[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AYRB8VMNT6PC2S6J37J52F":3,"skill-same:01M7AYRB8VMNT6PC2S6J37J52F":53},{"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":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7AYRB8VMNT6PC2S6J37J52F","project-launch-checklist",null,"Build and review two-tier production launch checklists — generic + framework-specific — and author vault reference checklists (ai-checklist family). Simplify verbose reference manuals into tickable checklists (ponytail pattern).","oat431\u002Fhermes_config_backup","oat431","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54722120?v=4","01M7AYD07EH8SYPMYY8CGZKS22","Oralita","01M7AYD0816QDF77E3TWCRSQC9",1,"Unlicense","https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup\u002Fblob\u002Fmain\u002Fworkflow\u002Fhermes-main-profile\u002Fproject-launch-checklist\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: project-launch-checklist\ndescription: Build and review two-tier production launch checklists — generic + framework-specific — and author vault reference checklists (ai-checklist family). Simplify verbose reference manuals into tickable checklists (ponytail pattern).\n---\n\n# Project Launch Checklist — Two-Tier System\n\nBuild production-ready launch checklists for any tech stack. Pattern: generic tick-first checklists + framework-specific companions + reference manuals.\n\n## The Two-Tier Pattern\n\nThree file types per domain, living in the same folder:\n\n```\ndomain-checklist\u002F\n├── {Domain} Launch.md           ← Generic. Tick FIRST. ~40-50 items, framework-agnostic.\n├── framework-vX-api.md          ← Framework companion. Tick AFTER generic. ~70-85 items.\n├── framework-reference.md       ← Reference manual. Deep dives, tutorials. Not ticked.\n└── (repeat for each framework)\n```\n\n### Tier 1: Generic Launch Checklist\n\n- 6-8 sections, 5-7 one-line items each\n- Target: ~45 items total\n- Every item: `- [ ] Description → [[vault-note]]` — links to knowledge vault, no explanations embedded\n- Zero code examples. Zero version trivia. Zero tutorials.\n- Sections: Security → API\u002FState → Database\u002FData → Resilience\u002FPerformance → Observability → Testing → Deployment → (+ Routing for frontend)\n- References framework companions: \"For {framework} specifics, see [[framework-vX]]\"\n- References dependent checklists: \"Assumes [[Related Launch]] is already done\"\n\n### Tier 2: Framework Companion\n\n- \"Tick [[{Domain} Launch]] first\" in the header\n- Framework-specific only: setup, routing, DI, middleware, ORM, testing tools\n- ~70-85 items. Still tickable. Still no tutorials.\n- Sections mirror generic but with framework details:\n  Project Setup → App Structure → Middleware\u002FRouting → Auth → Config\u002FSecrets → DB\u002FState → Testing → Observability → Build\u002FDeploy → Quick Sanity Check\n- Quick Sanity Check at the end: 8-10 items verifiable in 2 minutes\n\n### Tier 3: Reference Manuals (Keep Separately)\n\n- Can be long (100-250 lines), detailed, with code examples\n- Version-specific (Spring Boot 4.x, Fiber v3, React 19+, Angular 17+)\n- Contains tutorials, migration guides, option comparisons\n- NOT ticked before launch — consulted when a launch checklist item fails\n- Named without \"Launch\" suffix: `spring-boot-api.md`, `react-js.md`\n\n## Ponytail Filter\n\nWhen reviewing existing verbose checklists:\n1. Strip tutorials, code examples, and version-specific trivia\n2. Keep only tick boxes (`- [ ]`) with one-line descriptions\n3. Link to vault notes (`→ [[vault-note]]`) instead of embedding explanations\n4. Target ~40-50 items per file\n5. Keep original as deep reference; create `-v2.md` or rename to `{Domain} Launch.md`\n\nIf a checklist item needs > 1 line of explanation, it belongs in the reference manual, not the launch checklist.\n\n## Reference Checklists (ai-checklist family — a second house style)\n\n`checklist\u002Fai-checklist\u002F` is not the tick-first launch family. Its files (`ai.md`, `claude-driven.md`, `general-agents-driven.md`, plus topic files added since) are **reference checklists**: deeper, explanation-carrying, still tickable. Same vault, different style — match the family you are writing into.\n\nHouse style of the reference family:\n- Filename: `lowercase-hyphen.md` (`loop-engineering.md`, never `Loop Engineering.md`)\n- H1: `# \u003CTopic> Checklist`\n- Header blockquote: one-line purpose → `Siblings:` cross-links → `Last updated: YYYY-MM-DD (new file — \u003Cwhy>)`; bump the date on every later edit\n- Numbered sections (`## 1. …`), items as `- [ ] **Bold lead** — one-sentence explanation.