather than reorder planning\n- You need multi-echelon or multi-warehouse optimization\n\n---\n\n## Inputs\n\nGather these inputs — mark any gaps explicitly:\n\n**Demand data:**\n- Average daily or weekly unit sales (last 30/60/90 days)\n- Demand trend direction (growing / stable / declining)\n- Demand variability (standard deviation of daily sales, or coefficient of variation)\n- Known seasonality, promotions, or launches upcoming\n- Historical stockout periods (to adjust demand estimates)\n\n**Supply data:**\n- Supplier average lead time (order-to-receipt, in days)\n- Lead-time variability (best case / worst case / std dev)\n- Minimum order quantity (MOQ)\n- Carton multiples or packaging constraints\n- Supplier reliability notes (late shipment frequency, quality issues)\n\n**Inventory data:**\n- Current on-hand stock (units)\n- Current in-transit stock (units, ETA)\n- Storage capacity constraints\n- Current inventory carrying cost (% of COGS per year, or $/unit/month)\n\n**Business context:**\n- Target service level (e.g., 95%, 98%, 99%)\n- Stockout cost estimate (lost margin + customer impact)\n- Cash flow constraints or budget limits\n- Review cycle / reorder cadence (daily / weekly / monthly)\n- Product lifecycle stage (launch / growth / mature / clearance)\n\nSee `references/safety-stock-guide.md` for service level and z-score tables.\nSee `references/demand-analysis-guide.md` for demand estimation methods.\n\n---\n\n## Workflow\n\n### 1. Analyze demand pattern\n\nBefore calculating anything, understand the demand signal:\n\n```\nAverage daily demand: [X] units/day\nDemand std deviation: [σd] units/day\nTrend: [growing / stable / declining at Y% per period]\nSeasonality: [none / seasonal with peak in Z months]\nData quality: [strong (90+ days) / moderate (30–90 days) / weak (<30 days)]\n```\n\nIf demand data is weak, flag this prominently — the entire calculation depends on this input.\n\nSee `references/demand-analysis-guide.md` for methods to handle trend, seasonality, and sparse data.\n\n### 2. Model lead time\n\nSupplier lead time is rarely constant. Model both average and variability:\n\n```\nAverage lead time: [LT] days\nLead time std deviation: [σLT] days\nBest case: [X] days\nWorst case: [Y] days\nData source: [supplier quote / historical POs / assumption]\n```\n\n**Rule: If lead time is based on a supplier quote alone (not historical data), add 20–30% buffer. Suppliers are optimistic.**\n\n### 3. Calculate safety stock\n\nSafety stock bridges the gap between average expectations and real-world variability:\n\n**Method 1: Service-level approach (preferred when data exists)**\n```\nSS = z × √(LT × σd² + d² × σLT²)\n\nWhere:\nz = service level z-score (1.65 for 95%, 1.96 for 97.5%, 2.33 for 99%)\nLT = average lead time in days\nσd = standard deviation of daily demand\nd = average daily demand\nσLT = standard deviation of lead time in days\n```\n\n**Method 2: Days-of-cover heuristic (when data is limited)**\n```\nSS = average daily demand × safety days\n\nWhere safety days = typically 5–14 days depending on:\n- Lead time length (longer LT → more safety days)\n- Demand variability (higher variability → more safety days)\n- Stockout cost (higher cost → more safety days)\n```\n\nSee `references/safety-stock-guide.md` for z-score tables and method selection guidance.\n\n### 4. Calculate reorder point\n\n```\nROP = (average daily demand × average lead time) + safety stock\nROP = (d × LT) + SS\n```\n\nInterpret the result: \"When on-hand inventory drops to [ROP] units, place a new order.\"\n\nIf in-transit stock exists, use **effective inventory position**:\n```\nInventory position = on-hand + in-transit - backorders\nTrigger reorder when: inventory position ≤ ROP\n```\n\n### 5. Determine reorder quantity\n\n**Basic approach:**\n```\nReorder quantity = average daily demand × days of coverage target\n```\n\n**Constraint-adjusted approach:**\n```\nRaw quantity = demand × coverage days\nAdjusted for MOQ: max(raw quantity, MOQ)\nAdjusted for carton multiple: round up to nearest carton multiple\nAdjusted for cash: min(adjusted quantity, budget ÷ unit cost)\nAdjusted for storage: min(adjusted quantity, available storage)\n```\n\n**EOQ approach (when holding and ordering costs are known):**\n```\nEOQ = √(2 × annual demand × order cost / holding cost per unit per year)\n```\n\nSee `references/output-template.md` for the complete output format.\n\n### 6. Frame the risk tradeoffs\n\nEvery reorder decision involves tradeoffs. Make them visible:\n\n| Scenario | Stockout Risk | Cash Tied Up | Coverage |\n|---|---|---|---|\n| Conservative (ROP + 20%) | Very low | High | [X] days |\n| Recommended (ROP) | Low | Moderate | [Y] days |\n| Aggressive (ROP - 20%) | Moderate | Low | [Z] days |\n\nQuantify when possible:\n- \"Stockout of [X] days costs ~$[Y] in lost margin\"\n- \"Extra [X] units ties up $[Y] in cash for [Z] weeks\"\n\n### 7. Quality-check the recommendation\n\nBefore delivering, verify with `assets/reorder-checklist.md`:\n\n- Is the demand estimate based on data (not just a guess)?\n- Is lead-time variability accounted for?\n- Is safety stock calibrated to a service level or risk tolerance?\n- Does the reorder quantity respect MOQ and packaging constraints?\n- Are cash flow implications visible?\n- Are assumptions explicitly stated?\n- Is there guidance on when to recalculate?\n\n---\n\n## Output\n\nReturn a structured package (see `references/output-template.md`):\n\n1. **Assumptions table**\n   - Every input value with source and confidence level\n\n2. **Demand and lead-time model**\n   - Demand stats, trend, variability\n   - Lead time stats and variability\n\n3. **Reorder point calculation**\n   - Safety stock with method shown\n   - ROP with formula and plain-English interpretation\n\n4. **Reorder quantity recommendation**\n   - Raw quantity and constraint-adjusted quantity\n   - Cash impact estimate\n\n5. **Risk scenario table**\n   - Conservative / recommended / aggressive options\n   - Stockout risk and cash tradeoff for each\n\n6. **Action items and review triggers**\n   - When to place the next order\n   - When to recalculate (demand shift, supplier change, etc.)