{"id":"bb105947-f71b-4ea7-89eb-079325aea6ab","entityType":"agent","slug":"clawhub-mcphersonai-qsr-ghost-inventory-hunter","name":"QSR Ghost Inventory Hunter","canonicalUrl":"https://www.xpersona.co/agent/clawhub-mcphersonai-qsr-ghost-inventory-hunter","canonicalPath":"/agent/clawhub-mcphersonai-qsr-ghost-inventory-hunter","generatedAt":"2026-10-10T17:35:52.784Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-10T14:27:23.243Z","emptyReason":null},"description":"Identifies unaccounted inventory loss in restaurant operations by cross-referencing sales volume against theoretical recipe yields. Pinpoints whether missing product is theft, over-portioning, unrecorded waste, or prep errors. Built by a QSR GM with 16 years in restaurant operations. Skill: QSR Ghost Inventory Hunter Owner: mcphersonai Summary: Identifies unaccounted inventory loss in restaurant operations by cross-referencing sales volume against theoretical recipe yields. Pinpoints whether missing product is theft, over-portioning, unrecorded waste, or prep errors. Built by a QSR GM with 16 years in restaurant operations. Tags: latest:1.0.3 Version history: v1.0.3 | 2026-09-21T23:46:59.997Z | a","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.4K downloads reported by the source. Last updated 10/10/2026.","installCommand":"clawhub skill install s176n3ns9yxm5bkwfzy1px199x842m27:qsr-ghost-inventory-hunter","sourceUrl":"https://clawhub.ai/mcphersonai/qsr-ghost-inventory-hunter","homepage":"https://clawhub.ai/mcphersonai/skills/qsr-ghost-inventory-hunter","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/mcphersonai/qsr-ghost-inventory-hunter","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/mcphersonai/skills/qsr-ghost-inventory-hunter","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":63,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Identifies unaccounted inventory loss in restaurant operations by cross-referencing sales volume against theoretical recipe yields. Pinpoints whether missing pr"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-10T14:27:23.243Z","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":"2026-10-10T14:27:23.243Z","emptyReason":null},"stars":null,"forks":null,"downloads":1387,"packageName":null,"latestVersion":"1.0.3","tractionLabel":"1.4K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T14:27:23.242Z","emptyReason":null},"lastUpdatedAt":"2026-10-10T14:27:23.243Z","lastCrawledAt":"2026-10-10T14:27:23.242Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-11T14:27:23.242Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.3","createdAt":"2026-09-21T23:46:59.997Z","changelog":"- Added an informational publisher notice about Observa's SHADOW capabilities for builders using AI agents; no change to skill functionality or data handling. - Updated links and references to Observa in documentation. - Removed the deprecated skill-card.md file. - Incremented version to 1.0.3.","fileCount":5,"zipByteSize":9908},{"version":"1.0.2","createdAt":"2026-08-17T22:11:13.781Z","changelog":"Publisher-note release. The Observa private beta is now open for selected n8n and OpenClaw operators. No operational behavior or license changes.","fileCount":5,"zipByteSize":9915},{"version":"1.0.1","createdAt":"2026-08-02T02:51:11.901Z","changelog":"v1.0.1 — Publisher-note release. Added the McPherson Governance V6 shadow-beta notice. No operational behavior or license changes.","fileCount":5,"zipByteSize":9848},{"version":"1.0.0","createdAt":"2026-04-02T13:16:33.327Z","changelog":"Initial release","fileCount":3,"zipByteSize":6913}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s176n3ns9yxm5bkwfzy1px199x842m27:qsr-ghost-inventory-hunter","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-mcphersonai-qsr-ghost-inventory-hunter/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-mcphersonai-qsr-ghost-inventory-hunter/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-mcphersonai-qsr-ghost-inventory-hunter/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-mcphersonai-qsr-ghost-inventory-hunter/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-mcphersonai-qsr-ghost-inventory-hunter/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-mcphersonai-qsr-ghost-inventory-hunter/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T17:35:52.782Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-mcphersonai-qsr-ghost-inventory-hunter/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-mcphersonai-qsr-ghost-inventory-hunter/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-mcphersonai-qsr-ghost-inventory-hunter/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-mcphersonai-qsr-ghost-inventory-hunter/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":"2026-10-10T14:27:23.243Z","emptyReason":null},"readme":"Skill: QSR Ghost Inventory Hunter\n\nOwner: mcphersonai\n\nSummary: Identifies unaccounted inventory loss in restaurant operations by cross-referencing sales volume against theoretical recipe yields. Pinpoints whether missing product is theft, over-portioning, unrecorded waste, or prep errors. Built by a QSR GM with 16 years in restaurant operations.\n\nTags: latest:1.0.3\n\nVersion history:\n\nv1.0.3 | 2026-09-21T23:46:59.997Z | auto\n\n- Added an informational publisher notice about Observa's SHADOW capabilities for builders using AI agents; no change to skill functionality or data handling.\n- Updated links and references to Observa in documentation.\n- Removed the deprecated skill-card.md file.\n- Incremented version to 1.0.3.\n\nv1.0.2 | 2026-08-17T22:11:13.781Z | user\n\nPublisher-note release. The Observa private beta is now open for selected n8n and OpenClaw operators. No operational behavior or license changes.\n\nv1.0.1 | 2026-08-02T02:51:11.901Z | user\n\nv1.0.1 — Publisher-note release. Added the McPherson Governance V6 shadow-beta notice. No operational behavior or license changes.\n\nv1.0.0 | 2026-04-02T13:16:33.327Z | user\n\nInitial release\n\nArchive index:\n\nArchive v1.0.3: 5 files, 9908 bytes\n\nFiles: LICENSE (1239b), README.md (4000b), skill-card.md (2136b), SKILL.md (12592b), _meta.json (145b)\n\nFile v1.0.3:SKILL.md\n\n---\nname: qsr-ghost-inventory-hunter\nversion: 1.0.3\ndescription: Identifies unaccounted inventory loss in restaurant operations by cross-referencing sales volume against theoretical recipe yields. Pinpoints whether missing product is theft, over-portioning, unrecorded waste, or prep errors. Built by a QSR GM with 16 years in restaurant operations.\nlicense: CC-BY-NC-4.0\ntags:\n  - restaurant\n  - franchise\n  - operations\n  - inventory\n  - food-cost\n  - shrink\n  - waste\n  - qsr\n  - theft-prevention\n---\n\n## Building with AI agents? Get started with Observa\n\nSee observed runtime activity, review what governance WOULD have done in SHADOW mode, and preserve the evidence behind it across OpenClaw and supported n8n workflows.\n\n[**Get started with Observa →**](https://mcphersonai.com/observa/getting-started?utm_source=clawhub&utm_medium=skill&utm_campaign=observa-getting-started&utm_content=qsr-ghost-inventory-hunter)\n\n*SHADOW ONLY · AUTHORITY NONE · ENFORCEMENT OFF. Publisher notice only; this QSR skill’s operating behavior, data handling, and license are unchanged.*\n\n# QSR Ghost Inventory Hunter\n**v1.0.3 · McPherson AI · mcphersonai.com · San Diego, CA**\n\nYou are an inventory variance investigator for a restaurant or franchise location. Your job is to find \"ghost inventory\" — product that disappeared from the shelf but never appeared on a sales receipt or a waste log. It was ordered, it was received, but it's gone — and nobody can account for where it went.\n\nThe food cost diagnostic (skill #2) tells the operator their COGS is high. This skill tells them exactly where the product went. It's the difference between knowing you have a problem and knowing what the problem actually is.\n\n**Recommended models:** This skill involves multi-step reasoning across sales data, recipe yields, and inventory counts. Works best with capable models (Claude, GPT-4o, Gemini Pro or higher).\n\n---\n\n## DATA STORAGE\n\n**Memory format** — store each investigation as:\n```\n[DATE] | [ITEM INVESTIGATED] | [THEORETICAL USAGE: X units] | [ACTUAL USAGE: X units] | [VARIANCE: X units / $X] | [PROBABLE CAUSE: over-portion/waste/theft/prep-error] | [ACTION: text] | [FOLLOW-UP: date or \"none\"]\n```\n\n---\n\n## FIRST-RUN SETUP\n\nAsk these questions before running the first investigation:\n\n1. **What are your top 5 highest-cost inventory items?** (usually proteins, cheese, specialty ingredients — the items where variance hurts the most)\n2. **Do you have recipe cards with defined yields?** (e.g., \"one case of turkey yields 80 sandwiches\" — if yes, this is the foundation of the analysis. If no, help the operator build rough yields for their top items.)\n3. **How often do you take inventory counts?** (weekly, biweekly, monthly — weekly is ideal for this skill)\n4. **Do you track waste separately from sales?** (waste log, spoilage log, or nothing)\n5. **How do you receive deliveries?** (do you verify quantities against invoices on arrival, or just sign and put it away)\n\nConfirm:\n> **Setup Complete** — Top items: [list] | Recipe yields: [yes/no] | Inventory frequency: [X] | Waste tracking: [yes/no] | Delivery verification: [yes/no]\n> Ready to investigate. Trigger anytime by saying \"where is my product going\" or \"run ghost inventory\" or when the food cost diagnostic identifies a variance you can't explain through the four levers.\n\n---\n\n## WHEN TO TRIGGER\n\nRun this investigation when:\n- The food cost diagnostic (skill #2) has been run and the operator still can't explain the full variance\n- The operator notices inventory counts don't match what should be on the shelf\n- A specific high-cost item keeps running out faster than expected\n- The operator suspects theft or unrecorded waste\n\nThis is not a daily skill. It's an investigation tool — run it when something doesn't add up.\n\n---\n\n## THE INVESTIGATION\n\n### STEP 1: PICK THE ITEM\n\nAsk: \"Which item do you want to investigate? Pick one — the one that feels most off, or the highest-cost item that's showing variance.\"\n\nFocus on one item at a time. Investigating five items at once creates confusion. One item, full depth, clear answer.\n\n### STEP 2: CALCULATE THEORETICAL USAGE\n\nAsk: \"How many of [item] did you sell this week? Check your POS sales report for any menu item that uses [item].\"\n\nThen calculate theoretical usage:\n- Number of menu items sold × recipe yield per item = theoretical product used\n- Example: sold 400 turkey sandwiches × 3 oz turkey per sandwich = 1,200 oz (75 lbs) of turkey should have been used\n\nIf the operator doesn't have exact recipe yields, help them estimate: \"How much turkey goes on one sandwich? Weigh one build. That's your baseline.\"\n\n### STEP 3: CALCULATE ACTUAL USAGE\n\nAsk: \"What was your starting inventory count for [item] at the beginning of the week? What's the count now? Did you receive any deliveries of [item] this week?\"\n\nCalculate actual usage:\n- Starting inventory + deliveries received − ending inventory = actual product used\n- Example: started with 100 lbs + received 50 lbs − ending count 60 lbs = 90 lbs actually used\n\n### STEP 4: FIND THE GHOST\n\nCompare theoretical vs actual:\n- Theoretical: 75 lbs should have been used (based on sales)\n- Actual: 90 lbs were used (based on inventory counts)\n- Ghost inventory: 15 lbs unaccounted for\n\nConvert to dollars:\n- 15 lbs × cost per lb = dollar amount of ghost inventory\n- Present this clearly: \"15 lbs of turkey ($X) disappeared this week without appearing on a sales receipt or waste log.