[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MJNCJATRXK67P9A05T713J":3,"skill-same:01M6MJNCJATRXK67P9A05T713J":92},{"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":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":55,"ownerHtmlUrl":56,"ownerBlogUrl":57,"ownerDescription":58,"updatedAt":59,"install":60,"resources":73},"01M6MJNCJATRXK67P9A05T713J","growth-architect-foundry",null,"Multi-tenant agency growth engine with 31 deterministic commands. Use for ANY advertising, growth, campaign, content, lead, or client-reporting task. Triggers: foundry, audit, diagnose, report, campaign, content, tracking, leads, creative, competitive, season, forecast, tenants, calc, media buying, ad account, client report, growth engine, محرك النمو, تدقيق, تشخيص, تقرير, حملات, محتوى, تتبّع, نقطة التعادل, الروآس وقع, راجع حسابي, خطة, ميديا بلان, كبّر ولا أوقف","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FmohamedOmar11111\u002Fgrowth-architect-foundry\u002Fskills\u002Fgrowth-architect-foundry\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"growth architect foundry","architect","growth","foundry","growth engine","lead","tenant","for","advertising","leads","media buying","competitive","triggers","commands","deterministic","campaign","Media","reporting","audit","diagnose","forecast","2026-11-10 10:12:30",false,"---\nname: growth-architect-foundry\ndescription: >\n  Multi-tenant agency growth engine with 31 deterministic commands.\n  Use for ANY advertising, growth, campaign, content, lead, or client-reporting task.\n  Triggers: foundry, audit, diagnose, report, campaign, content, tracking,\n  leads, creative, competitive, season, forecast, tenants, calc,\n  media buying, ad account, client report, growth engine,\n  محرك النمو, تدقيق, تشخيص, تقرير, حملات, محتوى, تتبّع,\n  نقطة التعادل, الروآس وقع, راجع حسابي, خطة, ميديا بلان, كبّر ولا أوقف\nlicense: MIT\nmetadata:\n  author: Mohamed Omar\n  version: \"1.0.0\"\n  repo: https:\u002F\u002Fgithub.com\u002FmohamedOmar11111\u002Fgrowth-architect-foundry\n---\n\n# Growth Architect Foundry\n\nThe multi-agent growth kernel for agencies who don't want to build one from scratch.\n31 deterministic commands. Multi-tenant. Maker\u002Fchecker safety. Arabic-first.\n\n## Step 0 — Intake (ask once, then work)\n\nBefore running any command, gather:\n1. **Business model:** COD e-com · prepaid e-com · lead-gen · app · B2B · local service\n2. **Market(s) + language:** country, dialect, expat segments\n3. **Platforms + monthly budget** (currency, VAT-inclusive?)\n4. **Target:** CPA\u002FROAS\u002FCPL or unit economics to compute it. If missing → run `calc breakeven` first.\n5. **Data:** last 30 + previous 30 days by campaign (or \"no data yet\")\n\nIf enough numbers → answer first with assumptions, list missing at end.\nIf basics missing → one-message intake.\n\n## Core Rules (every command)\n\n1. **Signal before bids** — broken tracking → fix first; other advice provisional\n2. **Real economics** — COD judged on delivered revenue ÷ spend\n3. **Respect learning** — ~50 conversion events\u002Fweek; budget edits 15-20% at a time\n4. **Consolidate before fragment** — fewer campaigns with enough conversions beat many starved\n5. **Creative = main targeting lever** — diagnose angles, not fonts\n6. **Waste first, scale second** — search terms, placements, frequency, overlap\n7. **Right comparison set** — never judge Egyptian e-com by US lead-gen numbers\n8. **Split by country + language** — Egypt ≠ KSA ≠ UAE\n9. **Every projection is an estimate** with assumptions stated. Never guarantee\n10. **Hands off live accounts** — read free; any write needs explicit per-action yes\n\n## Output Contract\n\n- Lead with verdict (one line), then