[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77J0AVPRJREZ3CERPED3431":3,"skill-same:01M77J0AVPRJREZ3CERPED3431":47},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M77J0AVPRJREZ3CERPED3431","heath-ledger",null,"AI bookkeeping agent for Mercury bank accounts. Pulls transactions, categorizes them (rule-based + AI), and generates Excel workbooks with P&L, Balance Sheet, Cash Flow, and transaction detail. Use when the user wants to do bookkeeping, generate financial statements, categorize bank transactions, connect Mercury, or produce monthly\u002Fquarterly\u002Fannual books. Triggers on: bookkeeping, P&L, profit and loss, balance sheet, cash flow, financial statements, Mercury bank, categorize transactions, generate books, monthly close.","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fh\u002Fheath-ledger\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: heath-ledger\ndescription: \"AI bookkeeping agent for Mercury bank accounts. Pulls transactions, categorizes them (rule-based + AI), and generates Excel workbooks with P&L, Balance Sheet, Cash Flow, and transaction detail. Use when the user wants to do bookkeeping, generate financial statements, categorize bank transactions, connect Mercury, or produce monthly\u002Fquarterly\u002Fannual books. Triggers on: bookkeeping, P&L, profit and loss, balance sheet, cash flow, financial statements, Mercury bank, categorize transactions, generate books, monthly close.\"\n---\n\n# Heath Ledger\n\nAI bookkeeping skill for Mercury bank accounts.\n\n## Quick Start\n\n1. `scripts\u002Finit_db.mjs` — creates DB + seeds ~90 universal vendor→category rules\n2. `scripts\u002Fconnect_mercury.sh \u003CMERCURY_API_TOKEN> [entity_name]` — discovers accounts\n3. *(Optional)* `scripts\u002Fconnect_stripe.sh \u003Centity_id> \u003Cstripe_api_key>` — connect Stripe for exact revenue + fees\n4. *(If Stripe connected)* `scripts\u002Fpull_stripe_revenue.sh \u003Centity_id> \u003Cstart_date> \u003Cend_date>` — pull monthly revenue data\n5. `scripts\u002Fpull_transactions.sh \u003Centity_id> \u003Cstart_date> \u003Cend_date>`\n5. `scripts\u002Fcategorize.sh \u003Centity_id>` — rule-based first, AI for unknowns\n6. Review ambiguous items, correct with `scripts\u002Fset_category.sh`\n7. `scripts\u002Fgenerate_books.sh \u003Centity_id> \u003Cstart_date> \u003Cend_date> [output_path]`\n\n## Setup Flow\n\n### Mercury API Key (Required)\nGet from Mercury Dashboard → Settings → API Tokens. The token gives read-only access to transactions.\n\n### Stripe API Key (Optional but Recommended)\nWithout Stripe API: Mercury shows **net** Stripe deposits (revenue minus fees). The system estimates gross revenue using a configurable fee rate (default 2.3% + $0.30).\n\nWith Stripe API: You get **exact** gross revenue, exact fees, and proper refund tracking. Always prefer this when available.\n\nTo connect: `scripts\u002Fconnect_stripe.sh \u003Centity_id> \u003Cstripe_api_key>`\nThen pull data: `scripts\u002Fpull_stripe_revenue.sh \u003Centity_id> \u003Cstart_date> \u003Cend_date>`\n\nThe P&L generator automatically uses Stripe data when available, falling back to Mercury estimates otherwise.\n\n### Entity Settings\nConfigure per-entity via the `entity_settings` table:\n\n| Setting | Default | Description |\n|---------|---------|-------------|\n| `accounting_basis` | `accrual` | `accrual` or `cash` — cash basis uses posted dates only |\n| `month_offset` | `1` | Fiscal year month offset (1 = calendar year) |\n| `stripe_fee_rate` | `0.023` | Stripe percentage fee for gross-up calculation |\n| `stripe_fee_fixed` | `0.30` | Stripe fixed fee per transaction |\n| `amortization_monthly` | `null` | Monthly amortization amount for acquired assets |\n\n## Workflow\n\n1. **Connect Mercury** — `scripts\u002Fconnect_mercury.sh \u003Ctoken> [name]` discovers accounts, creates entity\n2. **Pull transactions** — `scripts\u002Fpull_transactions.sh \u003Centity_id> \u003Cstart_date> \u003Cend_date>`\n3. **Categorize** — `scripts\u002Fcategorize.sh \u003Centity_id> [max_transactions]` — rule-based first, then AI for unknowns\n4. **Review ambiguous** — Script outputs low-confidence items. Ask user, then update with `scripts\u002Fset_category.sh \u003Ctransaction_id> \u003Ccategory> [subcategory]`\n5. **Generate books** — `scripts\u002Fgenerate_books.sh \u003Centity_id> \u003Cstart_date> \u003Cend_date> [output_path]`\n\n## Scripts Reference\n\nAll scripts are in `scripts\u002F`. Run with bash or node. Database is SQLite at `data\u002Fheath.db`.