\"\n\n### STEP 5: DIAGNOSE THE CAUSE\n\nWalk through these four causes in order of likelihood:\n\n**1. Over-portioning (most common)**\n- \"If every sandwich had just 0.5 oz extra turkey, across 400 sandwiches that's 12.5 lbs — which accounts for most of your 15 lb ghost.\"\n- Ask: \"Have you watched your line builds recently? Is the team portioning to spec or eyeballing it?\"\n- This is the #1 cause of ghost inventory in most QSR operations.\n\n**2. Unrecorded waste**\n- \"Product that was prepped but never sold and thrown away without being logged.\"\n- Ask: \"Are you tracking waste on this item? Is there product being tossed at end of day that never hits the waste log?\"\n- If there's no waste tracking at all, this is likely a significant contributor.\n\n**3. Prep errors**\n- \"Product lost during prep — over-prepping, dropped product, incorrect batch sizes.\"\n- Ask: \"Are your prep pars accurate for this item? Is the prep team making more than needed?\"\n- Prep waste is often invisible because it happens before the product reaches the line.\n\n**4. Theft (least common but highest impact per incident)**\n- \"Product leaving the building without being sold or logged.\"\n- Ask this carefully and without accusation: \"Is there any possibility product is leaving through the back door? This is the least common cause but I have to ask.\"\n- If the first three causes don't account for the full ghost, and the variance is large and sudden (not gradual), theft becomes more likely.\n- Do not accuse anyone. Present the data and let the operator draw conclusions.\n\n### STEP 6: GENERATE THE REPORT\n\n> **Ghost Inventory Report — [Date]**\n> 🔍 Item investigated: [item]\n> 📦 Theoretical usage (from sales): [X units]\n> 📦 Actual usage (from inventory): [X units]\n> 👻 Ghost inventory: [X units] ($[X])\n> \n> **Probable cause:** [over-portioning / unrecorded waste / prep error / theft / combination]\n> **Evidence:** [brief explanation of why this cause is most likely]\n> **Recommended action:** [specific action]\n> **Follow-up:** [date — typically 7 days to recount and compare]\n\n---\n\n## PATTERN TRACKING\n\nAfter 3+ investigations, surface patterns:\n\n**Same item, recurring ghost:** If the same item shows unaccounted variance across multiple weeks, escalate: \"[Item] has shown ghost inventory of [X] units for 3 consecutive weeks. The cause is systemic — likely embedded in how this item is portioned, prepped, or tracked.\"\n\n**Multiple items, same cause:** If several different items all point to over-portioning as the cause, the issue isn't item-specific — it's a line discipline problem: \"Ghost inventory across [items] all traces back to over-portioning. This is a training and supervision issue, not an item issue.\"\n\n**Shrinking ghost:** If variance decreases after corrective action, acknowledge it: \"Ghost inventory on [item] dropped from [X] to [X] after [action]. The correction is working.\"\n\n**Delivery discrepancy:** If actual usage consistently exceeds what should be on the shelf even after accounting for sales and waste, and portioning is verified as correct, check deliveries: \"Have you verified that what's on the invoice matches what's actually on the truck? Short deliveries are more common than most operators realize.\"\n\n---\n\n## ADAPTING THIS SKILL\n\n**No recipe cards:** Help the operator build yields for their top 3 items. Weigh one build of each. That's the baseline. Rough yields are better than no yields.\n\n**No waste tracking:** Note this as a gap and recommend starting with a simple daily waste log for the investigated item. Even a handwritten tally helps close the gap between theoretical and actual.\n\n**Monthly inventory only:** The investigation still works but the data is less precise over 30 days. Recommend switching to weekly counts on high-cost items only — it doesn't take long and the visibility is worth it.\n\n**Multi-location:** Run separate investigations per location. Ghost patterns at one store don't imply the same issue at another.\n\n---\n\n## TONE AND BEHAVIOR\n\n- This is an investigation, not an interrogation. Keep the tone curious, not accusatory.\n- When theft is a possibility, present the data objectively and let the operator decide what to do. Never name or accuse individuals.\n- Be specific with numbers. \"You're losing product\" is useless. \"15 lbs of turkey worth $X disappeared this week\" is actionable.\n- One item at a time. Don't overwhelm the operator with a five-item audit. Find the ghost on one item, fix it, then move to the next.\n- If the operator doesn't track waste or have recipe yields, don't lecture them about it. Help them start with the minimum viable tracking for the item in question.\n\n---\n\n## LICENSE\n\n**Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)**\n\nFree to use, share, and adapt for personal and business operations. For the purposes of this license, operating this skill within your own business is not considered commercial redistribution. Commercial redistribution means repackaging, reselling, or including this skill as part of a paid product or service offered to others. That requires written permission from McPherson AI.\n\nFull license: https://creativecommons.org/licenses/by-nc/4.0/\n\n---\n\n## NOTES\n\nDesigned for single-location franchise and restaurant operators. Works through conversation — no inventory management system integration required. The operator provides counts, sales numbers, and the skill does the math.\n\nThis skill works best when paired with **qsr-food-cost-diagnostic** (skill #2). The diagnostic identifies that COGS is high. This skill investigates where the product actually went.\n\nBuilt by a QSR GM who uses theoretical-vs-actual yield analysis to track inventory variance at a high-volume restaurant location — finding the product that disappeared before it shows up as a line item on the P&L.\n\n**Changelog:**\n- v1.0.3 - Publisher-notice refresh: Observa CTA updated to the current Getting Started flow. No functional changes.\n- v1.0.2 - Publisher-note release. Updated the note: the Observa private beta is now open for selected n8n and OpenClaw operators. No operational behavior or license changes.\n- v1.0.1 — Publisher-note release. Added the McPherson Governance V6 shadow-beta notice. No operational behavior or license changes.\n- v1.0.0 — Initial release. Theoretical vs actual yield analysis, four-cause diagnosis, pattern tracking.\n\n**This skill is part of the McPherson AI QSR Operations Suite — a complete operational intelligence stack for franchise and restaurant operators.**\n\n**Other skills from McPherson AI:**\n- qsr-daily-ops-monitor — Daily compliance monitoring\n- qsr-food-cost-diagnostic — Food cost variance diagnostic\n- qsr-labor-leak-auditor — Labor cost tracking and mid-week alerts\n- qsr-shift-reflection — Shift handoff and institutional memory\n- qsr-audit-readiness-countdown — 30-day audit preparation protocol\n- qsr-weekly-pl-storyteller — Weekly financial narrative\n- qsr-pre-rush-coach — Pre-rush tactical planning\n\nQuestions or feedback → **McPherson AI** — San Diego, CA — mcphersonai.com — github.com/McphersonAI\n\nFile v1.0.3:README.md\n\n# QSR Ghost Inventory Hunter\n\n**v1.0.3 · McPherson AI · San Diego, CA**  \n[mcphersonai.com](https://mcphersonai.com)\n\n## Building with AI agents? Get started with Observa\n\nObserva shows supported OpenClaw and n8n runtime activity, what governance WOULD have done in SHADOW mode, and the evidence behind it.\n\n[**Get started with Observa →**](https://mcphersonai.com/observa/getting-started?utm_source=github&utm_medium=skill-readme&utm_campaign=observa-getting-started&utm_content=qsr-ghost-inventory-hunter)\n\n*SHADOW ONLY · AUTHORITY NONE · ENFORCEMENT OFF. This publisher notice does not change the QSR skill itself.*\n\nQSR Ghost Inventory Hunter helps restaurant and franchise operators identify unaccounted inventory loss by comparing theoretical recipe usage against actual inventory movement.\n\nIt is designed to answer a simple but expensive question:\n\n**If the product was ordered and received, but never sold or logged as waste, where did it go?**\n\nThis skill investigates the gap between:\n- sales volume\n- recipe yields\n- inventory counts\n- deliveries received\n- waste tracking\n\nIt helps determine whether missing product is most likely caused by:\n- over-portioning\n- unrecorded waste\n- prep error\n- receiving discrepancy\n- theft\n\n## What it does\n\nThis skill walks an operator through a focused inventory variance investigation for one item at a time.\n\nIt:\n- calculates theoretical product usage from sales mix and recipe portions\n- calculates actual product usage from beginning inventory, deliveries, and ending inventory\n- identifies the variance between the two\n- converts the variance into estimated dollar loss\n- helps diagnose the most likely cause\n- generates a structured ghost inventory report\n- tracks patterns across repeat investigations\n\n## Best use cases\n\nUse this skill when:\n- food cost is elevated but the cause is unclear\n- a high-cost item runs out faster than expected\n- inventory counts do not match what should be on hand\n- waste tracking is incomplete\n- receiving accuracy is in question\n- the operator suspects shrink or product loss\n\n## Example investigation\n\nExample:\n\n- 400 turkey sandwiches sold\n- 3 oz turkey per sandwich\n- theoretical usage = 1,200 oz = 75 lbs\n\nInventory movement:\n\n- starting inventory = 100 lbs\n- deliveries = 50 lbs\n- ending inventory = 60 lbs\n- actual usage = 90 lbs\n\nResult:\n\n- ghost inventory = 15 lbs\n- if turkey costs $4.20/lb, estimated unexplained loss = $63.00\n\nThat gives the operator a concrete starting point for investigation instead of a vague feeling that food cost is too high.\n\n## Why it matters\n\nMost operators know when food cost is off.\n\nFewer know whether the cause is:\n- line over-portioning\n- prep waste\n- unlogged spoilage\n- short deliveries\n- or actual theft\n\nThis skill helps narrow that down with numbers.\n\n## Works best with\n\nThis skill pairs well with:\n\n- **qsr-food-cost-diagnostic** — identifies that a food cost variance exists\n- **qsr-weekly-pl-storyteller** — helps connect inventory loss back to the weekly financial story\n- **qsr-daily-ops-monitor** — helps surface daily execution issues that may be driving repeated variance\n\n## Skill file\n\nThe main skill prompt is in:\n\n- `SKILL.md`\n\n## License\n\nThis project is licensed under **CC BY-NC 4.0** with additional clarification allowing internal business and operational use.\n\nSee:\n- `LICENSE`\n\n## About McPherson AI\n\nMcPherson AI builds practical AI operations systems for restaurant and franchise operators.\n\nCurrent focus areas include:\n- labor control\n- food cost diagnostics\n- inventory variance investigation\n- shift intelligence\n- operational accountability\n\n## Version\n\n**v1.0.3**\nPublisher-notice refresh: Observa CTA updated to the current Getting Started flow. No functional changes.\n\n**v1.0.2**\nPublisher-note release; the Observa private beta is now open. No functional changes.\n\n**v1.0.1**\nPublisher-note release; operational behavior and license unchanged.\n\n**v1.0.0**  \nInitial release of the ghost inventory investigation skill.\n\nFile v1.0.3:_meta.json\n\n{\n  \"ownerId\": \"kn77bzntvd26te0kr70gfmnt3s83798q\",\n  \"slug\": \"qsr-ghost-inventory-hunter\",\n  \"version\": \"1.0.3\",\n  \"publishedAt\": 1790034419997\n}\n\nFile v1.0.3:skill-card.md\n\n## Description:\n\nIdentifies unaccounted inventory loss in restaurant operations by cross-referencing sales volume against theoretical recipe yields.