evidence\n- Numbers not adjectives; show calculation for ROAS\u002FCPA\u002Fbudget\n- Three action buckets: ⚡ do today · ? test this week · ? stop\u002Freduce\n- Tables for plans\u002Faudits; naming: `{country}_{platform}_{objective}_{audience}_{offer}_{yyyymm}`\n- Reply in user's language\u002Fdialect; keep platform terms English (ROAS, CPA, CBO, Advantage+, PMax)\n- Mark each finding: *confirmed by data* or *hypothesis — verify with X*\n\n## Commands\n\nFoundry home (the folder holding `foundry.py`): `@@FOUNDRY_HOME@@`\nIf that value starts with `@@` the skill is being used in place: in Claude Code use `${CLAUDE_PLUGIN_ROOT}`, in any other agent use the folder two levels above this SKILL.md.\n\nAll commands run via `python \"\u003Chome>\u002Ffoundry.py\" \u003Cgroup> \u003Cverb> [--client \u003Ctenant>]` (`python3` on macOS\u002FLinux).\n\n**Workspace:** run from the user's own project folder (or set `FOUNDRY_WORKSPACE`). Tenants, `log.md`, `signals\u002F` and `tasks\u002F` live THERE, never in the plugin folder. First time: `setup doctor`, then `setup init --client \u003CName>`.\n\n**Machine output:** add `--json` to any command for one object: `schema_version, command, ok, exit_code, data, output, report_path, stderr` (`data` is structured for audit, diagnose, live pull and economics). Exit codes: 0 ok, 1 failed, 2 bad input, 3 refused by a safety gate. Parse `data`\u002F`ok`, not the prose.\n\n**Failure rule:** a `FETCH FAILED` line from `live` means the API call failed — never describe it as \"no campaigns\". Writes (`pause`, `budget`) are enforced in code: they need `--confirm` AND the user typing the campaign key at a real terminal, so an agent cannot complete them (exit code 3 = refused). Preview with the command without `--confirm`, show the user the exact change, and give them the full command to run themselves. Budget changes are capped at 20% cumulative per campaign per 7 days.\nReports write to `04_Reports\u002F` and append to `log.md`.\n\n### Account (deterministic, no LLM)\n| Command | Arabic | What it does |\n|---|---|---|\n| `foundry account audit --client \u003Ct>` | راجع حسابي | 0-100 score + grade + top fixes + 30-day plan |\n| `foundry account diagnose --client \u003Ct>` | الروآس وقع | Single biggest constraint + ranked findings |\n| `foundry account report --client \u003Ct> --lang ar` | تقرير للعميل | Decision-first client readout, EN or AR |\n| `foundry account report --client \u003Ct> --lang ar --format whatsapp` | — | Same digest, WhatsApp-ready plain text |\n\n### Economics (deterministic, zero-dep calculator)\n| Command | Arabic | What it does |\n|---|---|---|\n| `foundry economics breakeven --price 499 --cogs 150 ...` | نقطة التعادل | Break-even CPA + ROAS with stated assumptions |\n| `foundry economics cod --spend 20000 --orders 400 ...` | — | Real ROAS on COD account + profit verdict |\n| `foundry economics learning --cpa 120` | — | Budget to exit learning phase (~50 events\u002Fweek) |\n| `foundry economics vat --budget 10000 --country SA` | — | VAT split by MENA country (rates last verified 2026-10) |\n| `foundry economics leadgen --deal-value 5000 --close-rate 0.25 ...` | — | Break-even CPL \u002F CPQL + funnel profit verdict for lead-gen funnels |\n\n### Campaigns (reads captured ad-intel reports)\n| Command | What it does |\n|---|---|\n| `foundry campaigns list --client \u003Ct>` | All campaigns with status, spend, CTR, CPA |\n| `foundry campaigns status --client \u003Ct>` | Flagged: live vs paused vs zero-spend |\n| `foundry campaigns compare --client \u003Ct>` | Side-by-side with best CTR\u002FCPA highlighted |\n| `foundry campaigns import --client \u003Ct> --file export.csv` | Import a platform CSV export into a standard