\n   - Sensitivity warnings\n\n---\n\n## Quality bar\n\nStrong output should:\n- Show the math AND explain it in plain English\n- Separate reorder point (when to order) from reorder quantity (how much)\n- Account for demand variability, not just averages\n- Account for lead-time variability, not just supplier quotes\n- Respect real-world constraints (MOQ, cash, storage)\n- Frame the stockout vs overstock tradeoff explicitly\n- Flag fragile assumptions that could change the recommendation\n\n## What \"better\" looks like\n\nBetter output helps the operator act with confidence:\n- Knows when to reorder (and understands why that number, not another)\n- Knows roughly how much to buy (and sees the tradeoff in buying more or less)\n- Sees the cash vs stockout tradeoff in concrete terms\n- Understands where lead-time risk changes the answer\n- Can explain the decision to a buyer, founder, or ops lead\n- Has clear triggers for when to recalculate\n\n---\n\n## Examples\n\n### Example 1: Growing DTC skincare brand\n\n**Inputs:**\n- Product: Vitamin C Serum 30ml\n- Average daily sales: 42 units/day (last 90 days, growing ~8%/month)\n- Daily demand std dev: 12 units\n- Unit cost: $8.50, selling price: $29.99\n- Supplier lead time: 21 days avg (std dev: 4 days)\n- MOQ: 500 units, carton multiple: 50\n- Current stock: 890 units, none in transit\n- Target service level: 95%\n- Review cadence: weekly\n\n**Output excerpt:**\n\n```\nDEMAND MODEL\nAvg daily demand: 42 units → adjusted for growth: 46 units/day (8%/mo trend)\nDemand σ: 12 units/day\nData quality: Strong (90 days, consistent)\n\nSAFETY STOCK (Service-level method, z=1.65 for 95%)\nSS = 1.65 × √(21 × 12² + 46² × 4²)\nSS = 1.65 × √(3024 + 33856)\nSS = 1.65 × 192\nSS = 317 units → round to 320\n\nREORDER POINT\nROP = (46 × 21) + 320 = 966 + 320 = 1,286 units\n\n⚠️ Current stock (890) is BELOW reorder point. Order now.\n\nREORDER QUANTITY\nTarget coverage: 30 days post-receipt\nRaw qty: 46 × 30 = 1,380 units\nAdjusted for MOQ: 1,380 (above 500 MOQ ✓)\nAdjusted for carton: 1,400 (nearest 50 multiple)\nCash required: 1,400 × $8.50 = $11,900\n\nRISK SCENARIOS\n| Scenario | Order Qty | Stockout Risk | Cash | Coverage |\n|---|---|---|---|---|\n| Conservative | 1,700 | <2% | $14,450 | 37 days |\n| Recommended | 1,400 | ~5% | $11,900 | 30 days |\n| Aggressive | 1,100 | ~12% | $9,350 | 24 days |\n```\n\n### Example 2: Seasonal product with unreliable supplier\n\n**Inputs:**\n- Product: Insulated water bottle\n- Average daily sales: 18 units/day (but seasonal: 30/day in summer, 8/day in winter)\n- Current month: April (ramping up)\n- Supplier lead time: 35 days avg, range: 28–50 days\n- MOQ: 200, unit cost: $6.20\n- Current stock: 520, 300 in transit (ETA 2 weeks)\n\n**Output excerpt:**\n\n```\nDEMAND MODEL\nCurrent avg: 18 units/day\nSeasonal forecast (next 60 days): ramping to ~25 units/day\nUsing forward estimate: 25 units/day\nDemand σ: 7 units/day (higher variability due to seasonal transition)\n\n⚠️ LEAD TIME WARNING\nAvg LT: 35 days, but range is 28–50 days (σLT ≈ 6 days)\nThis supplier has high variability — safety stock must account for this.\n\nSAFETY STOCK (z=1.65 for 95%)\nSS = 1.65 × √(35 × 49 + 625 × 36) = 1.65 × √(1715 + 22500) = 1.65 × 156 = 257 units\n\nREORDER POINT\nROP = (25 × 35) + 257 = 875 + 257 = 1,132 units\n\nINVENTORY POSITION\nOn-hand: 520 + in-transit: 300 = 820\n820 < 1,132 → ⚠️ Below ROP. Order immediately.\n\nDays until stockout (no reorder): 520 ÷ 25 = 20.8 days\nIn-transit arrives in ~14 days → post-arrival: (520 - 350) + 300 = 470 units\n470 ÷ 25 = 18.8 more days → ~33 days total before stockout\n\nACTION: Order now. Lead time of 35 days means new stock arrives just as\ncurrent + in-transit runs out. Any delay = stockout during peak season.\n```\n\n---\n\n## Common mistakes\n\n1. **Using averages without variability** — \"We sell 20/day\" ignores that some days are 8 and others are 35\n2. **Trusting supplier lead times** — Quoted lead times are best-case; actual delivery is often 20–50% longer\n3. **Forgetting in-transit inventory** — Reordering when stock is low but 1,000 units are already shipping\n4. **Ignoring MOQ and carton constraints** — Calculating a perfect 347-unit order when MOQ is 500\n5. **No cash flow context** — Recommending a $50K order to a business with $30K available\n6. **Static one-time calculation** — Giving a number without saying when it should be recalculated\n7. **Safety stock = gut feel** — Using \"2 weeks of safety stock\" without connecting it to demand variability\n8. **Not adjusting for trend** — Using historical averages for a product that's growing 15%/month\n\n---\n\n## Resources\n\n- `references/output-template.md` — Complete structured output template\n- `references/safety-stock-guide.md` — Service levels, z-scores, and safety stock methods\n- `references/demand-analysis-guide.md` — Demand estimation, trend adjustment, and seasonality handling\n- `assets/reorder-checklist.md` — Pre-delivery quality checklist\n\nFile v1.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn70fv0ehp50emedet9tx3fekd82pw3b\",\n  \"slug\": \"inventory-reorder-calculator\",\n  \"version\": \"1.1.0\",\n  \"publishedAt\": 1774869412109\n}\n\nFile v1.1.0:references/demand-analysis-guide.md\n\n# Demand Analysis Guide for Reorder Planning\n\nMethods for estimating demand when data quality varies — from strong historical data to sparse or noisy signals.\n\n---\n\n## Demand Estimation Methods\n\n### Method 1: Simple moving average (SMA)\n\n**Use when:** Demand is stable with no clear trend or seasonality.\n\n```\nAvg daily demand = sum of daily sales (last N days) ÷ N\n\nRecommended windows:\n- Fast-moving items (10+ units/day): 30 days\n- Moderate movers (2–10/day): 60 days\n- Slow movers (<2/day): 90 days\n```\n\n**Calculate variability:**\n```\nσd = √(Σ(daily sales − average)² ÷ (N − 1))\nCV (coefficient of variation) = σd ÷ average\n\nCV < 0.5: Low variability — averages are reliable\nCV 0.5–1.0: Moderate — safety stock matters\nCV > 1.0: High — lumpy demand, consider different approach\n```\n\n### Method 2: Trend-adjusted demand\n\n**Use when:** Product is clearly growing or declining.\n\n```\nStep 1: Calculate trailing average (last 30 days vs prior 30 days)\nStep 2: Growth rate = (recent avg − prior avg) ÷ prior avg\nStep 3: Forward estimate = recent avg × (1 + monthly growth rate)^(months ahead)\n```\n\n**Example:**\n```\nLast 30 days avg: 42 units/day\nPrior 30 days avg: 38 units/day\nGrowth rate: (42 − 38) ÷ 38 = 10.5% per month\nForward estimate (1 month): 42 × 1.105 = 46.4 units/day\nForward estimate (2 months): 42 × 1.105² = 51.3 units/day\n```\n\n**Warning:** Don't extrapolate growth beyond 2–3 months without additional validation. Growth rarely stays linear.\n\n### Method 3: Seasonal adjustment\n\n**Use when:** Demand has clear seasonal patterns (holiday, summer, back-to-school, etc.)\n\n```\nStep 1: Get same-period-last-year sales (SPLY)\nStep 2: Calculate year-over-year growth factor\nStep 3: Forward estimate = SPLY × YoY growth factor\n\nExample:\nLast June sales: 800 units\nThis vs last year overall growth: +25%\nJune forecast: 800 × 1.25 = 1,000 units → 33 units/day\n```\n\n**If no prior-year data:** Use industry seasonal indices or estimate peak-to-trough ratio from whatever data exists.\n\n### Method 4: Sparse / new product estimation\n\n**Use when:** <30 days of sales data, new product launch, or highly intermittent demand.