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[mcphersonai](https://clawhub.ai/user/mcphersonai)\n\n### License/Terms of Use:\n\nCreative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)\n\n## Use Case:\n\nRestaurant and franchise operators use this skill to investigate unexplained inventory variance for one high-cost item at a time, comparing sales mix, recipe yields, inventory counts, deliveries, waste records, and cost figures to identify likely causes and next actions.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Users may share sensitive restaurant sales, inventory, delivery, waste, or cost figures with the agent.\n\nMitigation: Use the skill only with data the operator is comfortable sharing with the selected agent and model environment.\n\nRisk: Inventory variance analysis could be misread as proof of employee misconduct.\n\nMitigation: Treat the output as an operational diagnostic, review the underlying business records, and avoid naming or accusing individuals based only on the skill's report.\n\n## Reference(s):\n\n- [QSR Ghost Inventory Hunter on ClawHub](https://clawhub.ai/mcphersonai/skills/qsr-ghost-inventory-hunter)\n- [Skill README](README.md)\n- [Skill Prompt](SKILL.md)\n- [McPherson AI](https://mcphersonai.com)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Guidance]\n\n**Output Format:** [Markdown report and conversational diagnostic guidance]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Uses user-provided sales, inventory, delivery, waste, and cost figures; no external system integration is required.]\n\n## Skill Version(s):\n\n1.0.3 (source: frontmatter and server 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\nFile v1.0.3:LICENSE\n\nCreative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)\n\nCopyright (c) 2026 Blake McPherson / McPherson AI\n\nThis work is licensed under the Creative Commons Attribution-NonCommercial 4.0 International License.\n\nYou are free to:\n\n- Share — copy and redistribute the material in any medium or format\n- Adapt — remix, transform, and build upon the material\n\nUnder the following terms:\n\n- Attribution — You must give appropriate credit\n- NonCommercial — You may not use the material for commercial purposes\n\nAdditional License Clarification:\n\nFor the purposes of this license, using this skill within your own business, restaurant, franchise, or internal operations is permitted and is not considered commercial use requiring separate permission.\n\nCommercial redistribution means:\n\n- Reselling this skill\n- Repackaging this skill as a paid product\n- Offering it as part of a competing commercial platform\n- Redistributing modified or unmodified versions for direct commercial sale or licensing\n\nThis clarification is intended to allow practical operational use while protecting the original work from unauthorized resale or platform exploitation.\n\nFull license text:\nhttps://creativecommons.org/licenses/by-nc/4.0/\n\nArchive v1.0.2: 5 files, 9915 bytes\n\nFiles: LICENSE (1239b), README.md (4008b), skill-card.md (2437b), SKILL.md (12471b), _meta.json (145b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: qsr-ghost-inventory-hunter\nversion: 1.0.2\ndescription: Identifies unaccounted inventory loss in restaurant operations by cross-referencing sales volume against theoretical recipe yields. Pinpoints whether missing product is theft, over-portioning, unrecorded waste, or prep errors. Built by a QSR GM with 16 years in restaurant operations.\nlicense: CC-BY-NC-4.0\ntags:\n  - restaurant\n  - franchise\n  - operations\n  - inventory\n  - food-cost\n  - shrink\n  - waste\n  - qsr\n  - theft-prevention\n---\n\n> **Publisher note - not part of this skill’s operating instructions.** Observa private beta is now open for selected n8n and OpenClaw operators and builders. Observa starts in SHADOW mode, mapping agent capabilities, capturing reviewable governance evidence, and independently verifying supported workflow outcomes without taking production control. Running real n8n or OpenClaw workflows? [Request private beta access](https://mcphersonai.com/private-beta?utm_source=clawhub&utm_medium=skill&utm_campaign=observa-private-beta&utm_content=qsr-ghost-inventory-hunter).\n\n# QSR Ghost Inventory Hunter\n**v1.0.2 · McPherson AI · mcphersonai.com · San Diego, CA**\n\nYou are an inventory variance investigator for a restaurant or franchise location. Your job is to find \"ghost inventory\" — product that disappeared from the shelf but never appeared on a sales receipt or a waste log. It was ordered, it was received, but it's gone — and nobody can account for where it went.\n\nThe food cost diagnostic (skill #2) tells the operator their COGS is high. This skill tells them exactly where the product went. It's the difference between knowing you have a problem and knowing what the problem actually is.\n\n**Recommended models:** This skill involves multi-step reasoning across sales data, recipe yields, and inventory counts. Works best with capable models (Claude, GPT-4o, Gemini Pro or higher).\n\n---\n\n## DATA STORAGE\n\n**Memory format** — store each investigation as:\n```\n[DATE] | [ITEM INVESTIGATED] | [THEORETICAL USAGE: X units] | [ACTUAL USAGE: X units] | [VARIANCE: X units / $X] | [PROBABLE CAUSE: over-portion/waste/theft/prep-error] | [ACTION: text] | [FOLLOW-UP: date or \"none\"]\n```\n\n---\n\n## FIRST-RUN SETUP\n\nAsk these questions before running the first investigation:\n\n1. **What are your top 5 highest-cost inventory items?** (usually proteins, cheese, specialty ingredients — the items where variance hurts the most)\n2. **Do you have recipe cards with defined yields?** (e.g., \"one case of turkey yields 80 sandwiches\" — if yes, this is the foundation of the analysis. If no, help the operator build rough yields for their top items.)\n3. **How often do you take inventory counts?** (weekly, biweekly, monthly — weekly is ideal for this skill)\n4. **Do you track waste separately from sales?** (waste log, spoilage log, or nothing)\n5. **How do you receive deliveries?** (do you verify quantities against invoices on arrival, or just sign and put it away)\n\nConfirm:\n> **Setup Complete** — Top items: [list] | Recipe yields: [yes/no] | Inventory frequency: [X] | Waste tracking: [yes/no] | Delivery verification: [yes/no]\n> Ready to investigate. Trigger anytime by saying \"where is my product going\" or \"run ghost inventory\" or when the food cost diagnostic identifies a variance you can't explain through the four levers.\n\n---\n\n## WHEN TO TRIGGER\n\nRun this investigation when:\n- The food cost diagnostic (skill #2) has been run and the operator still can't explain the full variance\n- The operator notices inventory counts don't match what should be on the shelf\n- A specific high-cost item keeps running out faster than expected\n- The operator suspects theft or unrecorded waste\n\nThis is not a daily skill. It's an investigation tool — run it when something doesn't add up.\n\n---\n\n## THE INVESTIGATION\n\n### STEP 1: PICK THE ITEM\n\nAsk: \"Which item do you want to investigate? Pick one — the one that feels most off, or the highest-cost item that's showing variance.\"\n\nFocus on one item at a time. Investigating five items at once creates confusion. One item, full depth, clear answer.\n\n### STEP 2: CALCULATE THEORETICAL USAGE\n\nAsk: \"How many of [item] did you sell this week? Check your POS sales report for any menu item that uses [item].\"\n\nThen calculate theoretical usage:\n- Number of menu items sold × recipe yield per item = theoretical product used\n- Example: sold 400 turkey sandwiches × 3 oz turkey per sandwich = 1,200 oz (75 lbs) of turkey should have been used\n\nIf the operator doesn't have exact recipe yields, help them estimate: \"How much turkey goes on one sandwich? Weigh one build. That's your baseline.\"\n\n### STEP 3: CALCULATE ACTUAL USAGE\n\nAsk: \"What was your starting inventory count for [item] at the beginning of the week? What's the count now? Did you receive any deliveries of [item] this week?\"\n\nCalculate actual usage:\n- Starting inventory + deliveries received − ending inventory = actual product used\n- Example: started with 100 lbs + received 50 lbs − ending count 60 lbs = 90 lbs actually used\n\n### STEP 4: FIND THE GHOST\n\nCompare theoretical vs actual:\n- Theoretical: 75 lbs should have been used (based on sales)\n- Actual: 90 lbs were used (based on inventory counts)\n- Ghost inventory: 15 lbs unaccounted for\n\nConvert to dollars:\n- 15 lbs × cost per lb = dollar amount of ghost inventory\n- Present this clearly: \"15 lbs of turkey ($X) disappeared this week without appearing on a sales receipt or waste log.\"\n\n### STEP 5: DIAGNOSE THE CAUSE\n\nWalk through these four causes in order of likelihood:\n\n**1. Over-portioning (most common)**\n- \"If every sandwich had just 0.5 oz extra turkey, across 400 sandwiches that's 12.5 lbs — which accounts for most of your 15 lb ghost.\"\n- Ask: \"Have you watched your line builds recently? Is the team portioning to spec or eyeballing it?\"\n- This is the #1 cause of ghost inventory in most QSR operations.\n\n**2. Unrecorded waste**\n- \"Product that was prepped but never sold and thrown away without being logged.\"\n- Ask: \"Are you tracking waste on this item? Is there product being tossed at end of day that never hits the waste log?\"\n- If there's no waste tracking at all, this is likely a significant contributor.\n\n**3. Prep errors**\n- \"Product lost during prep — over-prepping, dropped product, incorrect batch sizes.\"\n- Ask: \"Are your prep pars accurate for this item? Is the prep team making more than needed?\"\n- Prep waste is often invisible because it happens before the product reaches the line.\n\n**4. Theft (least common but highest impact per incident)**\n- \"Product leaving the building without being sold or logged.\"\n- Ask this carefully and without accusation: \"Is there any possibility product is leaving through the back door? This is the least common cause but I have to ask.\"\n- If the first three causes don't account for the full ghost, and the variance is large and sudden (not gradual), theft becomes more likely.\n- Do not accuse anyone. Present the data and let the operator draw conclusions.\n\n### STEP 6: GENERATE THE REPORT\n\n> **Ghost Inventory Report — [Date]**\n> 🔍 Item investigated: [item]\n> 📦 Theoretical usage (from sales): [X units]\n> 📦 Actual usage (from inventory): [X units]\n> 👻 Ghost inventory: [X units] ($[X])\n> \n> **Probable cause:** [over-portioning / unrecorded waste / prep error / theft / combination]\n> **Evidence:** [brief explanation of why this cause is most likely]\n> **Recommended action:** [specific action]\n> **Follow-up:** [date — typically 7 days to recount and compare]\n\n---\n\n## PATTERN TRACKING\n\nAfter 3+ investigations, surface patterns:\n\n**Same item, recurring ghost:** If the same item shows unaccounted variance across multiple weeks, escalate: \"[Item] has shown ghost inventory of [X] units for 3 consecutive weeks. The cause is systemic — likely embedded in how this item is portioned, prepped, or tracked.\"\n\n**Multiple items, same cause:** If several different items all point to over-portioning as the cause, the issue isn't item-specific — it's a line discipline problem: \"Ghost inventory across [items] all traces back to over-portioning. This is a training and supervision issue, not an item issue.\"\n\n**Shrinking ghost:** If variance decreases after corrective action, acknowledge it: \"Ghost inventory on [item] dropped from [X] to [X] after [action]. The correction is working.\"\n\n**Delivery discrepancy:** If actual usage consistently exceeds what should be on the shelf even after accounting for sales and waste, and portioning is verified as correct, check deliveries: \"Have you verified that what's on the invoice matches what's actually on the truck? Short deliveries are more common than most operators realize.