\n\n| Script | Purpose |\n|--------|---------|\n| `init_db.mjs` | Create\u002Fmigrate SQLite database + seed rules |\n| `connect_mercury.sh` | Connect Mercury API, discover accounts |\n| `pull_transactions.sh` | Pull transactions for date range |\n| `categorize.sh` | Categorize transactions (rules + AI) |\n| `set_category.sh` | Manually set category for a transaction |\n| `add_rule.sh` | Add\u002Fupdate a categorization rule |\n| `generate_books.sh` | Generate Excel workbook |\n| `list_entities.sh` | List all entities |\n| `connect_stripe.sh` | Connect Stripe API to an entity |\n| `pull_stripe_revenue.sh` | Pull Stripe balance transactions by month |\n| `status.sh` | Show entity status (accounts, tx counts) |\n\n## Chart of Accounts\n\nSee `references\u002Fchart-of-accounts.md` for the full chart with P&L sections and cash flow classifications.\n\n## Learning & Compounding System\n\nHeath Ledger gets smarter over time through a layered rule system:\n\n### Rule Hierarchy\n1. **Entity-specific rules** (highest priority) — per-company overrides\n2. **Global rules** (`entity_id = NULL`) — apply to all entities\n3. **Seed rules** — universal vendor mappings shipped with the skill\n4. **AI categorization** — used when no rule matches\n\n### How Learning Works\n- Every manual correction creates or updates a categorization rule\n- Rules track `usage_count` — heavily-used rules are more reliable\n- `source` field tracks provenance: `seed`, `ai`, `human`, `manual`\n- Human-confirmed rules get `confidence: 0.95-1.0`\n- AI-generated rules start at `0.85` and can be promoted\n- Entity-specific rules can be promoted to global when they prove universal\n\n### The Compounding Effect\nAfter categorizing ~5,000 transactions across 2 entities, the system now auto-categorizes **~95%** of transactions without AI. Each new entity benefits from all previous learnings.\n\n## Known Limitations\n\n### Stripe Net vs Gross (Without Stripe API)\nMercury deposits from Stripe are **net** amounts (revenue minus ~2.9% + $0.30 fees). Without the Stripe API:\n- We estimate gross revenue using configurable fee rates\n- This creates \"synthetic\" Stripe Fee entries\n- Accuracy depends on your actual Stripe fee rate (varies by plan, card type, international)\n- **Solution**: Connect Stripe API for exact numbers\n\n### Deel Fee Splitting\nDeel combines platform fees and contractor payroll in one transaction stream. Pattern:\n- **Small fixed amounts** (~$2-5) → Deel Platform Fee → categorize as \"Software expenses\"\n- **Larger variable amounts** → Contractor Payroll → categorize as \"Wages & Salaries\"\n- The system learns this pattern but may need initial human guidance\n\n### Mercury API Limitations\n- Only returns posted transactions (not pending)\n- Some counterparty names are truncated or normalized differently\n- Wire descriptions may include reference numbers that create duplicate rules\n\n### Multi-Currency\n- Wise transfers create both a debit (USD) and may show FX fees separately\n- International wire fees from Mercury appear as separate line items\n- FX gains\u002Flosses are not tracked (would need multi-currency ledger)\n\n## AI Categorization\n\nThe `categorize.sh` script calls the host agent's model via stdin\u002Fstdout JSON protocol. It sends transaction batches and expects category assignments back. The script writes a prompt to stdout that the agent should process and return results for.