` with inline `→ [[link]] §n` pointers\n- House-standard extras where they fit: a `Scoping` tier table adapted from the tier model in [[ai]] \u002F [[general-agents-driven]], a `Quick Pre-Flight` minimum-bar list, and a `Sources` footer attributing each reference (`source — title (date): what it contributed`)\n- ⚠️ Emerging or contested topics: draw on several primary sources (canonical vendor engineering posts + practitioner write-ups), state plainly that the terminology is unsettled, and never present a new term as a settled standard\n\nAuthoring workflow:\n1. Read 1–2 sibling files in the target folder first and match the living style — styles drift; the most recent file in the folder beats any written convention\n2. Cross-link consistently: siblings by `[[lowercase-hyphen]]`; cross-vault notes by path-style with alias (`[[career-path\u002F…\u002F03_Agent_Loops_and_Orchestration|Agent Loops and Orchestration]]`); never spaces in backlinks\n3. Verify before reporting done: every `[[wikilink]]` resolves, no ambiguous basenames → `obsidian-vault-maintenance` → `scripts\u002Fverify_files.py`\n4. `checklist\u002FOverview.md` indexes only the original \"improved\" launch set — it does not list the ai-checklist family. Do not silently restructure it; offer the index update\n\n**\"Repo or checklist?\"** — when the user asks whether a topic deserves a repository, default to a vault checklist. A repository earns its existence only once executable artifacts exist (harness skeleton, example topologies, eval scripts); then the checklist becomes the repo's docs and the vault keeps a pointer.\n\n## Cross-Referencing Rules\n\n- Generic → Framework: \"For {framework} details, see [[framework-vX-api]]\"\n- Framework → Generic: \"Tick [[{Domain} Launch]] first\"\n- Generic ↔ Vaults: Every item links `→ [[vault-note]]` for deep knowledge\n\n## Common Missing Sections\n\nWhen reviewing checklists, always check for these commonly missing sections:\n- **Routing** (frontend): file-based routing, dynamic routes, navigation guards, 404\n- **Form validation**: Zod\u002Fschema + server-side re-validation (client UX, server security)\n- **OpenAPI\u002FSwagger** (backend): auto-generated docs, annotations\n- **Secrets management**: never in source code, Vault\u002FK8s\u002Fenv vars\n- **Graceful shutdown**: drain connections, close DB on SIGTERM\n\n## Auditing Existing Checklists (Domain Specialist Review)\n\nWhen a user asks to \"audit\" or \"review\" an existing checklist for production readiness:\n\n### 1. Read ALL files in the checklist folder first\nChecklists are usually a collection: a general file + engine\u002Ftopic-specific companions. Read every file in the folder before auditing — cross-file consistency matters (shared tier matrix format, shared wikilink targets, consistent section depth).\n\n### 2. Check for mandatory cross-cutting sections\nEvery production-grade checklist (database, AI, infrastructure) should have these cross-cutting sections. If missing, flag as 🔴 critical:\n- **Privacy & Data Protection** — PII inventory, right to erasure, retention, anonymization, data subject requests\n- **Data Quality** — validation rules, profiling, drift monitoring, integrity checks\n- **Maintenance & Operations** — routine maintenance, vacuum\u002Fcompaction, statistics freshness, deadlock detection\n\nThese are the three sections most commonly missing from checklists written by application engineers — they think about \"does it work\" not \"is the data correct\u002Fsafe\u002Fmaintainable over time.\"\n\n### 3. Engine-specific gap analysis\nEach engine has unique operational concerns that a general checklist can't cover. When auditing an engine-specific checklist, verify the engine's signature features are present (not just general DB principles). See `references\u002Fdatabase-checklist-audit-domains.md` for the full per-engine gap list (PostgreSQL, MongoDB, Valkey, Elasticsearch, ClickHouse, SQLite, Cassandra, plus AI\u002FLLM-specific sections).\n\n### 4. Tier matrix synchronization\nWhen you add or expand sections in a checklist:\n- The **tier scoping matrix table** must grow correspondingly — one row per section\n- The **Quick Sanity Check** must add launch-critical items from new sections\n- Re-verify: does every section in the checklist body have a row in the tier matrix?\n\n### 5. Honest scope warnings in tier matrices\nAdd explicit warnings when a technology doesn't fit certain tiers:\n- SQLite: \"⚠️ Typically not SQLite territory at Tier 5+ — consider migrating to PostgreSQL\"\n- Cassandra: \"⚠️ Overkill below Tier 4 — choose when you need >10K writes\u002Fsec or multi-DC active-active\"\nThis prevents the \"golden hammer\" problem where engineers scale a technology past its design intent.