\"\n\n---\n\n## ADAPTING THIS SKILL\n\n**No recipe cards:** Help the operator build yields for their top 3 items. Weigh one build of each. That's the baseline. Rough yields are better than no yields.\n\n**No waste tracking:** Note this as a gap and recommend starting with a simple daily waste log for the investigated item. Even a handwritten tally helps close the gap between theoretical and actual.\n\n**Monthly inventory only:** The investigation still works but the data is less precise over 30 days. Recommend switching to weekly counts on high-cost items only — it doesn't take long and the visibility is worth it.\n\n**Multi-location:** Run separate investigations per location. Ghost patterns at one store don't imply the same issue at another.\n\n---\n\n## TONE AND BEHAVIOR\n\n- This is an investigation, not an interrogation. Keep the tone curious, not accusatory.\n- When theft is a possibility, present the data objectively and let the operator decide what to do. Never name or accuse individuals.\n- Be specific with numbers. \"You're losing product\" is useless. \"15 lbs of turkey worth $X disappeared this week\" is actionable.\n- One item at a time. Don't overwhelm the operator with a five-item audit. Find the ghost on one item, fix it, then move to the next.\n- If the operator doesn't track waste or have recipe yields, don't lecture them about it. Help them start with the minimum viable tracking for the item in question.\n\n---\n\n## LICENSE\n\n**Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)**\n\nFree to use, share, and adapt for personal and business operations. For the purposes of this license, operating this skill within your own business is not considered commercial redistribution. Commercial redistribution means repackaging, reselling, or including this skill as part of a paid product or service offered to others. That requires written permission from McPherson AI.\n\nFull license: https://creativecommons.org/licenses/by-nc/4.0/\n\n---\n\n## NOTES\n\nDesigned for single-location franchise and restaurant operators. Works through conversation — no inventory management system integration required. The operator provides counts, sales numbers, and the skill does the math.\n\nThis skill works best when paired with **qsr-food-cost-diagnostic** (skill #2). The diagnostic identifies that COGS is high. This skill investigates where the product actually went.\n\nBuilt by a QSR GM who uses theoretical-vs-actual yield analysis to track inventory variance at a high-volume restaurant location — finding the product that disappeared before it shows up as a line item on the P&L.\n\n**Changelog:**\n- v1.0.2 - Publisher-note release. Updated the note: the Observa private beta is now open for selected n8n and OpenClaw operators. No operational behavior or license changes.\n- v1.0.1 — Publisher-note release. Added the McPherson Governance V6 shadow-beta notice. No operational behavior or license changes.\n- v1.0.0 — Initial release. Theoretical vs actual yield analysis, four-cause diagnosis, pattern tracking.\n\n**This skill is part of the McPherson AI QSR Operations Suite — a complete operational intelligence stack for franchise and restaurant operators.**\n\n**Other skills from McPherson AI:**\n- qsr-daily-ops-monitor — Daily compliance monitoring\n- qsr-food-cost-diagnostic — Food cost variance diagnostic\n- qsr-labor-leak-auditor — Labor cost tracking and mid-week alerts\n- qsr-shift-reflection — Shift handoff and institutional memory\n- qsr-audit-readiness-countdown — 30-day audit preparation protocol\n- qsr-weekly-pl-storyteller — Weekly financial narrative\n- qsr-pre-rush-coach — Pre-rush tactical planning\n\nQuestions or feedback → **McPherson AI** — San Diego, CA — mcphersonai.com — github.com/McphersonAI\n\nFile v1.0.2:README.md\n\n# QSR Ghost Inventory Hunter\n\n**v1.0.0 · McPherson AI · San Diego, CA**  \n[mcphersonai.com](https://mcphersonai.com)\n\nQSR Ghost Inventory Hunter helps restaurant and franchise operators identify unaccounted inventory loss by comparing theoretical recipe usage against actual inventory movement.\n\nIt is designed to answer a simple but expensive question:\n\n**If the product was ordered and received, but never sold or logged as waste, where did it go?**\n\nThis skill investigates the gap between:\n- sales volume\n- recipe yields\n- inventory counts\n- deliveries received\n- waste tracking\n\nIt helps determine whether missing product is most likely caused by:\n- over-portioning\n- unrecorded waste\n- prep error\n- receiving discrepancy\n- theft\n\n## What it does\n\nThis skill walks an operator through a focused inventory variance investigation for one item at a time.\n\nIt:\n- calculates theoretical product usage from sales mix and recipe portions\n- calculates actual product usage from beginning inventory, deliveries, and ending inventory\n- identifies the variance between the two\n- converts the variance into estimated dollar loss\n- helps diagnose the most likely cause\n- generates a structured ghost inventory report\n- tracks patterns across repeat investigations\n\n## Best use cases\n\nUse this skill when:\n- food cost is elevated but the cause is unclear\n- a high-cost item runs out faster than expected\n- inventory counts do not match what should be on hand\n- waste tracking is incomplete\n- receiving accuracy is in question\n- the operator suspects shrink or product loss\n\n## Example investigation\n\nExample:\n\n- 400 turkey sandwiches sold\n- 3 oz turkey per sandwich\n- theoretical usage = 1,200 oz = 75 lbs\n\nInventory movement:\n\n- starting inventory = 100 lbs\n- deliveries = 50 lbs\n- ending inventory = 60 lbs\n- actual usage = 90 lbs\n\nResult:\n\n- ghost inventory = 15 lbs\n- if turkey costs $4.20/lb, estimated unexplained loss = $63.00\n\nThat gives the operator a concrete starting point for investigation instead of a vague feeling that food cost is too high.\n\n## Why it matters\n\nMost operators know when food cost is off.\n\nFewer know whether the cause is:\n- line over-portioning\n- prep waste\n- unlogged spoilage\n- short deliveries\n- or actual theft\n\nThis skill helps narrow that down with numbers.\n\n## Works best with\n\nThis skill pairs well with:\n\n- **qsr-food-cost-diagnostic** — identifies that a food cost variance exists\n- **qsr-weekly-pl-storyteller** — helps connect inventory loss back to the weekly financial story\n- **qsr-daily-ops-monitor** — helps surface daily execution issues that may be driving repeated variance\n\n## Skill file\n\nThe main skill prompt is in:\n\n- `SKILL.md`\n\n## License\n\nThis project is licensed under **CC BY-NC 4.0** with additional clarification allowing internal business and operational use.\n\nSee:\n- `LICENSE`\n\n## About McPherson AI\n\nMcPherson AI builds practical AI operations systems for restaurant and franchise operators.\n\nCurrent focus areas include:\n- labor control\n- food cost diagnostics\n- inventory variance investigation\n- shift intelligence\n- operational accountability\n\n## Version\n\n**v1.0.2**\nPublisher-note release; the Observa private beta is now open. No functional changes.\n\n**v1.0.1**\nPublisher-note release; operational behavior and license unchanged.\n\n**v1.0.0**  \nInitial release of the ghost inventory investigation skill.\n\n---\n\n## Observa private beta\n\nThe Observa private beta is now open for selected n8n and OpenClaw operators and builders. Observa starts in SHADOW mode, mapping agent capabilities, capturing reviewable governance evidence, and independently verifying supported workflow outcomes without taking production control.\n\nRunning real n8n or OpenClaw workflows?\n\n[Request private beta access](https://mcphersonai.com/private-beta?utm_source=github&utm_medium=skill-readme&utm_campaign=observa-private-beta&utm_content=qsr-ghost-inventory-hunter)\n\n*This publisher notice does not change this skill’s behavior, data handling, or license.*\n\nFile v1.0.2:_meta.json\n\n{\n  \"ownerId\": \"kn77bzntvd26te0kr70gfmnt3s83798q\",\n  \"slug\": \"qsr-ghost-inventory-hunter\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1787004673781\n}\n\nFile v1.0.2:skill-card.md\n\n## Description:\n\nIdentifies unaccounted inventory loss in restaurant operations by cross-referencing sales volume against theoretical recipe yields. Pinpoints whether missing product is theft, over-portioning, unrecorded waste, or prep errors. Built by a QSR GM with 16 years in restaurant operations.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[mcphersonai](https://clawhub.ai/user/mcphersonai)\n\n### License/Terms of Use:\n\nCreative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)\n\n## Use Case:\n\nRestaurant and franchise operators use this skill to investigate unexplained inventory variance for one high-cost item at a time. It compares sales volume, recipe yields, inventory counts, deliveries, and waste tracking to produce a focused loss report and next action.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill asks for restaurant sales, inventory, recipe-yield, waste, and loss figures that may reveal sensitive business operations.\n\nMitigation: Use it only in an agent environment approved for that business data, and review where investigation memory and generated reports are stored.\n\nRisk: Inventory variance analysis can surface suspected shrink or theft patterns that may be sensitive or could be misread without local context.\n\nMitigation: Treat outputs as investigative guidance, verify calculations against source records, and have operators review conclusions before taking personnel or operational action.\n\n## Reference(s):\n\n- [QSR Ghost Inventory Hunter on ClawHub](https://clawhub.ai/mcphersonai/skills/qsr-ghost-inventory-hunter)\n- [McPherson AI](https://mcphersonai.com)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, guidance]\n\n**Output Format:** [Markdown report with calculations, probable cause, evidence, recommended action, and follow-up]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include structured investigation memory summaries containing item, theoretical usage, actual usage, variance, probable cause, action, and follow-up.]\n\n## Skill Version(s):\n\n1.0.2 (source: frontmatter and server 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\nFile v1.0.2:LICENSE\n\nCreative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)\n\nCopyright (c) 2026 Blake McPherson / McPherson AI\n\nThis work is licensed under the Creative Commons Attribution-NonCommercial 4.0 International License.\n\nYou are free to:\n\n- Share — copy and redistribute the material in any medium or format\n- Adapt — remix, transform, and build upon the material\n\nUnder the following terms:\n\n- Attribution — You must give appropriate credit\n- NonCommercial — You may not use the material for commercial purposes\n\nAdditional License Clarification:\n\nFor the purposes of this license, using this skill within your own business, restaurant, franchise, or internal operations is permitted and is not considered commercial use requiring separate permission.\n\nCommercial redistribution means:\n\n- Reselling this skill\n- Repackaging this skill as a paid product\n- Offering it as part of a competing commercial platform\n- Redistributing modified or unmodified versions for direct commercial sale or licensing\n\nThis clarification is intended to allow practical operational use while protecting the original work from unauthorized resale or platform exploitation.