ad-intel report (unblocks diagnose\u002Fcampaigns\u002Fforecast with no API) |\n\n### Content (reads signals, tasks, calendar)\n| Command | What it does |\n|---|---|\n| `foundry content pipeline --client \u003Ct>` | Full signal→brief→task→calendar pipeline view |\n| `foundry content calendar --client \u003Ct>` | Upcoming publish schedule |\n\n### Tracking (reads .env, no API calls)\n| Command | What it does |\n|---|---|\n| `foundry tracking check --client \u003Ct>` | Credential readiness per integration |\n| `foundry tracking events --client \u003Ct>` | Optimization event audit per platform |\n\n### Live (requires API credentials — touches real accounts)\n| Command | Read\u002FWrite | What it does |\n|---|---|---|\n| `foundry live pull --client \u003Ct>` | Read | Pull live campaign data from Google Ads + Meta |\n| `foundry live optimize --client \u003Ct> [--target-cpa \u003Cv>]` | Read | Scale\u002Fhold\u002Freduce\u002Fkill recommendations with numbers |\n| `foundry live pause --client \u003Ct> --campaign-id google:123 --confirm` | **Write** | Pause a campaign (--confirm + human types key at a terminal) |\n| `foundry live budget --client \u003Ct> --campaign-id meta:456 --new-budget 500 --confirm` | **Write** | Adjust budget (max 20% change, --confirm required) |\n\nCampaign IDs use `platform:id` format (e.g., `google:12345678`, `meta:23456789`). The `live pull` command outputs these keys.\n\n### Leads \u002F Creative \u002F Competitive \u002F Seasonal \u002F Forecast \u002F Ops\n| Command | What it does |\n|---|---|\n| `foundry leads score --client \u003Ct>` | Lead task scoring breakdown |\n| `foundry creative hooks --client \u003Ct>` | Hook ideas from winning signals |\n| `foundry creative angles --client \u003Ct>` | Angle matrix from performance data |\n| `foundry competitive audit --client \u003Ct>` | Positioning from strategy directives |\n| `foundry season plan --client \u003Ct>` | MENA seasonal calendar + prep timelines |\n| `foundry forecast project --client \u003Ct>` | Budget projections from captured data |\n| `foundry ops status --client \u003Ct>` | Engine health overview |\n| `foundry ops cadence --client \u003Ct>` | Loop schedule compliance |\n| `foundry tenants list` | All configured tenants with readiness |\n\n## Safety Rules\n\n1. **Read-only default** on live connections — MCP read free, any write needs explicit per-action yes with exact change shown\n2. **Honest limits** — thresholds are heuristics; verify changing facts; not legal\u002Ftax advice\n3. **Confidence labels** — every finding marked *confirmed by data* or *hypothesis*\n4. **No auto-publish** — maker\u002Fchecker built into every task contract\n5. **Money from calc.py** — every money figure comes from deterministic code, not from the AI guessing\n\n## When to Use This Skill\n\nUse this skill when the user mentions:\n- Advertising, ads, campaigns, media buying, performance\n- Account health, audit, diagnose, bottleneck, optimization\n- Client reports, weekly report, monthly report\n- Break-even, ROAS, CPA, COD, VAT, unit economics\n- Content pipeline, briefs, calendar, hooks, angles\n- Leads, scoring, outreach\n- Season, Ramadan, Eid, White Friday\n- Growth engine, foundry, محرك النمو\n- Any of the Arabic trigger phrases listed above\n\n## Installation\n\n```bash\n# Claude Code plugin\n\u002Fplugin marketplace add mohamedOmar11111\u002Fgrowth-architect-foundry\n\u002Fplugin install foundry@growth-architect-foundry\n\n# OpenCode, Freebuff\u002FCodebuff, Codex, Cursor (run from YOUR project folder)\npython \u003Cpath-to-foundry>\u002Fscripts\u002Finstall_agent.py\n\n# Standalone\npython foundry.py account audit --client Aurora_Skincare\n```\n\n## Honest Limits\n\n- Thresholds used in audit\u002Fdiagnose are heuristics, not benchmarks — judge each account against its own 90-day baseline\n- VAT rates change — verify before relying on them\n- Seasonal dates shift ~10 days\u002Fyear (lunar calendar) — verify before committing budget\n- Every projection is an estimate. Nothing here is a guarantee\n- This is not legal, tax, or financial advice\n\n## Content Vault\n\nReady-to-use content organized by type. All assets follow the `templates\u002FASSET_TEMPLATE.md` format.