\n\n### 6. Section renumbering\nWhen adding sections to the middle of a checklist, renumber ALL subsequent sections and update ALL internal cross-references (e.g., \"see §4\"). A full `write_file` rewrite is cleaner than multiple fragile `patch` calls when renumbering changes most of the file.\n\n### 7. Update cross-references in companion files\nWhen a general checklist gains new engine companions (e.g., database.md now references elasticsearch.md), update the general file's header to list all companions. Keep wikilinks consistent across the collection.\n\n### 8. \"Last updated\" date\nBump the date in the header blockquote on every file you modify.\n\n## Framework Picks (Ponytail Default)\n\nWhen user asks \"what framework for X?\" without experience:\n- Go → Fiber v3 (simpler than stdlib, lighter than Echo, Axum for Rust fans)\n- Rust → Axum (tokio-native, no macros, great docs. NOT Actix\u002FRocket\u002FWarp for beginners)\n- Node → NestJS (opinionated, DI, TypeScript-first, Express\u002FFastify)\n- Frontend state → TanStack Query for server state, signals\u002Fstores for client state. No Redux.\n","# Project Launch Checklist — Two-Tier System\n\nBuild production-ready launch checklists for any tech stack. Pattern: generic tick-first checklists + framework-specific companions + reference manuals.\n\n## The Two-Tier Pattern\n\nThree file types per domain, living in the same folder:\n\n```\ndomain-checklist\u002F\n├── {Domain} Launch.md           ← Generic. Tick FIRST. ~40-50 items, framework-agnostic.\n├── framework-vX-api.md          ← Framework companion. Tick AFTER generic. ~70-85 items.\n├── framework-reference.md       ← Reference manual. Deep dives, tutorials. Not ticked.\n└── (repeat for each framework)\n```\n\n### Tier 1: Generic Launch Checklist\n\n- 6-8 sections, 5-7 one-line items each\n- Target: ~45 items total\n- Every item: `- [ ] Description → [[vault-note]]` — links to knowledge vault, no explanations embedded\n- Zero code examples. Zero version trivia. Zero tutorials.\n- Sections: Security → API\u002FState → Database\u002FData → Resilience\u002FPerformance → Observability → Testing → Deployment → (+ Routing for frontend)\n- References framework companions: \"For {framework} specifics, see [[framework-vX]]\"\n- References dependent checklists: \"Assumes [[Related Launch]] is already done\"\n\n### Tier 2: Framework Companion\n\n- \"Tick [[{Domain} Launch]] first\" in the header\n- Framework-specific only: setup, routing, DI, middleware, ORM, testing tools\n- ~70-85 items. Still tickable. Still no tutorials.\n- Sections mirror generic but with framework details:\n  Project Setup → App Structure → Middleware\u002FRouting → Auth → Config\u002FSecrets → DB\u002FState → Testing → Observability → Build\u002FDeploy → Quick Sanity Check\n- Quick Sanity Check at the end: 8-10 items verifiable in 2 minutes\n\n### Tier 3: Reference Manuals (Keep Separately)\n\n- Can be long (100-250 lines), detailed, with code examples\n- Version-specific (Spring Boot 4.x, Fiber v3, React 19+, Angular 17+)\n- Contains tutorials, migration guides, option comparisons\n- NOT ticked before launch — consulted when a launch checklist item fails\n- Named without \"Launch\" suffix: `spring-boot-api.md`, `react-js.md`\n\n## Ponytail Filter\n\nWhen reviewing existing verbose checklists:\n1. Strip tutorials, code examples, and version-specific trivia\n2. Keep only tick boxes (`- [ ]`) with one-line descriptions\n3. Link to vault notes (`→ [[vault-note]]`) instead of embedding explanations\n4. Target ~40-50 items per file\n5. Keep original as deep reference; create `-v2.md` or rename to `{Domain} Launch.md`\n\nIf a checklist item needs > 1 line of explanation, it belongs in the reference manual, not the launch checklist.\n\n## Reference Checklists (ai-checklist family — a second house style)\n\n`checklist\u002Fai-checklist\u002F` is not the tick-first launch family. Its files (`ai.md`, `claude-driven.md`, `general-agents-driven.md`, plus topic files added since) are **reference checklists**: deeper, explanation-carrying, still tickable. Same vault, different style — match the family you are writing into.\n\nHouse style of the reference family:\n- Filename: `lowercase-hyphen.md` (`loop-engineering.md`, never `Loop Engineering.md`)\n- H1: `# \u003CTopic> Checklist`\n- Header blockquote: one-line purpose → `Siblings:` cross-links → `Last updated: YYYY-MM-DD (new file — \u003Cwhy>)`; bump the date on every later edit\n- Numbered sections (`## 1. …`), items as `- [ ] **Bold lead** — one-sentence explanation.