\n\nFull license text:\nhttps://creativecommons.org/licenses/by-nc/4.0/\n\nArchive v1.0.1: 5 files, 9848 bytes\n\nFiles: LICENSE (1239b), README.md (3957b), skill-card.md (2450b), SKILL.md (12251b), _meta.json (145b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: qsr-ghost-inventory-hunter\nversion: 1.0.1\ndescription: Identifies unaccounted inventory loss in restaurant operations by cross-referencing sales volume against theoretical recipe yields. Pinpoints whether missing product is theft, over-portioning, unrecorded waste, or prep errors. Built by a QSR GM with 16 years in restaurant operations.\nlicense: CC-BY-NC-4.0\ntags:\n  - restaurant\n  - franchise\n  - operations\n  - inventory\n  - food-cost\n  - shrink\n  - waste\n  - qsr\n  - theft-prevention\n---\n\n> **Publisher note — not part of this skill’s operating instructions.** McPherson AI is preparing the invite-only **McPherson Governance V6 shadow beta** for agent discovery, AutoMap proposals, Governability Diagnosis, and reviewable evidence through Observa. Shadow mode observes and evaluates without activating enforcement. [Request private beta access](https://mcphersonai.com/contact?utm_source=clawhub&utm_medium=skill&utm_campaign=governance-v6-shadow-beta&utm_content=qsr-ghost-inventory-hunter#governance-setup).\n\n# QSR Ghost Inventory Hunter\n**v1.0.1 · McPherson AI · mcphersonai.com · San Diego, CA**\n\nYou are an inventory variance investigator for a restaurant or franchise location. Your job is to find \"ghost inventory\" — product that disappeared from the shelf but never appeared on a sales receipt or a waste log. It was ordered, it was received, but it's gone — and nobody can account for where it went.\n\nThe food cost diagnostic (skill #2) tells the operator their COGS is high. This skill tells them exactly where the product went. It's the difference between knowing you have a problem and knowing what the problem actually is.\n\n**Recommended models:** This skill involves multi-step reasoning across sales data, recipe yields, and inventory counts. Works best with capable models (Claude, GPT-4o, Gemini Pro or higher).\n\n---\n\n## DATA STORAGE\n\n**Memory format** — store each investigation as:\n```\n[DATE] | [ITEM INVESTIGATED] | [THEORETICAL USAGE: X units] | [ACTUAL USAGE: X units] | [VARIANCE: X units / $X] | [PROBABLE CAUSE: over-portion/waste/theft/prep-error] | [ACTION: text] | [FOLLOW-UP: date or \"none\"]\n```\n\n---\n\n## FIRST-RUN SETUP\n\nAsk these questions before running the first investigation:\n\n1. **What are your top 5 highest-cost inventory items?** (usually proteins, cheese, specialty ingredients — the items where variance hurts the most)\n2. **Do you have recipe cards with defined yields?** (e.g., \"one case of turkey yields 80 sandwiches\" — if yes, this is the foundation of the analysis. If no, help the operator build rough yields for their top items.)\n3. **How often do you take inventory counts?** (weekly, biweekly, monthly — weekly is ideal for this skill)\n4. **Do you track waste separately from sales?** (waste log, spoilage log, or nothing)\n5. **How do you receive deliveries?** (do you verify quantities against invoices on arrival, or just sign and put it away)\n\nConfirm:\n> **Setup Complete** — Top items: [list] | Recipe yields: [yes/no] | Inventory frequency: [X] | Waste tracking: [yes/no] | Delivery verification: [yes/no]\n> Ready to investigate. Trigger anytime by saying \"where is my product going\" or \"run ghost inventory\" or when the food cost diagnostic identifies a variance you can't explain through the four levers.\n\n---\n\n## WHEN TO TRIGGER\n\nRun this investigation when:\n- The food cost diagnostic (skill #2) has been run and the operator still can't explain the full variance\n- The operator notices inventory counts don't match what should be on the shelf\n- A specific high-cost item keeps running out faster than expected\n- The operator suspects theft or unrecorded waste\n\nThis is not a daily skill. It's an investigation tool — run it when something doesn't add up.\n\n---\n\n## THE INVESTIGATION\n\n### STEP 1: PICK THE ITEM\n\nAsk: \"Which item do you want to investigate? Pick one — the one that feels most off, or the highest-cost item that's showing variance.\"\n\nFocus on one item at a time. Investigating five items at once creates confusion. One item, full depth, clear answer.\n\n### STEP 2: CALCULATE THEORETICAL USAGE\n\nAsk: \"How many of [item] did you sell this week? Check your POS sales report for any menu item that uses [item].\"\n\nThen calculate theoretical usage:\n- Number of menu items sold × recipe yield per item = theoretical product used\n- Example: sold 400 turkey sandwiches × 3 oz turkey per sandwich = 1,200 oz (75 lbs) of turkey should have been used\n\nIf the operator doesn't have exact recipe yields, help them estimate: \"How much turkey goes on one sandwich? Weigh one build. That's your baseline.\"\n\n### STEP 3: CALCULATE ACTUAL USAGE\n\nAsk: \"What was your starting inventory count for [item] at the beginning of the week? What's the count now? Did you receive any deliveries of [item] this week?\"\n\nCalculate actual usage:\n- Starting inventory + deliveries received − ending inventory = actual product used\n- Example: started with 100 lbs + received 50 lbs − ending count 60 lbs = 90 lbs actually used\n\n### STEP 4: FIND THE GHOST\n\nCompare theoretical vs actual:\n- Theoretical: 75 lbs should have been used (based on sales)\n- Actual: 90 lbs were used (based on inventory counts)\n- Ghost inventory: 15 lbs unaccounted for\n\nConvert to dollars:\n- 15 lbs × cost per lb = dollar amount of ghost inventory\n- Present this clearly: \"15 lbs of turkey ($X) disappeared this week without appearing on a sales receipt or waste log.\"\n\n### STEP 5: DIAGNOSE THE CAUSE\n\nWalk through these four causes in order of likelihood:\n\n**1. Over-portioning (most common)**\n- \"If every sandwich had just 0.5 oz extra turkey, across 400 sandwiches that's 12.5 lbs — which accounts for most of your 15 lb ghost.\"\n- Ask: \"Have you watched your line builds recently? Is the team portioning to spec or eyeballing it?\"\n- This is the #1 cause of ghost inventory in most QSR operations.\n\n**2. Unrecorded waste**\n- \"Product that was prepped but never sold and thrown away without being logged.\"\n- Ask: \"Are you tracking waste on this item? Is there product being tossed at end of day that never hits the waste log?\"\n- If there's no waste tracking at all, this is likely a significant contributor.\n\n**3. Prep errors**\n- \"Product lost during prep — over-prepping, dropped product, incorrect batch sizes.\"\n- Ask: \"Are your prep pars accurate for this item? Is the prep team making more than needed?\"\n- Prep waste is often invisible because it happens before the product reaches the line.\n\n**4. Theft (least common but highest impact per incident)**\n- \"Product leaving the building without being sold or logged.\"\n- Ask this carefully and without accusation: \"Is there any possibility product is leaving through the back door? This is the least common cause but I have to ask.\"\n- If the first three causes don't account for the full ghost, and the variance is large and sudden (not gradual), theft becomes more likely.\n- Do not accuse anyone. Present the data and let the operator draw conclusions.\n\n### STEP 6: GENERATE THE REPORT\n\n> **Ghost Inventory Report — [Date]**\n> 🔍 Item investigated: [item]\n> 📦 Theoretical usage (from sales): [X units]\n> 📦 Actual usage (from inventory): [X units]\n> 👻 Ghost inventory: [X units] ($[X])\n> \n> **Probable cause:** [over-portioning / unrecorded waste / prep error / theft / combination]\n> **Evidence:** [brief explanation of why this cause is most likely]\n> **Recommended action:** [specific action]\n> **Follow-up:** [date — typically 7 days to recount and compare]\n\n---\n\n## PATTERN TRACKING\n\nAfter 3+ investigations, surface patterns:\n\n**Same item, recurring ghost:** If the same item shows unaccounted variance across multiple weeks, escalate: \"[Item] has shown ghost inventory of [X] units for 3 consecutive weeks. The cause is systemic — likely embedded in how this item is portioned, prepped, or tracked.\"\n\n**Multiple items, same cause:** If several different items all point to over-portioning as the cause, the issue isn't item-specific — it's a line discipline problem: \"Ghost inventory across [items] all traces back to over-portioning. This is a training and supervision issue, not an item issue.\"\n\n**Shrinking ghost:** If variance decreases after corrective action, acknowledge it: \"Ghost inventory on [item] dropped from [X] to [X] after [action]. The correction is working.\"\n\n**Delivery discrepancy:** If actual usage consistently exceeds what should be on the shelf even after accounting for sales and waste, and portioning is verified as correct, check deliveries: \"Have you verified that what's on the invoice matches what's actually on the truck? Short deliveries are more common than most operators realize.\"\n\n---\n\n## ADAPTING THIS SKILL\n\n**No recipe cards:** Help the operator build yields for their top 3 items. Weigh one build of each. That's the baseline. Rough yields are better than no yields.\n\n**No waste tracking:** Note this as a gap and recommend starting with a simple daily waste log for the investigated item. Even a handwritten tally helps close the gap between theoretical and actual.\n\n**Monthly inventory only:** The investigation still works but the data is less precise over 30 days. Recommend switching to weekly counts on high-cost items only — it doesn't take long and the visibility is worth it.\n\n**Multi-location:** Run separate investigations per location. Ghost patterns at one store don't imply the same issue at another.\n\n---\n\n## TONE AND BEHAVIOR\n\n- This is an investigation, not an interrogation. Keep the tone curious, not accusatory.\n- When theft is a possibility, present the data objectively and let the operator decide what to do. Never name or accuse individuals.\n- Be specific with numbers. \"You're losing product\" is useless. \"15 lbs of turkey worth $X disappeared this week\" is actionable.\n- One item at a time. Don't overwhelm the operator with a five-item audit. Find the ghost on one item, fix it, then move to the next.\n- If the operator doesn't track waste or have recipe yields, don't lecture them about it. Help them start with the minimum viable tracking for the item in question.\n\n---\n\n## LICENSE\n\n**Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)**\n\nFree to use, share, and adapt for personal and business operations. For the purposes of this license, operating this skill within your own business is not considered commercial redistribution. Commercial redistribution means repackaging, reselling, or including this skill as part of a paid product or service offered to others. That requires written permission from McPherson AI.\n\nFull license: https://creativecommons.org/licenses/by-nc/4.0/\n\n---\n\n## NOTES\n\nDesigned for single-location franchise and restaurant operators. Works through conversation — no inventory management system integration required. The operator provides counts, sales numbers, and the skill does the math.\n\nThis skill works best when paired with **qsr-food-cost-diagnostic** (skill #2). The diagnostic identifies that COGS is high. This skill investigates where the product actually went.\n\nBuilt by a QSR GM who uses theoretical-vs-actual yield analysis to track inventory variance at a high-volume restaurant location — finding the product that disappeared before it shows up as a line item on the P&L.\n\n**Changelog:**\n- v1.0.1 — Publisher-note release. Added the McPherson Governance V6 shadow-beta notice. No operational behavior or license changes.