\n\nOptions:\n1. **Analog method:** Use sales data from a similar product as proxy\n2. **Marketing-adjusted:** Pre-launch forecast × actual-vs-forecast ratio from previous launches\n3. **Conservative start:** Use the lower bound of any estimate, set a short review cycle (weekly), and adjust rapidly\n4. **Order-based:** If early orders are lumpy (wholesale/B2B), separate wholesale from DTC demand\n\n**Rule: With weak data, shorten the review cycle. Don't compensate by adding massive safety stock — you'll tie up cash on an unproven product.**\n\n---\n\n## Adjusting for Data Quality Issues\n\n### Stockout periods in historical data\n\nIf the product was out of stock during your measurement window, raw sales underestimate true demand.\n\n```\nAdjustment:\n1. Identify stockout days (zero sales + zero inventory)\n2. Remove stockout days from the average calculation\n3. Or: estimate lost sales = avg daily demand × stockout days\n```\n\n**Example:**\n```\n90-day window, 12 days out of stock\nRecorded sales: 2,340 units\nNaive average: 2,340 ÷ 90 = 26/day\nAdjusted average: 2,340 ÷ 78 = 30/day ← use this\n```\n\n### Promotional spikes\n\nIf the measurement window includes a major promotion, separate organic from promoted demand:\n\n```\n1. Identify promotion days\n2. Calculate avg during promo and avg outside promo\n3. Use non-promo average for baseline demand\n4. Add promo impact separately if another promotion is planned\n```\n\n### Return rate adjustment\n\nFor products with significant return rates:\n\n```\nNet demand = gross sales × (1 − return rate)\nUse net demand for reorder planning\n```\n\n---\n\n## Demand Classification\n\nClassify products to select the right method:\n\n| Pattern | Characteristics | Best Method | Safety Stock Approach |\n|---|---|---|---|\n| **Smooth** | CV < 0.5, consistent daily sales | SMA or trend-adjusted | Standard formula (Method 1) |\n| **Erratic** | CV 0.5–1.0, variable but regular | SMA with longer window | Higher service level or days-of-cover |\n| **Lumpy** | CV > 1.0, intermittent large orders | Separate B2B from DTC | Days-of-cover + manual review |\n| **Seasonal** | Clear peaks and troughs | Seasonal adjustment | Adjust by season, peak needs more |\n| **New/Launch** | <30 days data | Analog or conservative | Minimal stock + weekly review |\n\n---\n\n## When to Recalculate Demand Estimates\n\n| Trigger | Action |\n|---|---|\n| Monthly (routine) | Refresh SMA with latest 30/60/90 days |\n| Demand shifts >15% | Investigate cause, update forward estimate |\n| New promotion planned | Build separate promo demand estimate |\n| Seasonal transition | Switch to seasonal method, update SPLY |\n| Stockout occurred | Adjust historical data, review safety stock |\n| New sales channel added | Separate channel demand, recalculate total |\n| Product entering decline | Shorten measurement window, reduce forward estimate |\n\nFile v1.1.0:references/output-template.md\n\n# Inventory Reorder Calculator Output Template\n\nStructure every reorder recommendation with this format:\n\n---\n\n## Assumptions\n\n| Variable | Value | Source | Confidence |\n|---|---|---|---|\n| Average daily demand | [X] units/day | [Sales data, last N days] | [High / Medium / Low] |\n| Demand std deviation | [σd] units/day | [Calculated from data / estimated] | [High / Medium / Low] |\n| Demand trend | [Growing / Stable / Declining at Y%] | [Data trend / assumption] | [High / Medium / Low] |\n| Supplier lead time | [LT] days | [Historical POs / supplier quote] | [High / Medium / Low] |\n| Lead time std deviation | [σLT] days | [Historical / estimated] | [High / Medium / Low] |\n| Unit cost (landed) | $[X] | [Invoice / quote] | [High / Medium / Low] |\n| Target service level | [X]% | [Business decision] | — |\n| MOQ | [X] units | [Supplier terms] | [High / Medium / Low] |\n| Carton multiple | [X] units | [Supplier / 3PL spec] | [High / Medium / Low] |\n| Review cadence | [Daily / Weekly / Monthly] | [Current process] | — |\n\n---\n\n## Demand Model\n\n```\nAverage daily demand: [X] units/day\nAdjusted for trend: [Y] units/day (if applicable)\nDemand σ: [σd] units/day\nCoefficient of variation: [CV = σd/d] → [low (<0.5) / moderate (0.5–1.0) / high (>1.0)]\nData quality: [Strong / Moderate / Weak] — based on [X] days of history\nSeasonality: [None / Peak in X months / Currently in peak]\n```\n\n⚠️ [Flag any demand-data concerns here]\n\n---\n\n## Lead Time Model\n\n```\nAverage lead time: [LT] days\nLead time σ: [σLT] days\nBest case: [X] days\nWorst case: [Y] days\nSource: [Historical POs (N orders) / Supplier quote / Assumption]\n```\n\n⚠️ [Flag any lead-time concerns here — e.g., supplier based in region with holiday shutdowns, port congestion, etc.]\n\n---\n\n## Safety Stock Calculation\n\n**Method used:** [Service-level / Days-of-cover heuristic]\n\n```\n[Show formula and calculation step by step]\n\nService level: [X]% → z-score: [Z]\nSS = z × √(LT × σd² + d² × σLT²)\nSS = [Z] × √([LT] × [σd]² + [d]² × [σLT]²)\nSS = [Z] × √([A] + [B])\nSS = [Z] × [C]\nSS = [result] units → rounded to [final] units\n```\n\nPlain English: \"Keep [X] units as a buffer to maintain [Y]% chance of not stocking out during a replenishment cycle.\"\n\n---\n\n## Reorder Point\n\n```\nROP = Lead Time Demand + Safety Stock\nROP = (d × LT) + SS\nROP = ([d] × [LT]) + [SS]\nROP = [LTD] + [SS]\nROP = [result] units\n```\n\n**Interpretation:** \"When your inventory position (on-hand + in-transit − backorders) drops to **[ROP] units**, place a new purchase order.\"\n\n### Current Status\n```\nOn-hand: [X] units\nIn-transit: [Y] units (ETA: [date])\nInventory position: [X + Y] units\nROP: [Z] units\nStatus: [✅ Above ROP — no action needed / ⚠️ Below ROP — order now / 🚨 Critical — days to stockout: N]\n```\n\n---\n\n## Reorder Quantity\n\n```\nTarget coverage: [X] days post-receipt\nRaw quantity: [d] × [coverage days] = [Q] units\n```\n\n**Constraint adjustments:**\n| Constraint | Adjustment | Result |\n|---|---|---|\n| MOQ ([X] units) | [Above / rounded up] | [Q'] units |\n| Carton multiple ([X] units) | [Rounded up to nearest] | [Q''] units |\n| Cash available ($[X]) | [Within / exceeds budget] | [Q'''] units |\n| Storage capacity | [Within / exceeds limit] | [Final Q] units |\n\n**Final recommended order: [Final Q] units**\n**Estimated cost: $[Final Q × unit cost]**\n\n---\n\n## Risk Scenario Table\n\n| Scenario | Order Qty | Safety Stock | Stockout Risk | Cash Tied Up | Coverage Post-Receipt |\n|---|---|---|---|---|---|\n| Conservative (+20% SS) | [Q] | [SS×1.2] | [X]% | $[Y] | [Z] days |\n| **Recommended** | **[Q]** | **[SS]** | **[X]%** | **$[Y]** | **[Z] days** |\n| Aggressive (−20% SS) | [Q] | [SS×0.8] | [X]% | $[Y] | [Z] days |\n\n**Stockout cost context:** [X] days of stockout ≈ $[Y] in lost gross margin + [qualitative impact: review damage, ad waste, etc.]