\n\nWhen AI confidence \u003C 0.85, transactions are flagged as ambiguous for user review.\n\n## Key Details\n\n- **Cash or accrual basis** — configurable per entity\n- **Multiple entities supported** — each with own connections and rules\n- **Rules persist** — categorization rules saved to SQLite, reused across runs\n- **Seed rules** — ~90 universal vendor mappings loaded on init\n- **Excel output** — 4-tab workbook: P&L, Balance Sheet, Cash Flow, Transaction Detail\n","# Heath Ledger\n\nAI bookkeeping skill for Mercury bank accounts.\n\n## Quick Start\n\n1. `scripts\u002Finit_db.mjs` — creates DB + seeds ~90 universal vendor→category rules\n2. `scripts\u002Fconnect_mercury.sh \u003CMERCURY_API_TOKEN> [entity_name]` — discovers accounts\n3. *(Optional)* `scripts\u002Fconnect_stripe.sh \u003Centity_id> \u003Cstripe_api_key>` — connect Stripe for exact revenue + fees\n4. *(If Stripe connected)* `scripts\u002Fpull_stripe_revenue.sh \u003Centity_id> \u003Cstart_date> \u003Cend_date>` — pull monthly revenue data\n5. `scripts\u002Fpull_transactions.sh \u003Centity_id> \u003Cstart_date> \u003Cend_date>`\n5. `scripts\u002Fcategorize.sh \u003Centity_id>` — rule-based first, AI for unknowns\n6. Review ambiguous items, correct with `scripts\u002Fset_category.sh`\n7. `scripts\u002Fgenerate_books.sh \u003Centity_id> \u003Cstart_date> \u003Cend_date> [output_path]`\n\n## Setup Flow\n\n### Mercury API Key (Required)\nGet from Mercury Dashboard → Settings → API Tokens. The token gives read-only access to transactions.\n\n### Stripe API Key (Optional but Recommended)\nWithout Stripe API: Mercury shows **net** Stripe deposits (revenue minus fees). The system estimates gross revenue using a configurable fee rate (default 2.3% + $0.30).\n\nWith Stripe API: You get **exact** gross revenue, exact fees, and proper refund tracking. Always prefer this when available.\n\nTo connect: `scripts\u002Fconnect_stripe.sh \u003Centity_id> \u003Cstripe_api_key>`\nThen pull data: `scripts\u002Fpull_stripe_revenue.sh \u003Centity_id> \u003Cstart_date> \u003Cend_date>`\n\nThe P&L generator automatically uses Stripe data when available, falling back to Mercury estimates otherwise.\n\n### Entity Settings\nConfigure per-entity via the `entity_settings` table:\n\n| Setting | Default | Description |\n|---------|---------|-------------|\n| `accounting_basis` | `accrual` | `accrual` or `cash` — cash basis uses posted dates only |\n| `month_offset` | `1` | Fiscal year month offset (1 = calendar year) |\n| `stripe_fee_rate` | `0.023` | Stripe percentage fee for gross-up calculation |\n| `stripe_fee_fixed` | `0.30` | Stripe fixed fee per transaction |\n| `amortization_monthly` | `null` | Monthly amortization amount for acquired assets |\n\n## Workflow\n\n1. **Connect Mercury** — `scripts\u002Fconnect_mercury.sh \u003Ctoken> [name]` discovers accounts, creates entity\n2. **Pull transactions** — `scripts\u002Fpull_transactions.sh \u003Centity_id> \u003Cstart_date> \u003Cend_date>`\n3. **Categorize** — `scripts\u002Fcategorize.sh \u003Centity_id> [max_transactions]` — rule-based first, then AI for unknowns\n4. **Review ambiguous** — Script outputs low-confidence items. Ask user, then update with `scripts\u002Fset_category.sh \u003Ctransaction_id> \u003Ccategory> [subcategory]`\n5. **Generate books** — `scripts\u002Fgenerate_books.sh \u003Centity_id> \u003Cstart_date> \u003Cend_date> [output_path]`\n\n## Scripts Reference\n\nAll scripts are in `scripts\u002F`. Run with bash or node. Database is SQLite at `data\u002Fheath.db`.