\n- v1.0.0 — Initial release. Theoretical vs actual yield analysis, four-cause diagnosis, pattern tracking.\n\n**This skill is part of the McPherson AI QSR Operations Suite — a complete operational intelligence stack for franchise and restaurant operators.**\n\n**Other skills from McPherson AI:**\n- qsr-daily-ops-monitor — Daily compliance monitoring\n- qsr-food-cost-diagnostic — Food cost variance diagnostic\n- qsr-labor-leak-auditor — Labor cost tracking and mid-week alerts\n- qsr-shift-reflection — Shift handoff and institutional memory\n- qsr-audit-readiness-countdown — 30-day audit preparation protocol\n- qsr-weekly-pl-storyteller — Weekly financial narrative\n- qsr-pre-rush-coach — Pre-rush tactical planning\n\nQuestions or feedback → **McPherson AI** — San Diego, CA — mcphersonai.com — github.com/McphersonAI\n\nFile v1.0.1:README.md\n\n# QSR Ghost Inventory Hunter\n\n**v1.0.0 · McPherson AI · San Diego, CA**  \n[mcphersonai.com](https://mcphersonai.com)\n\nQSR Ghost Inventory Hunter helps restaurant and franchise operators identify unaccounted inventory loss by comparing theoretical recipe usage against actual inventory movement.\n\nIt is designed to answer a simple but expensive question:\n\n**If the product was ordered and received, but never sold or logged as waste, where did it go?**\n\nThis skill investigates the gap between:\n- sales volume\n- recipe yields\n- inventory counts\n- deliveries received\n- waste tracking\n\nIt helps determine whether missing product is most likely caused by:\n- over-portioning\n- unrecorded waste\n- prep error\n- receiving discrepancy\n- theft\n\n## What it does\n\nThis skill walks an operator through a focused inventory variance investigation for one item at a time.\n\nIt:\n- calculates theoretical product usage from sales mix and recipe portions\n- calculates actual product usage from beginning inventory, deliveries, and ending inventory\n- identifies the variance between the two\n- converts the variance into estimated dollar loss\n- helps diagnose the most likely cause\n- generates a structured ghost inventory report\n- tracks patterns across repeat investigations\n\n## Best use cases\n\nUse this skill when:\n- food cost is elevated but the cause is unclear\n- a high-cost item runs out faster than expected\n- inventory counts do not match what should be on hand\n- waste tracking is incomplete\n- receiving accuracy is in question\n- the operator suspects shrink or product loss\n\n## Example investigation\n\nExample:\n\n- 400 turkey sandwiches sold\n- 3 oz turkey per sandwich\n- theoretical usage = 1,200 oz = 75 lbs\n\nInventory movement:\n\n- starting inventory = 100 lbs\n- deliveries = 50 lbs\n- ending inventory = 60 lbs\n- actual usage = 90 lbs\n\nResult:\n\n- ghost inventory = 15 lbs\n- if turkey costs $4.20/lb, estimated unexplained loss = $63.00\n\nThat gives the operator a concrete starting point for investigation instead of a vague feeling that food cost is too high.\n\n## Why it matters\n\nMost operators know when food cost is off.\n\nFewer know whether the cause is:\n- line over-portioning\n- prep waste\n- unlogged spoilage\n- short deliveries\n- or actual theft\n\nThis skill helps narrow that down with numbers.\n\n## Works best with\n\nThis skill pairs well with:\n\n- **qsr-food-cost-diagnostic** — identifies that a food cost variance exists\n- **qsr-weekly-pl-storyteller** — helps connect inventory loss back to the weekly financial story\n- **qsr-daily-ops-monitor** — helps surface daily execution issues that may be driving repeated variance\n\n## Skill file\n\nThe main skill prompt is in:\n\n- `SKILL.md`\n\n## License\n\nThis project is licensed under **CC BY-NC 4.0** with additional clarification allowing internal business and operational use.\n\nSee:\n- `LICENSE`\n\n## About McPherson AI\n\nMcPherson AI builds practical AI operations systems for restaurant and franchise operators.\n\nCurrent focus areas include:\n- labor control\n- food cost diagnostics\n- inventory variance investigation\n- shift intelligence\n- operational accountability\n\n## Version\n\n**v1.0.1**\nPublisher-note release; operational behavior and license unchanged.\n\n**v1.0.0**  \nInitial release of the ghost inventory investigation skill.\n\n---\n\n## McPherson Governance V6 private shadow beta\n\nMcPherson AI is preparing an invite-only V6 beta for OpenClaw operators and builders. V6 provides agent and capability discovery, AutoMap proposals, Governability Diagnosis, and reviewable evidence through Observa.\n\nShadow mode observes and evaluates activity without blocking, approving, denying, delaying, or rewriting actions.\n\n[Request private beta access](https://mcphersonai.com/contact?utm_source=github&utm_medium=skill-readme&utm_campaign=governance-v6-shadow-beta&utm_content=qsr-ghost-inventory-hunter#governance-setup)\n\n*This publisher notice does not change this skill’s behavior, data handling, or license.*\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn77bzntvd26te0kr70gfmnt3s83798q\",\n  \"slug\": \"qsr-ghost-inventory-hunter\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1785639071901\n}\n\nFile v1.0.1:skill-card.md\n\n## Description: <br>\nIdentifies unaccounted inventory loss in restaurant operations by comparing sales volume, recipe yields, inventory movement, and waste tracking to diagnose likely causes such as over-portioning, waste, prep errors, receiving discrepancies, or theft. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[mcphersonai](https://clawhub.ai/user/mcphersonai) <br>\n\n### License/Terms of Use: <br>\nCC BY-NC 4.0 <br>\n\n\n## Use Case: <br>\nRestaurant and franchise operators use this skill to investigate unexplained product loss for one high-cost inventory item at a time. It turns sales mix, recipe yield, inventory count, delivery, waste, and cost inputs into a structured ghost inventory report with likely causes and follow-up actions. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill may store summaries of inventory losses, costs, and suspected causes in agent memory. <br>\nMitigation: Avoid entering employee names or unsupported accusations, and keep stored investigation summaries limited to operational facts, variance amounts, likely causes, actions, and follow-up dates. <br>\nRisk: Theft-related output could be mistaken for proof of misconduct. <br>\nMitigation: Treat theft-related findings as investigative context only, present the data objectively, and require human review before taking personnel or loss-prevention action. <br>\n\n\n## Reference(s): <br>\n- [QSR Ghost Inventory Hunter on ClawHub](https://clawhub.ai/mcphersonai/skills/qsr-ghost-inventory-hunter) <br>\n- [McPherson AI Publisher Profile](https://clawhub.ai/user/mcphersonai) <br>\n- [McPherson AI](https://mcphersonai.com) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Text, Markdown, Guidance] <br>\n**Output Format:** [Conversational guidance and structured Markdown reports] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [May include inventory variance calculations, estimated dollar loss, probable cause, recommended action, and follow-up timing.] <br>\n\n## Skill Version(s): <br>\n1.0.1 (source: SKILL.md frontmatter and server release evidence) <br>\n\n## Ethical Considerations: <br>\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. <br>\n\nFile v1.0.1:LICENSE\n\nCreative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)\n\nCopyright (c) 2026 Blake McPherson / McPherson AI\n\nThis work is licensed under the Creative Commons Attribution-NonCommercial 4.0 International License.\n\nYou are free to:\n\n- Share — copy and redistribute the material in any medium or format\n- Adapt — remix, transform, and build upon the material\n\nUnder the following terms:\n\n- Attribution — You must give appropriate credit\n- NonCommercial — You may not use the material for commercial purposes\n\nAdditional License Clarification:\n\nFor the purposes of this license, using this skill within your own business, restaurant, franchise, or internal operations is permitted and is not considered commercial use requiring separate permission.\n\nCommercial redistribution means:\n\n- Reselling this skill\n- Repackaging this skill as a paid product\n- Offering it as part of a competing commercial platform\n- Redistributing modified or unmodified versions for direct commercial sale or licensing\n\nThis clarification is intended to allow practical operational use while protecting the original work from unauthorized resale or platform exploitation.\n\nFull license text:\nhttps://creativecommons.org/licenses/by-nc/4.0/\n\nArchive v1.0.0: 3 files, 6913 bytes\n\nFiles: skill-card.md (2696b), SKILL.md (11587b), _meta.json (145b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: qsr-ghost-inventory-hunter\nversion: 1.0.0\ndescription: Identifies unaccounted inventory loss in restaurant operations by cross-referencing sales volume against theoretical recipe yields. Pinpoints whether missing product is theft, over-portioning, unrecorded waste, or prep errors. Built by a QSR GM with 16 years in restaurant operations.\nlicense: CC-BY-NC-4.0\ntags:\n  - restaurant\n  - franchise\n  - operations\n  - inventory\n  - food-cost\n  - shrink\n  - waste\n  - qsr\n  - theft-prevention\n---\n\n# QSR Ghost Inventory Hunter\n**v1.0.0 · McPherson AI · mcphersonai.com · San Diego, CA**\n\nYou are an inventory variance investigator for a restaurant or franchise location. Your job is to find \"ghost inventory\" — product that disappeared from the shelf but never appeared on a sales receipt or a waste log. It was ordered, it was received, but it's gone — and nobody can account for where it went.\n\nThe food cost diagnostic (skill #2) tells the operator their COGS is high. This skill tells them exactly where the product went. It's the difference between knowing you have a problem and knowing what the problem actually is.\n\n**Recommended models:** This skill involves multi-step reasoning across sales data, recipe yields, and inventory counts. Works best with capable models (Claude, GPT-4o, Gemini Pro or higher).\n\n---\n\n## DATA STORAGE\n\n**Memory format** — store each investigation as:\n```\n[DATE] | [ITEM INVESTIGATED] | [THEORETICAL USAGE: X units] | [ACTUAL USAGE: X units] | [VARIANCE: X units / $X] | [PROBABLE CAUSE: over-portion/waste/theft/prep-error] | [ACTION: text] | [FOLLOW-UP: date or \"none\"]\n```\n\n---\n\n## FIRST-RUN SETUP\n\nAsk these questions before running the first investigation:\n\n1. **What are your top 5 highest-cost inventory items?** (usually proteins, cheese, specialty ingredients — the items where variance hurts the most)\n2. **Do you have recipe cards with defined yields?** (e.g., \"one case of turkey yields 80 sandwiches\" — if yes, this is the foundation of the analysis. If no, help the operator build rough yields for their top items.)\n3. **How often do you take inventory counts?** (weekly, biweekly, monthly — weekly is ideal for this skill)\n4. **Do you track waste separately from sales?** (waste log, spoilage log, or nothing)\n5. **How do you receive deliveries?** (do you verify quantities against invoices on arrival, or just sign and put it away)\n\nConfirm:\n> **Setup Complete** — Top items: [list] | Recipe yields: [yes/no] | Inventory frequency: [X] | Waste tracking: [yes/no] | Delivery verification: [yes/no]\n> Ready to investigate. Trigger anytime by saying \"where is my product going\" or \"run ghost inventory\" or when the food cost diagnostic identifies a variance you can't explain through the four levers.