\n**Carrying cost context:** [X] extra units ≈ $[Y]/month in holding cost\n\n---\n\n## Action Items\n\n**Immediate:**\n- [ ] [Place PO for X units / No action needed — next review on DATE]\n- [ ] [Confirm lead time with supplier before ordering]\n- [ ] [Review in-transit shipment status]\n\n**Recalculate when:**\n- Demand shifts >15% from current average\n- Supplier lead time changes significantly\n- Upcoming promotion or seasonal shift (recalculate 1 lead time in advance)\n- After a stockout event (review safety stock adequacy)\n- [Specific trigger for this product]\n\n**Sensitivity warnings:**\n- [Which assumptions, if wrong, change the recommendation most?]\n- [What's the breakeven point where conservative vs aggressive flips?]\n- [Any upcoming events that could disrupt this calculation?]\n\nFile v1.1.0:references/safety-stock-guide.md\n\n# Safety Stock Guide\n\nFramework for calculating safety stock based on service level targets, demand variability, and lead time uncertainty.\n\n---\n\n## Service Level and Z-Score Table\n\nThe service level represents the probability of NOT stocking out during a replenishment cycle.\n\n| Service Level | Z-Score | When to Use |\n|---|---|---|\n| 85% | 1.04 | Low-value items, easy to substitute, minimal stockout cost |\n| 90% | 1.28 | Standard items, moderate substitution risk |\n| 95% | 1.65 | Important SKUs, meaningful revenue impact from stockout |\n| 97.5% | 1.96 | High-value items, significant customer impact |\n| 98% | 2.05 | Key products, brand-critical items |\n| 99% | 2.33 | Mission-critical, no acceptable substitute, hero SKUs |\n| 99.5% | 2.58 | Life-safety or contractual obligation items |\n| 99.9% | 3.09 | Extreme — rarely justified in ecommerce |\n\n### How to choose a service level\n\nAsk these questions:\n\n1. **What happens if this product stocks out?**\n   - Customer buys from competitor → higher service level (97%+)\n   - Customer waits or substitutes → moderate (90–95%)\n   - No significant impact → lower (85–90%)\n\n2. **What's the margin on this product?**\n   - High margin → can afford more safety stock\n   - Low margin → excess inventory cost matters more\n\n3. **How long is the lead time?**\n   - Long lead time → higher service level to compensate\n   - Short lead time (< 7 days) → lower service level acceptable\n\n4. **Is demand predictable?**\n   - Stable, predictable → lower service level works\n   - Volatile or seasonal → need higher service level\n\n---\n\n## Safety Stock Formulas\n\n### Method 1: Combined demand and lead-time variability (preferred)\n\nUse when you have data on both demand variability AND lead-time variability:\n\n```\nSS = z × √(LT × σd² + d² × σLT²)\n\nWhere:\nz = z-score from service level table\nLT = average lead time (days)\nσd = standard deviation of daily demand\nd = average daily demand\nσLT = standard deviation of lead time (days)\n```\n\n**Example:**\n```\nz = 1.65 (95% service level)\nLT = 14 days\nσd = 5 units/day\nd = 30 units/day\nσLT = 3 days\n\nSS = 1.65 × √(14 × 25 + 900 × 9)\nSS = 1.65 × √(350 + 8100)\nSS = 1.65 × √8450\nSS = 1.65 × 91.9\nSS = 152 units\n```\n\n### Method 2: Demand variability only\n\nUse when lead time is reliable (σLT ≈ 0):\n\n```\nSS = z × σd × √LT\n```\n\n**Example:**\n```\nz = 1.65, σd = 5, LT = 14\nSS = 1.65 × 5 × √14 = 1.65 × 5 × 3.74 = 31 units\n```\n\nNote: This gives MUCH less safety stock than Method 1. Only use if supplier lead time is truly consistent.\n\n### Method 3: Days-of-cover heuristic\n\nUse when you don't have good variability data:\n\n```\nSS = average daily demand × safety days\n```\n\n| Situation | Safety Days | Rationale |\n|---|---|---|\n| Short, reliable lead time (<7d) | 3–5 days | Low risk, quick recovery |\n| Moderate lead time (7–21d) | 7–10 days | Standard buffer |\n| Long lead time (21–45d) | 10–14 days | Significant exposure |\n| Long + unreliable lead time | 14–21 days | High risk, slow recovery |\n| Seasonal peak approaching | Add 5–7 days | Demand uncertainty increasing |\n\n**Limitation:** This method doesn't account for actual variability. It's a starting point, not a precision tool.\n\n### Method 4: Max–average method\n\nUse as a quick sanity check:\n\n```\nSS = (max daily demand × max lead time) − (avg daily demand × avg lead time)\n```\n\nThis represents the worst-case gap. It's usually too conservative but useful as an upper bound.\n\n---\n\n## Common Safety Stock Mistakes\n\n1. **Using σ of weekly data for a daily formula** — Make sure demand σ matches the time unit. If using weekly​σ, divide by √7 for daily.\n\n2. **Ignoring lead-time variability** — If you only model demand variability, you'll underestimate safety stock by 30–60% for suppliers with inconsistent delivery.\n\n3. **Setting safety stock once and forgetting** — Demand and lead times change. Recalculate quarterly at minimum.\n\n4. **Same service level for all SKUs** — Hero products deserve 98%+. Slow movers might need only 85%.\n\n5. **Confusing service level types** — Cycle service level (% of cycles without stockout) .≠ fill rate (% of units shipped on time). This guide uses cycle service level.\n\n6. **Not accounting for demand during review period** — If you review inventory weekly, add the review period to lead time in the formula: use (LT + review period) instead of just LT.\n\n---\n\n## Carrying Cost Reference\n\nSafety stock ties up cash. Here's a rough guide to annual carrying cost:\n\n| Cost Component | Typical Range | Notes |\n|---|---|---|\n| Cost of capital | 8–15% | Opportunity cost of cash tied in inventory |\n| Storage / warehousing | 2–5% | 3PL fees, rent allocation |\n| Insurance | 0.5–1% | Inventory insurance premiums |\n| Shrinkage / obsolescence | 2–5% | Damage, expiry, write-offs |\n| **Total carrying cost** | **12–25%** | **Of COGS per year** |\n\n**Quick calculation:**\n```\nMonthly carrying cost per unit = unit cost × annual carrying rate ÷ 12\nExample: $8.50 × 20% ÷ 12 = $0.14/unit/month\nSafety stock of 300 units = $42/month in carrying cost\n```\n\nCompare this to stockout cost to validate your service level choice.\n\nFile v1.1.0:assets/reorder-checklist.md\n\n# Reorder Recommendation Quality Checklist\n\nBefore delivering a reorder recommendation, verify each item:\n\n---\n\n## Demand estimation\n- [ ] Demand average based on actual sales data (not guess)?\n- [ ] Measurement window appropriate for velocity (30/60/90 days)?\n- [ ] Demand variability (σ or CV) calculated or estimated?\n- [ ] Stockout periods excluded or adjusted in historical data?\n- [ ] Trend accounted for (growing/declining products)?\n- [ ] Seasonality considered if relevant?\n- [ ] Promotional spikes separated from organic demand?