\n\n| Type | Path | Contents |\n|---|---|---|\n| Templates | `templates\u002F` | ASSET_TEMPLATE, CASE_STUDY_TEMPLATE, EXPERIMENT_LOG_TEMPLATE |\n| Playbooks | `playbooks\u002F` | Launch (7-day onboarding), Funnel (ladder diagnosis), COD Operations |\n| Frameworks | `frameworks\u002F` | COD Profit Funnel, Bilingual Content System |\n| Benchmarks | `benchmarks\u002F` | MENA e-com benchmarks (sourced, cited) |\n| Swipe Files | `swipe-files\u002F` | 20 hooks (EN+AR), CTAs, WhatsApp scripts |\n| Worked Examples | `worked-examples\u002F` | COD ROAS diagnosis, Signal-to-content pipeline |\n| Prompts | `prompts\u002F` | Account audit, Creative brief, Ad copy (MENA bilingual) |\n\nEvery benchmark number is sourced. Every worked example is labeled fictional. Every prompt has an \"honest limits\" section.","# Growth Architect Foundry\n\nThe multi-agent growth kernel for agencies who don't want to build one from scratch.\n31 deterministic commands. Multi-tenant. Maker\u002Fchecker safety. Arabic-first.\n\n## Step 0 — Intake (ask once, then work)\n\nBefore running any command, gather:\n1. **Business model:** COD e-com · prepaid e-com · lead-gen · app · B2B · local service\n2. **Market(s) + language:** country, dialect, expat segments\n3. **Platforms + monthly budget** (currency, VAT-inclusive?)\n4. **Target:** CPA\u002FROAS\u002FCPL or unit economics to compute it. If missing → run `calc breakeven` first.\n5. **Data:** last 30 + previous 30 days by campaign (or \"no data yet\")\n\nIf enough numbers → answer first with assumptions, list missing at end.\nIf basics missing → one-message intake.\n\n## Core Rules (every command)\n\n1. **Signal before bids** — broken tracking → fix first; other advice provisional\n2. **Real economics** — COD judged on delivered revenue ÷ spend\n3. **Respect learning** — ~50 conversion events\u002Fweek; budget edits 15-20% at a time\n4. **Consolidate before fragment** — fewer campaigns with enough conversions beat many starved\n5. **Creative = main targeting lever** — diagnose angles, not fonts\n6. **Waste first, scale second** — search terms, placements, frequency, overlap\n7. **Right comparison set** — never judge Egyptian e-com by US lead-gen numbers\n8. **Split by country + language** — Egypt ≠ KSA ≠ UAE\n9. **Every projection is an estimate** with assumptions stated. Never guarantee\n10. **Hands off live accounts** — read free; any write needs explicit per-action yes\n\n## Output Contract\n\n- Lead with verdict (one line), then evidence\n- Numbers not adjectives; show calculation for ROAS\u002FCPA\u002Fbudget\n- Three action buckets: ⚡ do today · ? test this week · ? stop\u002Freduce\n- Tables for plans\u002Faudits; naming: `{country}_{platform}_{objective}_{audience}_{offer}_{yyyymm}`\n- Reply in user's language\u002Fdialect; keep platform terms English (ROAS, CPA, CBO, Advantage+, PMax)\n- Mark each finding: *confirmed by data* or *hypothesis — verify with X*\n\n## Commands\n\nFoundry home (the folder holding `foundry.py`): `@@FOUNDRY_HOME@@`\nIf that value starts with `@@` the skill is being used in place: in Claude Code use `${CLAUDE_PLUGIN_ROOT}`, in any other agent use the folder two levels above this SKILL.md.