` with inline `→ [[link]] §n` pointers\n- House-standard extras where they fit: a `Scoping` tier table adapted from the tier model in [[ai]] \u002F [[general-agents-driven]], a `Quick Pre-Flight` minimum-bar list, and a `Sources` footer attributing each reference (`source — title (date): what it contributed`)\n- ⚠️ Emerging or contested topics: draw on several primary sources (canonical vendor engineering posts + practitioner write-ups), state plainly that the terminology is unsettled, and never present a new term as a settled standard\n\nAuthoring workflow:\n1. Read 1–2 sibling files in the target folder first and match the living style — styles drift; the most recent file in the folder beats any written convention\n2. Cross-link consistently: siblings by `[[lowercase-hyphen]]`; cross-vault notes by path-style with alias (`[[career-path\u002F…\u002F03_Agent_Loops_and_Orchestration|Agent Loops and Orchestration]]`); never spaces in backlinks\n3. Verify before reporting done: every `[[wikilink]]` resolves, no ambiguous basenames → `obsidian-vault-maintenance` → `scripts\u002Fverify_files.py`\n4. `checklist\u002FOverview.md` indexes only the original \"improved\" launch set — it does not list the ai-checklist family. Do not silently restructure it; offer the index update\n\n**\"Repo or checklist?\"** — when the user asks whether a topic deserves a repository, default to a vault checklist. A repository earns its existence only once executable artifacts exist (harness skeleton, example topologies, eval scripts); then the checklist becomes the repo's docs and the vault keeps a pointer.\n\n## Cross-Referencing Rules\n\n- Generic → Framework: \"For {framework} details, see [[framework-vX-api]]\"\n- Framework → Generic: \"Tick [[{Domain} Launch]] first\"\n- Generic ↔ Vaults: Every item links `→ [[vault-note]]` for deep knowledge\n\n## Common Missing Sections\n\nWhen reviewing checklists, always check for these commonly missing sections:\n- **Routing** (frontend): file-based routing, dynamic routes, navigation guards, 404\n- **Form validation**: Zod\u002Fschema + server-side re-validation (client UX, server security)\n- **OpenAPI\u002FSwagger** (backend): auto-generated docs, annotations\n- **Secrets management**: never in source code, Vault\u002FK8s\u002Fenv vars\n- **Graceful shutdown**: drain connections, close DB on SIGTERM\n\n## Auditing Existing Checklists (Domain Specialist Review)\n\nWhen a user asks to \"audit\" or \"review\" an existing checklist for production readiness:\n\n### 1. Read ALL files in the checklist folder first\nChecklists are usually a collection: a general file + engine\u002Ftopic-specific companions. Read every file in the folder before auditing — cross-file consistency matters (shared tier matrix format, shared wikilink targets, consistent section depth).\n\n### 2. Check for mandatory cross-cutting sections\nEvery production-grade checklist (database, AI, infrastructure) should have these cross-cutting sections. If missing, flag as 🔴 critical:\n- **Privacy & Data Protection** — PII inventory, right to erasure, retention, anonymization, data subject requests\n- **Data Quality** — validation rules, profiling, drift monitoring, integrity checks\n- **Maintenance & Operations** — routine maintenance, vacuum\u002Fcompaction, statistics freshness, deadlock detection\n\nThese are the three sections most commonly missing from checklists written by application engineers — they think about \"does it work\" not \"is the data correct\u002Fsafe\u002Fmaintainable over time.\"\n\n### 3. Engine-specific gap analysis\nEach engine has unique operational concerns that a general checklist can't cover. When auditing an engine-specific checklist, verify the engine's signature features are present (not just general DB principles). See `references\u002Fdatabase-checklist-audit-domains.md` for the full per-engine gap list (PostgreSQL, MongoDB, Valkey, Elasticsearch, ClickHouse, SQLite, Cassandra, plus AI\u002FLLM-specific sections).\n\n### 4. Tier matrix synchronization\nWhen you add or expand sections in a checklist:\n- The **tier scoping matrix table** must grow correspondingly — one row per section\n- The **Quick Sanity Check** must add launch-critical items from new sections\n- Re-verify: does every section in the checklist body have a row in the tier matrix?\n\n### 5. Honest scope warnings in tier matrices\nAdd explicit warnings when a technology doesn't fit certain tiers:\n- SQLite: \"⚠️ Typically not SQLite territory at Tier 5+ — consider migrating to PostgreSQL\"\n- Cassandra: \"⚠️ Overkill below Tier 4 — choose when you need >10K writes\u002Fsec or multi-DC active-active\"\nThis prevents the \"golden hammer\" problem where engineers scale a technology past its design intent.