\n\n## Lead time modeling\n- [ ] Lead time sourced from historical POs (not just supplier quote)?\n- [ ] Lead-time variability accounted for (σLT or range)?\n- [ ] Buffer added if using supplier quote only (+20–30%)?\n- [ ] Upcoming disruptions flagged (holidays, port congestion, etc.)?\n\n## Safety stock\n- [ ] Safety stock method stated (service-level vs days-of-cover)?\n- [ ] Service level appropriate for product importance?\n- [ ] Formula shown with intermediate steps?\n- [ ] Both demand AND lead-time variability included?\n- [ ] Result sanity-checked (not obviously too high or low)?\n- [ ] Plain-English interpretation provided?\n\n## Reorder point\n- [ ] ROP = lead time demand + safety stock (formula shown)?\n- [ ] In-transit inventory accounted for in position calculation?\n- [ ] Current inventory position compared to ROP?\n- [ ] Clear status: above ROP / below ROP / critical?\n- [ ] Days to stockout estimated if below ROP?\n\n## Reorder quantity\n- [ ] Coverage period stated and justified?\n- [ ] MOQ constraint respected?\n- [ ] Carton / packaging multiples applied?\n- [ ] Cash impact calculated (units × unit cost)?\n- [ ] Storage capacity checked?\n- [ ] EOQ considered if ordering/holding costs available?\n\n## Risk and tradeoffs\n- [ ] Conservative / recommended / aggressive scenarios shown?\n- [ ] Stockout risk quantified or described for each?\n- [ ] Cash tied up shown for each scenario?\n- [ ] Stockout cost vs carrying cost framed?\n- [ ] No false precision (ranges shown where appropriate)?\n\n## Assumptions and transparency\n- [ ] Every input value has a stated source?\n- [ ] Confidence level flagged (high / medium / low)?\n- [ ] Fragile assumptions called out explicitly?\n- [ ] \"If X changes, recalculate\" triggers listed?\n\n## Actionability\n- [ ] Clear next step (order now / wait until DATE / review in X days)?\n- [ ] Recommendation can be executed without further analysis?\n- [ ] Operator can explain the logic to a buyer or founder?\n- [ ] Review cadence recommended?\n\n## Common error check\n- [ ] Not using weekly σ in a daily formula (units match)?\n- [ ] Not confusing on-hand with inventory position?\n- [ ] Not recommending below MOQ?\n- [ ] Not ignoring in-transit stock?\n- [ ] Not extrapolating growth beyond 2–3 months?\n- [ ] Numbers pass a gut check (not absurdly high or low)?\n\nFile v1.1.0:skill-card.md\n\n## Description:\n\nEstimate ecommerce reorder timing and quantity using demand, lead time, and safety stock assumptions so teams can set reorder points and reduce stockout risk with less guesswork.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[leooooooow](https://clawhub.ai/user/leooooooow)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nEcommerce operators, buyers, founders, and inventory teams use this skill to calculate reorder points and purchase quantities for SKUs or product groups. It helps turn demand, lead-time, safety-stock, MOQ, cash, and storage assumptions into an actionable reorder recommendation with visible tradeoffs.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Reorder recommendations can affect purchasing decisions, stockout exposure, and cash flow.\n\nMitigation: Review assumptions, formulas, supplier inputs, cash constraints, and final quantities before acting on the recommendation.\n\nRisk: Weak demand history, supplier quotes, or unmodeled lead-time variability can make the calculated reorder point fragile.\n\nMitigation: Flag low-confidence inputs, account for demand and lead-time variability, and recalculate when demand shifts, supplier lead time changes, promotions occur, or stockouts happen.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/leooooooow/skills/inventory-reorder-calculator)\n- [Demand Analysis Guide for Reorder Planning](references/demand-analysis-guide.md)\n- [Safety Stock Guide](references/safety-stock-guide.md)\n- [Inventory Reorder Calculator Output Template](references/output-template.md)\n- [Reorder Recommendation Quality Checklist](assets/reorder-checklist.md)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, guidance]\n\n**Output Format:** [Structured Markdown with tables, formulas, action items, and review triggers]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Shows assumptions, demand and lead-time models, safety stock, reorder point, reorder quantity, risk scenarios, and recalculation triggers.]\n\n## Skill Version(s):\n\n1.1.0 (source: release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.0.2: 3 files, 1872 bytes\n\nFiles: references/output-template.md (438b), SKILL.md (2270b), _meta.json (147b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: inventory-reorder-calculator\ndescription: Estimate ecommerce reorder timing and quantity using demand, lead time, and safety stock assumptions so teams can set reorder points and reduce stockout risk with less guesswork.\n---\n\n# Inventory Reorder Calculator\n\nEstimate when to reorder and how much to buy before stock risk turns into lost revenue or excess inventory.\n\n## Use when\n\n- You need a practical reorder point for a SKU\n- Demand is growing, volatile, or seasonal\n- Lead time is long or unreliable\n- You want to reduce stockouts without overbuying cash-intensive inventory\n\n## Do not use when\n\n- You need a full supply-chain planning system or ERP implementation\n- Historical demand is too weak to support even rough assumptions\n- Supplier constraints are unknown and nobody can estimate them\n- The task is warehouse slotting or operations design rather than reorder planning\n\n## Inputs\n\n- current on-hand inventory\n- average daily or weekly demand\n- demand variability if known\n- supplier lead time and lead-time variability\n- safety stock target or service-level preference\n- MOQ, carton multiple, or purchase constraints\n- review cycle / reorder cadence\n- optional promo, launch, or seasonality assumptions\n\n## Workflow\n\n1. Estimate demand during lead time.\n2. Add safety stock based on uncertainty and risk tolerance.\n3. Calculate reorder point.\n4. Estimate recommended reorder quantity using demand, cadence, and purchasing constraints.\n5. Flag stockout risk, overstock risk, and assumption sensitivity.\n\n## Output\n\n1. Assumptions table\n2. Reorder point\n3. Recommended reorder quantity\n4. Stock-risk summary\n5. Notes on sensitivity and next decision steps\n\n## Quality bar\n\n- Must clearly separate reorder point from reorder quantity\n- Must show the impact of lead time and demand uncertainty\n- Should support daily operating decisions, not just formula display\n- Should call out where assumptions are fragile\n\n## What better looks like\n\nBetter output helps the operator act with confidence:\n- knows when to reorder\n- knows roughly how much to buy\n- sees the cash vs stockout tradeoff\n- understands where lead-time risk changes the answer\n- can explain the decision to a buyer, founder, or ops lead\n\n## Resource\n\nSee `references/output-template.md`.