\n\nAll commands run via `python \"\u003Chome>\u002Ffoundry.py\" \u003Cgroup> \u003Cverb> [--client \u003Ctenant>]` (`python3` on macOS\u002FLinux).\n\n**Workspace:** run from the user's own project folder (or set `FOUNDRY_WORKSPACE`). Tenants, `log.md`, `signals\u002F` and `tasks\u002F` live THERE, never in the plugin folder. First time: `setup doctor`, then `setup init --client \u003CName>`.\n\n**Machine output:** add `--json` to any command for one object: `schema_version, command, ok, exit_code, data, output, report_path, stderr` (`data` is structured for audit, diagnose, live pull and economics). Exit codes: 0 ok, 1 failed, 2 bad input, 3 refused by a safety gate. Parse `data`\u002F`ok`, not the prose.\n\n**Failure rule:** a `FETCH FAILED` line from `live` means the API call failed — never describe it as \"no campaigns\". Writes (`pause`, `budget`) are enforced in code: they need `--confirm` AND the user typing the campaign key at a real terminal, so an agent cannot complete them (exit code 3 = refused). Preview with the command without `--confirm`, show the user the exact change, and give them the full command to run themselves. Budget changes are capped at 20% cumulative per campaign per 7 days.\nReports write to `04_Reports\u002F` and append to `log.md`.\n\n### Account (deterministic, no LLM)\n| Command | Arabic | What it does |\n|---|---|---|\n| `foundry account audit --client \u003Ct>` | راجع حسابي | 0-100 score + grade + top fixes + 30-day plan |\n| `foundry account diagnose --client \u003Ct>` | الروآس وقع | Single biggest constraint + ranked findings |\n| `foundry account report --client \u003Ct> --lang ar` | تقرير للعميل | Decision-first client readout, EN or AR |\n| `foundry account report --client \u003Ct> --lang ar --format whatsapp` | — | Same digest, WhatsApp-ready plain text |\n\n### Economics (deterministic, zero-dep calculator)\n| Command | Arabic | What it does |\n|---|---|---|\n| `foundry economics breakeven --price 499 --cogs 150 ...` | نقطة التعادل | Break-even CPA + ROAS with stated assumptions |\n| `foundry economics cod --spend 20000 --orders 400 ...` | — | Real ROAS on COD account + profit verdict |\n| `foundry economics learning --cpa 120` | — | Budget to exit learning phase (~50 events\u002Fweek) |\n| `foundry economics vat --budget 10000 --country SA` | — | VAT split by MENA country (rates last verified 2026-10) |\n| `foundry economics leadgen --deal-value 5000 --close-rate 0.25 ...` | — | Break-even CPL \u002F CPQL + funnel profit verdict for lead-gen funnels |\n\n### Campaigns (reads captured ad-intel reports)\n| Command | What it does |\n|---|---|\n| `foundry campaigns list --client \u003Ct>` | All campaigns with status, spend, CTR, CPA |\n| `foundry campaigns status --client \u003Ct>` | Flagged: live vs paused vs zero-spend |\n| `foundry campaigns compare --client \u003Ct>` | Side-by-side with best CTR\u002FCPA highlighted |\n| `foundry campaigns import --client \u003Ct> --file export.csv` | Import a platform CSV export into a standard ad-intel report (unblocks diagnose\u002Fcampaigns\u002Fforecast with no API) |\n\n### Content (reads signals, tasks, calendar)\n| Command | What it does |\n|---|---|\n| `foundry content pipeline --client \u003Ct>` | Full signal→brief→task→calendar pipeline view |\n| `foundry content calendar --client \u003Ct>` | Upcoming publish schedule |\n\n### Tracking (reads .env, no API calls)\n| Command | What it does |\n|---|---|\n| `foundry tracking check --client \u003Ct>` | Credential readiness per integration |\n| `foundry tracking events --client \u003Ct>` | Optimization event audit per platform |\n\n### Live (requires API credentials — touches real accounts)\n| Command | Read\u002FWrite | What it does |\n|---|---|---|\n| `foundry live pull --client \u003Ct>` | Read | Pull live campaign data from Google Ads + Meta |\n| `foundry live optimize --client \u003Ct> [--target-cpa \u003Cv>]` | Read | Scale\u002Fhold\u002Freduce\u002Fkill recommendations with numbers |\n| `foundry live pause --client \u003Ct> --campaign-id google:123 --confirm` | **Write** | Pause a campaign (--confirm + human types key at a terminal) |\n| `foundry live budget --client \u003Ct> --campaign-id meta:456 --new-budget 500 --confirm` | **Write** | Adjust budget (max 20% change, --confirm required) |\n\nCampaign IDs use `platform:id` format (e.g., `google:12345678`, `meta:23456789`). The `live pull` command outputs these keys.\n\n### Leads \u002F Creative \u002F Competitive \u002F Seasonal \u002F Forecast \u002F Ops\n| Command | What it does |\n|---|---|\n| `foundry leads score --client \u003Ct>` | Lead task scoring breakdown |\n| `foundry creative hooks --client \u003Ct>` | Hook ideas from winning signals |\n| `foundry creative angles --client \u003Ct>` | Angle matrix from performance data |\n| `foundry competitive audit --client \u003Ct>` | Positioning from strategy directives |\n| `foundry season plan --client \u003Ct>` | MENA seasonal calendar + prep timelines |\n| `foundry forecast project --client \u003Ct>` | Budget projections from captured data |\n| `foundry ops status --client \u003Ct>` | Engine health overview |\n| `foundry ops cadence --client \u003Ct>` | Loop schedule compliance |\n| `foundry tenants list` | All configured tenants with readiness |\n\n## Safety Rules\n\n1. **Read-only default** on live connections — MCP read free, any write needs explicit per-action yes with exact change shown\n2. **Honest limits** — thresholds are heuristics; verify changing facts; not legal\u002Ftax advice\n3. **Confidence labels** — every finding marked *confirmed by data* or *hypothesis*\n4. **No auto-publish** — maker\u002Fchecker built into every task contract\n5. **Money from calc.py** — every money figure comes from deterministic code, not from the AI guessing\n\n## When to Use This Skill\n\nUse this skill when the user mentions:\n- Advertising, ads, campaigns, media buying, performance\n- Account health, audit, diagnose, bottleneck, optimization\n- Client reports, weekly report, monthly report\n- Break-even, ROAS, CPA, COD, VAT, unit economics\n- Content pipeline, briefs, calendar, hooks, angles\n- Leads, scoring, outreach\n- Season, Ramadan, Eid, White Friday\n- Growth engine, foundry, محرك النمو\n- Any of the Arabic trigger phrases listed above\n\n## Installation\n\n```bash\n# Claude Code plugin\n\u002Fplugin marketplace add mohamedOmar11111\u002Fgrowth-architect-foundry\n\u002Fplugin install foundry@growth-architect-foundry\n\n# OpenCode, Freebuff\u002FCodebuff, Codex, Cursor (run from YOUR project folder)\npython \u003Cpath-to-foundry>\u002Fscripts\u002Finstall_agent.py\n\n# Standalone\npython foundry.py account audit --client Aurora_Skincare\n```\n\n## Honest Limits\n\n- Thresholds used in audit\u002Fdiagnose are heuristics, not benchmarks — judge each account against its own 90-day baseline\n- VAT rates change — verify before relying on them\n- Seasonal dates shift ~10 days\u002Fyear (lunar calendar) — verify before committing budget\n- Every projection is an estimate. Nothing here is a guarantee\n- This is not legal, tax, or financial advice\n\n## Content Vault\n\nReady-to-use content organized by type. All assets follow the `templates\u002FASSET_TEMPLATE.md` format.