\n\n| Script | Purpose |\n|--------|---------|\n| `init_db.mjs` | Create\u002Fmigrate SQLite database + seed rules |\n| `connect_mercury.sh` | Connect Mercury API, discover accounts |\n| `pull_transactions.sh` | Pull transactions for date range |\n| `categorize.sh` | Categorize transactions (rules + AI) |\n| `set_category.sh` | Manually set category for a transaction |\n| `add_rule.sh` | Add\u002Fupdate a categorization rule |\n| `generate_books.sh` | Generate Excel workbook |\n| `list_entities.sh` | List all entities |\n| `connect_stripe.sh` | Connect Stripe API to an entity |\n| `pull_stripe_revenue.sh` | Pull Stripe balance transactions by month |\n| `status.sh` | Show entity status (accounts, tx counts) |\n\n## Chart of Accounts\n\nSee `references\u002Fchart-of-accounts.md` for the full chart with P&L sections and cash flow classifications.\n\n## Learning & Compounding System\n\nHeath Ledger gets smarter over time through a layered rule system:\n\n### Rule Hierarchy\n1. **Entity-specific rules** (highest priority) — per-company overrides\n2. **Global rules** (`entity_id = NULL`) — apply to all entities\n3. **Seed rules** — universal vendor mappings shipped with the skill\n4. **AI categorization** — used when no rule matches\n\n### How Learning Works\n- Every manual correction creates or updates a categorization rule\n- Rules track `usage_count` — heavily-used rules are more reliable\n- `source` field tracks provenance: `seed`, `ai`, `human`, `manual`\n- Human-confirmed rules get `confidence: 0.95-1.0`\n- AI-generated rules start at `0.85` and can be promoted\n- Entity-specific rules can be promoted to global when they prove universal\n\n### The Compounding Effect\nAfter categorizing ~5,000 transactions across 2 entities, the system now auto-categorizes **~95%** of transactions without AI. Each new entity benefits from all previous learnings.\n\n## Known Limitations\n\n### Stripe Net vs Gross (Without Stripe API)\nMercury deposits from Stripe are **net** amounts (revenue minus ~2.9% + $0.30 fees). Without the Stripe API:\n- We estimate gross revenue using configurable fee rates\n- This creates \"synthetic\" Stripe Fee entries\n- Accuracy depends on your actual Stripe fee rate (varies by plan, card type, international)\n- **Solution**: Connect Stripe API for exact numbers\n\n### Deel Fee Splitting\nDeel combines platform fees and contractor payroll in one transaction stream. Pattern:\n- **Small fixed amounts** (~$2-5) → Deel Platform Fee → categorize as \"Software expenses\"\n- **Larger variable amounts** → Contractor Payroll → categorize as \"Wages & Salaries\"\n- The system learns this pattern but may need initial human guidance\n\n### Mercury API Limitations\n- Only returns posted transactions (not pending)\n- Some counterparty names are truncated or normalized differently\n- Wire descriptions may include reference numbers that create duplicate rules\n\n### Multi-Currency\n- Wise transfers create both a debit (USD) and may show FX fees separately\n- International wire fees from Mercury appear as separate line items\n- FX gains\u002Flosses are not tracked (would need multi-currency ledger)\n\n## AI Categorization\n\nThe `categorize.sh` script calls the host agent's model via stdin\u002Fstdout JSON protocol. It sends transaction batches and expects category assignments back. The script writes a prompt to stdout that the agent should process and return results for.\n\nWhen AI confidence \u003C 0.85, transactions are flagged as ambiguous for user review.\n\n## Key Details\n\n- **Cash or accrual basis** — configurable per entity\n- **Multiple entities supported** — each with own connections and rules\n- **Rules persist** — categorization rules saved to SQLite, reused across runs\n- **Seed rules** — ~90 universal vendor mappings loaded on init\n- **Excel output** — 4-tab workbook: P&L, Balance Sheet, Cash Flow, Transaction Detail\n",{"name":5,"description":7},"master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fh\u002Fheath-ledger",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill heath-ledger",{"tool":39,"command":40},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill heath-ledger",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill heath-ledger","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fh\u002Fheath-ledger\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]