\n\n### 6. Section renumbering\nWhen adding sections to the middle of a checklist, renumber ALL subsequent sections and update ALL internal cross-references (e.g., \"see §4\"). A full `write_file` rewrite is cleaner than multiple fragile `patch` calls when renumbering changes most of the file.\n\n### 7. Update cross-references in companion files\nWhen a general checklist gains new engine companions (e.g., database.md now references elasticsearch.md), update the general file's header to list all companions. Keep wikilinks consistent across the collection.\n\n### 8. \"Last updated\" date\nBump the date in the header blockquote on every file you modify.\n\n## Framework Picks (Ponytail Default)\n\nWhen user asks \"what framework for X?\" without experience:\n- Go → Fiber v3 (simpler than stdlib, lighter than Echo, Axum for Rust fans)\n- Rust → Axum (tokio-native, no macros, great docs. NOT Actix\u002FRocket\u002FWarp for beginners)\n- Node → NestJS (opinionated, DI, TypeScript-first, Express\u002FFastify)\n- Frontend state → TanStack Query for server state, signals\u002Fstores for client state. No Redux.\n",{"name":5,"description":7},"main","2988869c5a7d7be2225c9ea7a54a4a56a59b0d45","workflow\u002Fhermes-main-profile\u002Fproject-launch-checklist",0,"https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup","https:\u002F\u002Fgithub.com\u002Foat431","https:\u002F\u002Fpanomete.com\u002F","Hope and Luck is not a part of the strategy, \r\n\r\nSoftskill produces plan Hard skill produce product.","2026-11-03 00:43:08",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add oat431\u002Fhermes_config_backup --skill project-launch-checklist",{"tool":39,"command":40},"bunx","bunx skills add oat431\u002Fhermes_config_backup --skill project-launch-checklist",{"tool":42,"command":43},"pnpm","pnpm dlx skills add oat431\u002Fhermes_config_backup --skill project-launch-checklist","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup\u002Fblob\u002Fmain\u002Fworkflow\u002Fhermes-main-profile\u002Fproject-launch-checklist\u002FSKILL.md",true,[47],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fdatabase-checklist-audit-domains.md","REFERENCE","参考文档",7982,"https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup\u002Fblob\u002Fmain\u002Fworkflow\u002Fhermes-main-profile\u002Fproject-launch-checklist\u002Freferences\u002Fdatabase-checklist-audit-domains.md",[54,62,69,76,83,90],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":58,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7AYZ2JY3NFKAPQSC39N5F3F","project-spec-docs","Fill\u002Fupdate project_spec docs (templates, MM handoffs).","MIT","https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup\u002Fblob\u002Fmain\u002Fworkflow\u002Fui-ux\u002Fproject-spec-docs\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":58,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7AYYRZPE7HQX7778558X52S","penpot-mcp","Penpot MCP: connect, verify, and fix streaming via nginx.","https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup\u002Fblob\u002Fmain\u002Fworkflow\u002Fui-ux\u002Fpenpot-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},"01M7AYYNKP61CN2281VMJDXMB5","nginx-streaming-proxy","Configure nginx for streaming endpoints (SSE, MCP, WS).","https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup\u002Fblob\u002Fmain\u002Fworkflow\u002Fui-ux\u002Fnginx-streaming-proxy\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":58,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7AYYJP0MDV1D3WVEEZB3SGA","branding-ci","Use for brand\u002FCI identity, style guides, and brand docs.","https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup\u002Fblob\u002Fmain\u002Fworkflow\u002Fui-ux\u002Fbranding-ci\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},"01M7AYYGCXVT97DDTCM0ZJT6F6","yuanbao","Yuanbao (元宝) groups: @mention users, query info\u002Fmembers.","https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup\u002Fblob\u002Fmain\u002Fworkflow\u002Fshared-skills\u002Fyuanbao\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7AYYC2Y65NMGMD4GQXAZMMS","slidev","Create and present web-based slidedecks for developers using Slidev with Markdown, Vue components, code highlighting, animations, and interactive features. Use when building technical presentations, conference talks, code walkthroughs, teaching materials, or developer decks.","https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup\u002Fblob\u002Fmain\u002Fworkflow\u002Fshared-skills\u002Fslidev\u002FSKILL.md",[],[]]