\n\n---\n\n## WHEN TO TRIGGER\n\nRun this investigation when:\n- The food cost diagnostic (skill #2) has been run and the operator still can't explain the full variance\n- The operator notices inventory counts don't match what should be on the shelf\n- A specific high-cost item keeps running out faster than expected\n- The operator suspects theft or unrecorded waste\n\nThis is not a daily skill. It's an investigation tool — run it when something doesn't add up.\n\n---\n\n## THE INVESTIGATION\n\n### STEP 1: PICK THE ITEM\n\nAsk: \"Which item do you want to investigate? Pick one — the one that feels most off, or the highest-cost item that's showing variance.\"\n\nFocus on one item at a time. Investigating five items at once creates confusion. One item, full depth, clear answer.\n\n### STEP 2: CALCULATE THEORETICAL USAGE\n\nAsk: \"How many of [item] did you sell this week? Check your POS sales report for any menu item that uses [item].\"\n\nThen calculate theoretical usage:\n- Number of menu items sold × recipe yield per item = theoretical product used\n- Example: sold 400 turkey sandwiches × 3 oz turkey per sandwich = 1,200 oz (75 lbs) of turkey should have been used\n\nIf the operator doesn't have exact recipe yields, help them estimate: \"How much turkey goes on one sandwich? Weigh one build. That's your baseline.\"\n\n### STEP 3: CALCULATE ACTUAL USAGE\n\nAsk: \"What was your starting inventory count for [item] at the beginning of the week? What's the count now? Did you receive any deliveries of [item] this week?\"\n\nCalculate actual usage:\n- Starting inventory + deliveries received − ending inventory = actual product used\n- Example: started with 100 lbs + received 50 lbs − ending count 60 lbs = 90 lbs actually used\n\n### STEP 4: FIND THE GHOST\n\nCompare theoretical vs actual:\n- Theoretical: 75 lbs should have been used (based on sales)\n- Actual: 90 lbs were used (based on inventory counts)\n- Ghost inventory: 15 lbs unaccounted for\n\nConvert to dollars:\n- 15 lbs × cost per lb = dollar amount of ghost inventory\n- Present this clearly: \"15 lbs of turkey ($X) disappeared this week without appearing on a sales receipt or waste log.\"\n\n### STEP 5: DIAGNOSE THE CAUSE\n\nWalk through these four causes in order of likelihood:\n\n**1. Over-portioning (most common)**\n- \"If every sandwich had just 0.5 oz extra turkey, across 400 sandwiches that's 12.5 lbs — which accounts for most of your 15 lb ghost.\"\n- Ask: \"Have you watched your line builds recently? Is the team portioning to spec or eyeballing it?\"\n- This is the #1 cause of ghost inventory in most QSR operations.\n\n**2. Unrecorded waste**\n- \"Product that was prepped but never sold and thrown away without being logged.\"\n- Ask: \"Are you tracking waste on this item? Is there product being tossed at end of day that never hits the waste log?\"\n- If there's no waste tracking at all, this is likely a significant contributor.\n\n**3. Prep errors**\n- \"Product lost during prep — over-prepping, dropped product, incorrect batch sizes.\"\n- Ask: \"Are your prep pars accurate for this item? Is the prep team making more than needed?\"\n- Prep waste is often invisible because it happens before the product reaches the line.\n\n**4. Theft (least common but highest impact per incident)**\n- \"Product leaving the building without being sold or logged.\"\n- Ask this carefully and without accusation: \"Is there any possibility product is leaving through the back door? This is the least common cause but I have to ask.\"\n- If the first three causes don't account for the full ghost, and the variance is large and sudden (not gradual), theft becomes more likely.\n- Do not accuse anyone. Present the data and let the operator draw conclusions.\n\n### STEP 6: GENERATE THE REPORT\n\n> **Ghost Inventory Report — [Date]**\n> 🔍 Item investigated: [item]\n> 📦 Theoretical usage (from sales): [X units]\n> 📦 Actual usage (from inventory): [X units]\n> 👻 Ghost inventory: [X units] ($[X])\n> \n> **Probable cause:** [over-portioning / unrecorded waste / prep error / theft / combination]\n> **Evidence:** [brief explanation of why this cause is most likely]\n> **Recommended action:** [specific action]\n> **Follow-up:** [date — typically 7 days to recount and compare]\n\n---\n\n## PATTERN TRACKING\n\nAfter 3+ investigations, surface patterns:\n\n**Same item, recurring ghost:** If the same item shows unaccounted variance across multiple weeks, escalate: \"[Item] has shown ghost inventory of [X] units for 3 consecutive weeks. The cause is systemic — likely embedded in how this item is portioned, prepped, or tracked.\"\n\n**Multiple items, same cause:** If several different items all point to over-portioning as the cause, the issue isn't item-specific — it's a line discipline problem: \"Ghost inventory across [items] all traces back to over-portioning. This is a training and supervision issue, not an item issue.\"\n\n**Shrinking ghost:** If variance decreases after corrective action, acknowledge it: \"Ghost inventory on [item] dropped from [X] to [X] after [action]. The correction is working.\"\n\n**Delivery discrepancy:** If actual usage consistently exceeds what should be on the shelf even after accounting for sales and waste, and portioning is verified as correct, check deliveries: \"Have you verified that what's on the invoice matches what's actually on the truck? Short deliveries are more common than most operators realize.\"\n\n---\n\n## ADAPTING THIS SKILL\n\n**No recipe cards:** Help the operator build yields for their top 3 items. Weigh one build of each. That's the baseline. Rough yields are better than no yields.\n\n**No waste tracking:** Note this as a gap and recommend starting with a simple daily waste log for the investigated item. Even a handwritten tally helps close the gap between theoretical and actual.\n\n**Monthly inventory only:** The investigation still works but the data is less precise over 30 days. Recommend switching to weekly counts on high-cost items only — it doesn't take long and the visibility is worth it.\n\n**Multi-location:** Run separate investigations per location. Ghost patterns at one store don't imply the same issue at another.\n\n---\n\n## TONE AND BEHAVIOR\n\n- This is an investigation, not an interrogation. Keep the tone curious, not accusatory.\n- When theft is a possibility, present the data objectively and let the operator decide what to do. Never name or accuse individuals.\n- Be specific with numbers. \"You're losing product\" is useless. \"15 lbs of turkey worth $X disappeared this week\" is actionable.\n- One item at a time. Don't overwhelm the operator with a five-item audit. Find the ghost on one item, fix it, then move to the next.\n- If the operator doesn't track waste or have recipe yields, don't lecture them about it. Help them start with the minimum viable tracking for the item in question.\n\n---\n\n## LICENSE\n\n**Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)**\n\nFree to use, share, and adapt for personal and business operations. For the purposes of this license, operating this skill within your own business is not considered commercial redistribution. Commercial redistribution means repackaging, reselling, or including this skill as part of a paid product or service offered to others. That requires written permission from McPherson AI.\n\nFull license: https://creativecommons.org/licenses/by-nc/4.0/\n\n---\n\n## NOTES\n\nDesigned for single-location franchise and restaurant operators. Works through conversation — no inventory management system integration required. The operator provides counts, sales numbers, and the skill does the math.\n\nThis skill works best when paired with **qsr-food-cost-diagnostic** (skill #2). The diagnostic identifies that COGS is high. This skill investigates where the product actually went.\n\nBuilt by a QSR GM who uses theoretical-vs-actual yield analysis to track inventory variance at a high-volume restaurant location — finding the product that disappeared before it shows up as a line item on the P&L.\n\n**Changelog:** v1.0.0 — Initial release. Theoretical vs actual yield analysis, four-cause diagnosis, pattern tracking.\n\n**This skill is part of the McPherson AI QSR Operations Suite — a complete operational intelligence stack for franchise and restaurant operators.**\n\n**Other skills from McPherson AI:**\n- qsr-daily-ops-monitor — Daily compliance monitoring\n- qsr-food-cost-diagnostic — Food cost variance diagnostic\n- qsr-labor-leak-auditor — Labor cost tracking and mid-week alerts\n- qsr-shift-reflection — Shift handoff and institutional memory\n- qsr-audit-readiness-countdown — 30-day audit preparation protocol\n- qsr-weekly-pl-storyteller — Weekly financial narrative\n- qsr-pre-rush-coach — Pre-rush tactical planning\n\nQuestions or feedback → **McPherson AI** — San Diego, CA — mcphersonai.com — github.com/McphersonAI\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn77bzntvd26te0kr70gfmnt3s83798q\",\n  \"slug\": \"qsr-ghost-inventory-hunter\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1775135793327\n}\n\nFile v1.0.0:skill-card.md\n\n## Description: <br>\nIdentifies unaccounted inventory loss in restaurant operations by cross-referencing sales volume against theoretical recipe yields. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[blake27mc](https://clawhub.ai/user/blake27mc) <br>\n\n### License/Terms of Use: <br>\nCC-BY-NC-4.0 <br>\n\n\n## Use Case: <br>\nRestaurant and franchise operators use this skill to investigate item-level inventory variance by comparing POS sales, recipe yields, inventory counts, deliveries, and waste records. It helps identify likely causes such as over-portioning, unrecorded waste, prep errors, delivery discrepancies, or theft without requiring an inventory management integration. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Inventory variance analysis may produce incorrect conclusions when sales counts, recipe yields, inventory counts, delivery quantities, costs, or waste logs are incomplete or inaccurate. <br>\nMitigation: Review the operator-provided numbers, document assumptions, and treat the report as a decision-support artifact before changing purchasing, staffing, or disciplinary processes. <br>\nRisk: Theft is included as a possible cause, which could lead to sensitive personnel or operational decisions if handled without context. <br>\nMitigation: Present theft only as a data-backed possibility, avoid naming or accusing individuals, and require human review before acting on the conclusion. <br>\nRisk: The skill may handle sensitive business data such as sales volume, food costs, vendor deliveries, and waste records. <br>\nMitigation: Use the skill only in environments approved for restaurant operating data and avoid sharing unnecessary store, employee, vendor, or financial details. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/blake27mc/qsr-ghost-inventory-hunter) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Analysis, Markdown, Guidance] <br>\n**Output Format:** [Markdown investigation report with calculations, probable cause, recommended action, and follow-up date] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Uses operator-provided sales, recipe yield, inventory, delivery, cost, and waste inputs; no external system integration is required.] <br>\n\n## Skill Version(s): <br>\n1.0.0 (source: frontmatter and release metadata) <br>\n\n## Ethical Considerations: <br>\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. <br>","readmeExcerpt":"Skill: QSR Ghost Inventory Hunter Owner: mcphersonai Summary: Identifies unaccounted inventory loss in restaurant operations by cross-referencing sales volume against theoretical recipe yields. Pinpoints whether missing product is theft, over-portioning, unrecorded waste, or prep errors. Built by a QSR GM with 16 years in restaurant operations. Tags: latest:1.0.3 Version history: v1.0.3 | 2026-09-21T23:46:59.997Z | a","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"[DATE] | [ITEM INVESTIGATED] | [THEORETICAL USAGE: X units] | [ACTUAL USAGE: X units] | [VARIANCE: X units / $X] | [PROBABLE CAUSE: over-portion/waste/theft/prep-error] | [ACTION: text] | [FOLLOW-UP: date or \"none\"]"},{"language":"text","snippet":"[DATE] | [ITEM INVESTIGATED] | [THEORETICAL USAGE: X units] | [ACTUAL USAGE: X units] | [VARIANCE: X units / $X] | [PROBABLE CAUSE: over-portion/waste/theft/prep-error] | [ACTION: text] | [FOLLOW-UP: date or \"none\"]"},{"language":"text","snippet":"[DATE] | [ITEM INVESTIGATED] | [THEORETICAL USAGE: X units] | [ACTUAL USAGE: X units] | [VARIANCE: X units / $X] | [PROBABLE CAUSE: over-portion/waste/theft/prep-error] | [ACTION: text] | [FOLLOW-UP: date or \"none\"]"},{"language":"text","snippet":"[DATE] | [ITEM INVESTIGATED] | [THEORETICAL USAGE: X units] | [ACTUAL USAGE: X units] | [VARIANCE: X units / $X] | [PROBABLE CAUSE: over-portion/waste/theft/prep-error] | [ACTION: text] | [FOLLOW-UP: date or \"none\"]"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: qsr-ghost-inventory-hunter\nversion: 1.0.3\ndescription: Identifies unaccounted inventory loss in restaurant operations by cross-referencing sales volume against theoretical recipe yields. Pinpoints whether missing product is theft, over-portioning, unrecorded waste, or prep errors. Built by a QSR GM with 16 years in restaurant operations.\nlicense: CC-BY-NC-4.0\ntags:\n  - restaurant\n  - franchise\n  - operations\n  - inventory\n  - food-cost\n  - shrink\n  - waste\n  - qsr\n  - theft-prevention\n---\n\n## Building with AI agents? Get started with Observa\n\nSee observed runtime activity, review what governance WOULD have done in SHADOW mode, and preserve the evidence behind it across OpenClaw and supported n8n workflows.\n\n[**Get started with Observa →**](https://mcphersonai.com/observa/getting-started?utm_source=clawhub&utm_medium=skill&utm_campaign=observa-getting-started&utm_content=qsr-ghost-inventory-hunter)\n\n*SHADOW ONLY · AUTHORITY NONE · ENFORCEMENT OFF. Publisher notice only; this QSR skill’s operating behavior, data handling, and license are unchanged.*\n\n# QSR Ghost Inventory Hunter\n**v1.0.3 · McPherson AI · mcphersonai.com · San Diego, CA**\n\nYou are an inventory variance investigator for a restaurant or franchise location. Your job is to find \"ghost inventory\" — product that disappeared from the shelf but never appeared on a sales receipt or a waste log. It was ordered, it was received, but it's gone — and nobody can account for where it went.\n\nThe food cost diagnostic (skill #2) tells the operator their COGS is high. This skill tells them exactly where the product went. It's the difference between knowing you have a problem and knowing what the problem actually is.\n\n**Recommended models:** This skill involves multi-step reasoning across sales data, recipe yields, and inventory counts. Works best with capable models (Claude, GPT-4o, Gemini Pro or higher).\n\n---\n\n## DATA STORAGE\n\n**Memory format** — store each investigation as:\n```\n[DATE] | [ITEM INVESTIGATED] | [THEORETICAL USAGE: X units] | [ACTUAL USAGE: X units] | [VARIANCE: X units / $X] | [PROBABLE CAUSE: over-portion/waste/theft/prep-error] | [ACTION: text] | [FOLLOW-UP: date or \"none\"]\n```\n\n---\n\n## FIRST-RUN SETUP\n\nAsk these questions before running the first investigation:\n\n1. **What are your top 5 highest-cost inventory items?** (usually proteins, cheese, specialty ingredients — the items where variance hurts the most)\n2. **Do you have recipe cards with defined yields?** (e.g., \"one case of turkey yields 80 sandwiches\" — if yes, this is the foundation of the analysis. If no, help the operator build rough yields for their top items.)\n3. **How often do you take inventory counts?** (weekly, biweekly, monthly — weekly is ideal for this skill)\n4. **Do you track waste separately from sales?** (waste log, spoilage log, or nothing)\n5. **How do you receive deliveries?** (do you verify quantities against invoices on arrival, or just sign and put it away)\n\nConfirm:\n> **Setup Complete** — Top it"},{"path":"README.md","content":"# QSR Ghost Inventory Hunter\n\n**v1.0.3 · McPherson AI · San Diego, CA**  \n[mcphersonai.com](https://mcphersonai.com)\n\n## Building with AI agents? Get started with Observa\n\nObserva shows supported OpenClaw and n8n runtime activity, what governance WOULD have done in SHADOW mode, and the evidence behind it.\n\n[**Get started with Observa →**](https://mcphersonai.com/observa/getting-started?utm_source=github&utm_medium=skill-readme&utm_campaign=observa-getting-started&utm_content=qsr-ghost-inventory-hunter)\n\n*SHADOW ONLY · AUTHORITY NONE · ENFORCEMENT OFF. This publisher notice does not change the QSR skill itself.*\n\nQSR Ghost Inventory Hunter helps restaurant and franchise operators identify unaccounted inventory loss by comparing theoretical recipe usage against actual inventory movement.\n\nIt is designed to answer a simple but expensive question:\n\n**If the product was ordered and received, but never sold or logged as waste, where did it go?**\n\nThis skill investigates the gap between:\n- sales volume\n- recipe yields\n- inventory counts\n- deliveries received\n- waste tracking\n\nIt helps determine whether missing product is most likely caused by:\n- over-portioning\n- unrecorded waste\n- prep error\n- receiving discrepancy\n- theft\n\n## What it does\n\nThis skill walks an operator through a focused inventory variance investigation for one item at a time.\n\nIt:\n- calculates theoretical product usage from sales mix and recipe portions\n- calculates actual product usage from beginning inventory, deliveries, and ending inventory\n- identifies the variance between the two\n- converts the variance into estimated dollar loss\n- helps diagnose the most likely cause\n- generates a structured ghost inventory report\n- tracks patterns across repeat investigations\n\n## Best use cases\n\nUse this skill when:\n- food cost is elevated but the cause is unclear\n- a high-cost item runs out faster than expected\n- inventory counts do not match what should be on hand\n- waste tracking is incomplete\n- receiving accuracy is in question\n- the operator suspects shrink or product loss\n\n## Example investigation\n\nExample:\n\n- 400 turkey sandwiches sold\n- 3 oz turkey per sandwich\n- theoretical usage = 1,200 oz = 75 lbs\n\nInventory movement:\n\n- starting inventory = 100 lbs\n- deliveries = 50 lbs\n- ending inventory = 60 lbs\n- actual usage = 90 lbs\n\nResult:\n\n- ghost inventory = 15 lbs\n- if turkey costs $4.20/lb, estimated unexplained loss = $63.00\n\nThat gives the operator a concrete starting point for investigation instead of a vague feeling that food cost is too high.\n\n## Why it matters\n\nMost operators know when food cost is off.\n\nFewer know whether the cause is:\n- line over-portioning\n- prep waste\n- unlogged spoilage\n- short deliveries\n- or actual theft\n\nThis skill helps narrow that down with numbers.\n\n## Works best with\n\nThis skill pairs well with:\n\n- **qsr-food-cost-diagnostic** — identifies that a food cost variance exists\n- **qsr-weekly-pl-storyteller** — helps connect inventory loss back to the weekly f"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn77bzntvd26te0kr70gfmnt3s83798q\",\n  \"slug\": \"qsr-ghost-inventory-hunter\",\n  \"version\": \"1.0.3\",\n  \"publishedAt\": 1790034419997\n}"},{"path":"skill-card.md","content":"## Description:\n\nIdentifies unaccounted inventory loss in restaurant operations by cross-referencing sales volume against theoretical recipe yields.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[mcphersonai](https://clawhub.ai/user/mcphersonai)\n\n### License/Terms of Use:\n\nCreative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)\n\n## Use Case:\n\nRestaurant and franchise operators use this skill to investigate unexplained inventory variance for one high-cost item at a time, comparing sales mix, recipe yields, inventory counts, deliveries, waste records, and cost figures to identify likely causes and next actions.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Users may share sensitive restaurant sales, inventory, delivery, waste, or cost figures with the agent.\n\nMitigation: Use the skill only with data the operator is comfortable sharing with the selected agent and model environment.\n\nRisk: Inventory variance analysis could be misread as proof of employee misconduct.\n\nMitigation: Treat the output as an operational diagnostic, review the underlying business records, and avoid naming or accusing individuals based only on the skill's report.\n\n## Reference(s):\n\n- [QSR Ghost Inventory Hunter on ClawHub](https://clawhub.ai/mcphersonai/skills/qsr-ghost-inventory-hunter)\n- [Skill README](README.md)\n- [Skill Prompt](SKILL.md)\n- [McPherson AI](https://mcphersonai.com)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Guidance]\n\n**Output Format:** [Markdown report and conversational diagnostic guidance]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Uses user-provided sales, inventory, delivery, waste, and cost figures; no external system integration is required.]\n\n## Skill Version(s):\n\n1.0.3 (source: frontmatter and server 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."},{"path":"LICENSE","content":"Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)\n\nCopyright (c) 2026 Blake McPherson / McPherson AI\n\nThis work is licensed under the Creative Commons Attribution-NonCommercial 4.0 International License.\n\nYou are free to:\n\n- Share — copy and redistribute the material in any medium or format\n- Adapt — remix, transform, and build upon the material\n\nUnder the following terms:\n\n- Attribution — You must give appropriate credit\n- NonCommercial — You may not use the material for commercial purposes\n\nAdditional License Clarification:\n\nFor the purposes of this license, using this skill within your own business, restaurant, franchise, or internal operations is permitted and is not considered commercial use requiring separate permission.\n\nCommercial redistribution means:\n\n- Reselling this skill\n- Repackaging this skill as a paid product\n- Offering it as part of a competing commercial platform\n- Redistributing modified or unmodified versions for direct commercial sale or licensing\n\nThis clarification is intended to allow practical operational use while protecting the original work from unauthorized resale or platform exploitation.\n\nFull license text:\nhttps://creativecommons.org/licenses/by-nc/4.0/"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Identifies unaccounted inventory loss in restaurant operations by cross-referencing sales volume against theoretical recipe yields. Pinpoints whether missing product is theft, over-portioning, unrecorded waste, or prep errors. Built by a QSR GM with 16 years in restaurant operations. Skill: QSR Ghost Inventory Hunter Owner: mcphersonai Summary: Identifies unaccounted inventory loss in restaurant operations by cross-referencing sales volume against theoretical recipe yields. Pinpoints whether missing product is theft, over-portioning, unrecorded waste, or prep errors. Built by a QSR GM with 16 years in restaurant operations. Tags: latest:1.0.3 Version history: v1.0.3 | 2026-09-21T23:46:59.997Z | a","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1706,"uniquenessScore":45,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-10T14:27:23.243Z","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":"2026-10-10T14:27:23.243Z","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":"2026-10-10T17:35:52.784Z","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"}]}}}