\n\nFile v1.0.2:_meta.json\n\n{\n  \"ownerId\": \"kn70fv0ehp50emedet9tx3fekd82pw3b\",\n  \"slug\": \"inventory-reorder-calculator\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1774513986422\n}\n\nFile v1.0.2:references/output-template.md\n\n# Inventory Reorder Calculator Output Template\n\n## 1) Assumptions\n| Variable | Value | Notes |\n|---|---|---|\n\n## 2) Demand and stock model\n- Current stock:\n- Avg daily sales:\n- Lead time demand:\n- Safety stock:\n- Reorder point:\n\n## 3) Reorder suggestion\n- Suggested reorder quantity:\n- Estimated coverage after reorder:\n- MOQ / packaging constraint note:\n\n## 4) Risk notes\n- Stockout risk:\n- Overstock / cash drag risk:\n- Recommendation:\n\nArchive v1.0.1: 3 files, 2086 bytes\n\nFiles: references/output-template.md (438b), SKILL.md (2215b), _meta.json (147b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: inventory-reorder-calculator\ndescription: Estimate ecommerce reorder timing and quantity using demand, lead time, and safety stock assumptions. Use when operators need a practical reorder point instead of guesswork.\n---\n\n# Inventory Reorder Calculator\n\n补货不是“快没了再下单”，而是提前算出风险和时间窗口。\n\n## 先交互，再计算\n\n开始时先问：\n1. 你们现在想算的是：\n   - reorder point\n   - reorder quantity\n   - stockout risk window\n   - 大促前备货量\n2. 你们平时怎么设 safety stock？\n3. lead time 是固定值还是波动区间？\n4. 是否要考虑 MOQ、现金约束、季节性或活动影响？\n5. 要沿用现有逻辑，还是让我给推荐补货框架？\n\n## Python script guidance\n\n当用户给出结构化数据后：\n- 生成 Python 脚本完成补货点 / 补货量计算\n- 展示需求、交期、安全库存假设\n- 输出风险区间\n- 返回可复用脚本\n\n## 解决的问题\n\n很多库存问题不是不会卖，而是：\n- 卖太快，断货；\n- 下太多，压现金；\n- lead time 一波动，计划就失真；\n- 没有 safety stock，运营靠感觉补货。\n\n这个 skill 的目标是：\n**根据销量、库存、交期和安全库存，算出更稳妥的 reorder point 和建议补货量。**\n\n## 何时使用\n\n- SKU 在快速增长或大促前；\n- 供应链 lead time 不稳定；\n- 需要在不断货和不压货之间找平衡。\n\n## 输入要求\n\n- 当前库存\n- 日均销量 / 周均销量\n- 供应商 lead time\n- MOQ / 包装倍数\n- 安全库存目标\n- 可选：季节性、大促、补货周期限制\n\n## 工作流\n\n1. 明确补货逻辑和风险目标。\n2. 估算补货周期内需求。\n3. 加上安全库存缓冲。\n4. 计算 reorder point。\n5. 给出建议补货量和风险提示。\n6. 返回可复用 Python 脚本。\n\n## 输出格式\n\n1. 假设表\n2. Reorder point\n3. 建议补货量\n4. 风险区间与建议\n5. Python 脚本\n\n## 质量标准\n\n- 明确写出交期和需求假设。\n- 区分补货点和补货量。\n- 能支持日常运营决策，而不是只给公式。\n- 对波动风险有提醒。\n- 未确认口径前不假装精确。\n\n## 资源\n\n参考 `references/output-template.md`。\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn70fv0ehp50emedet9tx3fekd82pw3b\",\n  \"slug\": \"inventory-reorder-calculator\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1773840144145\n}\n\nFile v1.0.1:references/output-template.md\n\n# Inventory Reorder Calculator Output Template\n\n## 1) Assumptions\n| Variable | Value | Notes |\n|---|---|---|\n\n## 2) Demand and stock model\n- Current stock:\n- Avg daily sales:\n- Lead time demand:\n- Safety stock:\n- Reorder point:\n\n## 3) Reorder suggestion\n- Suggested reorder quantity:\n- Estimated coverage after reorder:\n- MOQ / packaging constraint note:\n\n## 4) Risk notes\n- Stockout risk:\n- Overstock / cash drag risk:\n- Recommendation:\n\nArchive v1.0.0: 3 files, 1722 bytes\n\nFiles: references/output-template.md (438b), SKILL.md (1484b), _meta.json (147b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: inventory-reorder-calculator\ndescription: Estimate ecommerce reorder timing and quantity using demand, lead time, and safety stock assumptions. Use when operators need a practical reorder point instead of guesswork.\n---\n\n# Inventory Reorder Calculator\n\n补货不是“快没了再下单”，而是提前算出风险和时间窗口。\n\n## 解决的问题\n\n很多库存问题不是不会卖，而是：\n- 卖太快，断货；\n- 下太多，压现金；\n- lead time 一波动，计划就失真；\n- 没有 safety stock，运营靠感觉补货。\n\n这个 skill 的目标是：\n**根据销量、库存、交期和安全库存，算出更稳妥的 reorder point 和建议补货量。**\n\n## 何时使用\n\n- SKU 在快速增长或大促前；\n- 供应链 lead time 不稳定；\n- 需要在不断货和不压货之间找平衡。\n\n## 输入要求\n\n- 当前库存\n- 日均销量 / 周均销量\n- 供应商 lead time\n- MOQ / 包装倍数\n- 安全库存目标\n- 可选：季节性、大促、补货周期限制\n\n## 工作流\n\n1. 估算补货周期内需求。\n2. 加上安全库存缓冲。\n3. 计算 reorder point。\n4. 给出建议补货量和风险提示。\n\n## 输出格式\n\n1. 假设表\n2. Reorder point\n3. 建议补货量\n4. 风险区间与建议\n\n## 质量标准\n\n- 明确写出交期和需求假设。\n- 区分补货点和补货量。\n- 能支持日常运营决策，而不是只给公式。\n- 对波动风险有提醒。\n\n## 资源\n\n参考 `references/output-template.md`。\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn70fv0ehp50emedet9tx3fekd82pw3b\",\n  \"slug\": \"inventory-reorder-calculator\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1773659366451\n}\n\nFile v1.0.0:references/output-template.md\n\n# Inventory Reorder Calculator Output Template\n\n## 1) Assumptions\n| Variable | Value | Notes |\n|---|---|---|\n\n## 2) Demand and stock model\n- Current stock:\n- Avg daily sales:\n- Lead time demand:\n- Safety stock:\n- Reorder point:\n\n## 3) Reorder suggestion\n- Suggested reorder quantity:\n- Estimated coverage after reorder:\n- MOQ / packaging constraint note:\n\n## 4) Risk notes\n- Stockout risk:\n- Overstock / cash drag risk:\n- Recommendation:","readmeExcerpt":"Skill: Inventory Reorder Calculator Owner: leooooooow Summary: Estimate ecommerce reorder timing and quantity using demand, lead time, and safety stock assumptions so teams can set reorder points and reduce stockout risk... Tags: latest:1.1.0 Version history: v1.1.0 | 2026-03-30T11:16:52.109Z | user Major upgrade: Added 3 new reference files (safety-stock-guide, demand-analysis-guide, reorder-checklist). Expanded SKI","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"Average daily demand: [X] units/day\nDemand std deviation: [σd] units/day\nTrend: [growing / stable / declining at Y% per period]\nSeasonality: [none / seasonal with peak in Z months]\nData quality: [strong (90+ days) / moderate (30–90 days) / weak (<30 days)]"},{"language":"text","snippet":"Average lead time: [LT] days\nLead time std deviation: [σLT] days\nBest case: [X] days\nWorst case: [Y] days\nData source: [supplier quote / historical POs / assumption]"},{"language":"text","snippet":"SS = z × √(LT × σd² + d² × σLT²)\n\nWhere:\nz = service level z-score (1.65 for 95%, 1.96 for 97.5%, 2.33 for 99%)\nLT = average lead time in days\nσd = standard deviation of daily demand\nd = average daily demand\nσLT = standard deviation of lead time in days"},{"language":"text","snippet":"SS = average daily demand × safety days\n\nWhere safety days = typically 5–14 days depending on:\n- Lead time length (longer LT → more safety days)\n- Demand variability (higher variability → more safety days)\n- Stockout cost (higher cost → more safety days)"},{"language":"text","snippet":"ROP = (average daily demand × average lead time) + safety stock\nROP = (d × LT) + SS"},{"language":"text","snippet":"Inventory position = on-hand + in-transit - backorders\nTrigger reorder when: inventory position ≤ ROP"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: inventory-reorder-calculator\ndescription: Estimate ecommerce reorder timing and quantity using demand, lead time, and safety stock assumptions so teams can set reorder points and reduce stockout risk with less guesswork.