\n\n| Type | Path | Contents |\n|---|---|---|\n| Templates | `templates\u002F` | ASSET_TEMPLATE, CASE_STUDY_TEMPLATE, EXPERIMENT_LOG_TEMPLATE |\n| Playbooks | `playbooks\u002F` | Launch (7-day onboarding), Funnel (ladder diagnosis), COD Operations |\n| Frameworks | `frameworks\u002F` | COD Profit Funnel, Bilingual Content System |\n| Benchmarks | `benchmarks\u002F` | MENA e-com benchmarks (sourced, cited) |\n| Swipe Files | `swipe-files\u002F` | 20 hooks (EN+AR), CTAs, WhatsApp scripts |\n| Worked Examples | `worked-examples\u002F` | COD ROAS diagnosis, Signal-to-content pipeline |\n| Prompts | `prompts\u002F` | Account audit, Creative brief, Ad copy (MENA bilingual) |\n\nEvery benchmark number is sourced. Every worked example is labeled fictional. Every prompt has an \"honest limits\" section.",{"name":5,"license":15,"metadata":45,"description":49},{"repo":46,"author":47,"version":48},"https:\u002F\u002Fgithub.com\u002FmohamedOmar11111\u002Fgrowth-architect-foundry","Mohamed Omar","1.0.0","Multi-tenant agency growth engine with 31 deterministic commands. Use for ANY advertising, growth, campaign, content, lead, or client-reporting task. Triggers: foundry, audit, diagnose, report, campaign, content, tracking, leads, creative, competitive, season, forecast, tenants, calc, media buying, ad account, client report, growth engine, محرك النمو, تدقيق, تشخيص, تقرير, حملات, محتوى, تتبّع, نقطة التعادل, الروآس وقع, راجع حسابي, خطة, ميديا بلان, كبّر ولا أوقف\n","main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002FmohamedOmar11111\u002Fgrowth-architect-foundry\u002Fskills\u002Fgrowth-architect-foundry",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill growth-architect-foundry",{"tool":66,"command":67},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill growth-architect-foundry",{"tool":69,"command":70},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill growth-architect-foundry","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FmohamedOmar11111\u002Fgrowth-architect-foundry\u002Fskills\u002Fgrowth-architect-foundry\u002FSKILL.md",true,[74,80,84,88],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Faudit-checklist.md","REFERENCE","参考文档",1972,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FmohamedOmar11111\u002Fgrowth-architect-foundry\u002Fskills\u002Fgrowth-architect-foundry\u002Freferences\u002Faudit-checklist.md",{"path":81,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fdiagnose-ladder.md",1763,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FmohamedOmar11111\u002Fgrowth-architect-foundry\u002Fskills\u002Fgrowth-architect-foundry\u002Freferences\u002Fdiagnose-ladder.md",{"path":85,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Flive-operations.md",2853,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FmohamedOmar11111\u002Fgrowth-architect-foundry\u002Fskills\u002Fgrowth-architect-foundry\u002Freferences\u002Flive-operations.md",{"path":89,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Freport-templates.md",1628,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FmohamedOmar11111\u002Fgrowth-architect-foundry\u002Fskills\u002Fgrowth-architect-foundry\u002Freferences\u002Freport-templates.md",[93,102,110,118,126,134],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":97,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":101},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":106,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":101},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":114,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":101},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":122,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":101},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":130,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":101},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":138,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":101},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]