\n---\n\n# Inventory Reorder Calculator\n\nEstimate when to reorder and how much to buy before stock risk turns into lost revenue or excess inventory.\n\nThis skill goes beyond plugging numbers into a formula. It applies a structured inventory-planning workflow — demand analysis, lead-time modeling, safety stock calibration, and cash-vs-stockout tradeoff framing — to produce reorder recommendations operators can actually act on.\n\n---\n\n## Quick Reference\n\n| Decision | Key Signal | Strong | Acceptable | Weak |\n|---|---|---|---|---|\n| Demand estimation | Historical vs assumed | Uses actual sales data + trend/seasonality | Reasonable assumption documented | Made-up round number |\n| Safety stock | Risk calibration | Service-level-based (z-score × σ) | Days-of-cover heuristic | No safety stock or arbitrary buffer |\n| Lead time | Supplier reliability | Avg + variability modeled | Single estimate documented | Ignored or assumed instant |\n| Reorder point | Formula clarity | ROP = LT demand + safety stock, shown | Calculated but not explained | Just a number with no breakdown |\n| Order quantity | Constraint-aware | Accounts for MOQ, carton multiples, cash | Basic EOQ or demand × days | Arbitrary round number |\n| Risk framing | Actionable tradeoffs | Stockout cost vs carrying cost quantified | Risks named qualitatively | No risk discussion |\n\n---\n\n## Solves\n\nMost ecommerce teams get reorder planning wrong not because they lack data, but because:\n\n- **Gut-feel ordering** — buying \"about the same as last time\" without modeling demand changes\n- **Ignoring lead-time variability** — treating supplier lead time as fixed when it fluctuates 20–50%\n- **No safety stock logic** — either zero buffer (stockouts) or massive buffer (cash drag)\n- **Formula without context** — calculating ROP without explaining what drives it or when it breaks\n- **Missing constraints** — ignoring MOQs, carton multiples, storage limits, or cash flow\n- **No risk framing** — presenting a single number without showing the stockout vs overstock tradeoff\n- **Static calculations** — one-time number with no guidance on when to recalculate\n\nGoal: **Produce a reorder recommendation that an ops lead, buyer, or founder can act on today — with the math shown, assumptions visible, and risks framed.**\n\n---\n\n## Use when\n\n- You need a practical reorder point for a SKU or product group\n- Demand is growing, volatile, or seasonal\n- Lead time is long or unreliable\n- You want to reduce stockouts without overbuying cash-intensive inventory\n- A team needs to explain reorder logic to a buyer, founder, or ops lead\n- You're setting up initial reorder rules for a new product or supplier\n- Transitioning from gut-feel ordering to data-informed replenishment\n\n## Do not use when\n\n- You need a full suppl"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn70fv0ehp50emedet9tx3fekd82pw3b\",\n  \"slug\": \"inventory-reorder-calculator\",\n  \"version\": \"1.1.0\",\n  \"publishedAt\": 1774869412109\n}"},{"path":"references/demand-analysis-guide.md","content":"# Demand Analysis Guide for Reorder Planning\n\nMethods for estimating demand when data quality varies — from strong historical data to sparse or noisy signals.\n\n---\n\n## Demand Estimation Methods\n\n### Method 1: Simple moving average (SMA)\n\n**Use when:** Demand is stable with no clear trend or seasonality.\n\n```\nAvg daily demand = sum of daily sales (last N days) ÷ N\n\nRecommended windows:\n- Fast-moving items (10+ units/day): 30 days\n- Moderate movers (2–10/day): 60 days\n- Slow movers (<2/day): 90 days\n```\n\n**Calculate variability:**\n```\nσd = √(Σ(daily sales − average)² ÷ (N − 1))\nCV (coefficient of variation) = σd ÷ average\n\nCV < 0.5: Low variability — averages are reliable\nCV 0.5–1.0: Moderate — safety stock matters\nCV > 1.0: High — lumpy demand, consider different approach\n```\n\n### Method 2: Trend-adjusted demand\n\n**Use when:** Product is clearly growing or declining.\n\n```\nStep 1: Calculate trailing average (last 30 days vs prior 30 days)\nStep 2: Growth rate = (recent avg − prior avg) ÷ prior avg\nStep 3: Forward estimate = recent avg × (1 + monthly growth rate)^(months ahead)\n```\n\n**Example:**\n```\nLast 30 days avg: 42 units/day\nPrior 30 days avg: 38 units/day\nGrowth rate: (42 − 38) ÷ 38 = 10.5% per month\nForward estimate (1 month): 42 × 1.105 = 46.4 units/day\nForward estimate (2 months): 42 × 1.105² = 51.3 units/day\n```\n\n**Warning:** Don't extrapolate growth beyond 2–3 months without additional validation. Growth rarely stays linear.\n\n### Method 3: Seasonal adjustment\n\n**Use when:** Demand has clear seasonal patterns (holiday, summer, back-to-school, etc.)\n\n```\nStep 1: Get same-period-last-year sales (SPLY)\nStep 2: Calculate year-over-year growth factor\nStep 3: Forward estimate = SPLY × YoY growth factor\n\nExample:\nLast June sales: 800 units\nThis vs last year overall growth: +25%\nJune forecast: 800 × 1.25 = 1,000 units → 33 units/day\n```\n\n**If no prior-year data:** Use industry seasonal indices or estimate peak-to-trough ratio from whatever data exists.\n\n### Method 4: Sparse / new product estimation\n\n**Use when:** <30 days of sales data, new product launch, or highly intermittent demand.\n\nOptions:\n1. **Analog method:** Use sales data from a similar product as proxy\n2. **Marketing-adjusted:** Pre-launch forecast × actual-vs-forecast ratio from previous launches\n3. **Conservative start:** Use the lower bound of any estimate, set a short review cycle (weekly), and adjust rapidly\n4. **Order-based:** If early orders are lumpy (wholesale/B2B), separate wholesale from DTC demand\n\n**Rule: With weak data, shorten the review cycle. Don't compensate by adding massive safety stock — you'll tie up cash on an unproven product.**\n\n---\n\n## Adjusting for Data Quality Issues\n\n### Stockout periods in historical data\n\nIf the product was out of stock during your measurement window, raw sales underestimate true demand.\n\n```\nAdjustment:\n1. Identify stockout days (zero sales + zero inventory)\n2. Remove stockout days from the average calculation\n3. Or: estimate lost sales ="},{"path":"references/output-template.md","content":"# Inventory Reorder Calculator Output Template\n\nStructure every reorder recommendation with this format:\n\n---\n\n## Assumptions\n\n| Variable | Value | Source | Confidence |\n|---|---|---|---|\n| Average daily demand | [X] units/day | [Sales data, last N days] | [High / Medium / Low] |\n| Demand std deviation | [σd] units/day | [Calculated from data / estimated] | [High / Medium / Low] |\n| Demand trend | [Growing / Stable / Declining at Y%] | [Data trend / assumption] | [High / Medium / Low] |\n| Supplier lead time | [LT] days | [Historical POs / supplier quote] | [High / Medium / Low] |\n| Lead time std deviation | [σLT] days | [Historical / estimated] | [High / Medium / Low] |\n| Unit cost (landed) | $[X] | [Invoice / quote] | [High / Medium / Low] |\n| Target service level | [X]% | [Business decision] | — |\n| MOQ | [X] units | [Supplier terms] | [High / Medium / Low] |\n| Carton multiple | [X] units | [Supplier / 3PL spec] | [High / Medium / Low] |\n| Review cadence | [Daily / Weekly / Monthly] | [Current process] | — |\n\n---\n\n## Demand Model\n\n```\nAverage daily demand: [X] units/day\nAdjusted for trend: [Y] units/day (if applicable)\nDemand σ: [σd] units/day\nCoefficient of variation: [CV = σd/d] → [low (<0.5) / moderate (0.5–1.0) / high (>1.0)]\nData quality: [Strong / Moderate / Weak] — based on [X] days of history\nSeasonality: [None / Peak in X months / Currently in peak]\n```\n\n⚠️ [Flag any demand-data concerns here]\n\n---\n\n## Lead Time Model\n\n```\nAverage lead time: [LT] days\nLead time σ: [σLT] days\nBest case: [X] days\nWorst case: [Y] days\nSource: [Historical POs (N orders) / Supplier quote / Assumption]\n```\n\n⚠️ [Flag any lead-time concerns here — e.g., supplier based in region with holiday shutdowns, port congestion, etc.]\n\n---\n\n## Safety Stock Calculation\n\n**Method used:** [Service-level / Days-of-cover heuristic]\n\n```\n[Show formula and calculation step by step]\n\nService level: [X]% → z-score: [Z]\nSS = z × √(LT × σd² + d² × σLT²)\nSS = [Z] × √([LT] × [σd]² + [d]² × [σLT]²)\nSS = [Z] × √([A] + [B])\nSS = [Z] × [C]\nSS = [result] units → rounded to [final] units\n```\n\nPlain English: \"Keep [X] units as a buffer to maintain [Y]% chance of not stocking out during a replenishment cycle.\"\n\n---\n\n## Reorder Point\n\n```\nROP = Lead Time Demand + Safety Stock\nROP = (d × LT) + SS\nROP = ([d] × [LT]) + [SS]\nROP = [LTD] + [SS]\nROP = [result] units\n```\n\n**Interpretation:** \"When your inventory position (on-hand + in-transit − backorders) drops to **[ROP] units**, place a new purchase order.\"\n\n### Current Status\n```\nOn-hand: [X] units\nIn-transit: [Y] units (ETA: [date])\nInventory position: [X + Y] units\nROP: [Z] units\nStatus: [✅ Above ROP — no action needed / ⚠️ Below ROP — order now / 🚨 Critical — days to stockout: N]\n```\n\n---\n\n## Reorder Quantity\n\n```\nTarget coverage: [X] days post-receipt\nRaw quantity: [d] × [coverage days] = [Q] units\n```\n\n**Constraint adjustments:**\n| Constraint | Adjustment | Result |\n|---|---|---|\n| MOQ ([X] units) | [Above / rounded up] | [Q'] units |\n| Ca"},{"path":"references/safety-stock-guide.md","content":"# Safety Stock Guide\n\nFramework for calculating safety stock based on service level targets, demand variability, and lead time uncertainty.\n\n---\n\n## Service Level and Z-Score Table\n\nThe service level represents the probability of NOT stocking out during a replenishment cycle.\n\n| Service Level | Z-Score | When to Use |\n|---|---|---|\n| 85% | 1.04 | Low-value items, easy to substitute, minimal stockout cost |\n| 90% | 1.28 | Standard items, moderate substitution risk |\n| 95% | 1.65 | Important SKUs, meaningful revenue impact from stockout |\n| 97.5% | 1.96 | High-value items, significant customer impact |\n| 98% | 2.05 | Key products, brand-critical items |\n| 99% | 2.33 | Mission-critical, no acceptable substitute, hero SKUs |\n| 99.5% | 2.58 | Life-safety or contractual obligation items |\n| 99.9% | 3.09 | Extreme — rarely justified in ecommerce |\n\n### How to choose a service level\n\nAsk these questions:\n\n1. **What happens if this product stocks out?**\n   - Customer buys from competitor → higher service level (97%+)\n   - Customer waits or substitutes → moderate (90–95%)\n   - No significant impact → lower (85–90%)\n\n2. **What's the margin on this product?**\n   - High margin → can afford more safety stock\n   - Low margin → excess inventory cost matters more\n\n3. **How long is the lead time?**\n   - Long lead time → higher service level to compensate\n   - Short lead time (< 7 days) → lower service level acceptable\n\n4. **Is demand predictable?**\n   - Stable, predictable → lower service level works\n   - Volatile or seasonal → need higher service level\n\n---\n\n## Safety Stock Formulas\n\n### Method 1: Combined demand and lead-time variability (preferred)\n\nUse when you have data on both demand variability AND lead-time variability:\n\n```\nSS = z × √(LT × σd² + d² × σLT²)\n\nWhere:\nz = z-score from service level table\nLT = average lead time (days)\nσd = standard deviation of daily demand\nd = average daily demand\nσLT = standard deviation of lead time (days)\n```\n\n**Example:**\n```\nz = 1.65 (95% service level)\nLT = 14 days\nσd = 5 units/day\nd = 30 units/day\nσLT = 3 days\n\nSS = 1.65 × √(14 × 25 + 900 × 9)\nSS = 1.65 × √(350 + 8100)\nSS = 1.65 × √8450\nSS = 1.65 × 91.9\nSS = 152 units\n```\n\n### Method 2: Demand variability only\n\nUse when lead time is reliable (σLT ≈ 0):\n\n```\nSS = z × σd × √LT\n```\n\n**Example:**\n```\nz = 1.65, σd = 5, LT = 14\nSS = 1.65 × 5 × √14 = 1.65 × 5 × 3.74 = 31 units\n```\n\nNote: This gives MUCH less safety stock than Method 1. Only use if supplier lead time is truly consistent.\n\n### Method 3: Days-of-cover heuristic\n\nUse when you don't have good variability data:\n\n```\nSS = average daily demand × safety days\n```\n\n| Situation | Safety Days | Rationale |\n|---|---|---|\n| Short, reliable lead time (<7d) | 3–5 days | Low risk, quick recovery |\n| Moderate lead time (7–21d) | 7–10 days | Standard buffer |\n| Long lead time (21–45d) | 10–14 days | Significant exposure |\n| Long + unreliable lead time | 14–21 days | High risk, slow recovery |\n| Seasonal peak approaching | Add 5–"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Estimate ecommerce reorder timing and quantity using demand, lead time, and safety stock assumptions so teams can set reorder points and reduce stockout risk... Skill: Inventory Reorder Calculator Owner: leooooooow Summary: Estimate ecommerce reorder timing and quantity using demand, lead time, and safety stock assumptions so teams can set reorder points and reduce stockout risk... Tags: latest:1.1.0 Version history: v1.1.0 | 2026-03-30T11:16:52.109Z | user Major upgrade: Added 3 new reference files (safety-stock-guide, demand-analysis-guide, reorder-checklist). Expanded SKI","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1378,"uniquenessScore":50,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-10T07:10:21.731Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-10T07:10:21.731Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-10T09:03:41.054Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}