[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AYW4VCGQA27H9YY5R8QRCP":3,"skill-same:01M7AYW4VCGQA27H9YY5R8QRCP":56},{"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":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":39,"ownerDescription":40,"updatedAt":41,"install":42,"resources":55},"01M7AYW4VCGQA27H9YY5R8QRCP","checklist-audit",null,"Use when auditing or applying a vault checklist.","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\u002Fqa\u002Fchecklist-audit\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: checklist-audit\ndescription: Use when auditing or applying a vault checklist.\ndifficulty: senior\ncreated: 2026-08-06\ntags: [checklist, audit, review, vault, knowledge-base, gap-analysis]\n---\n\n# Checklist Audit\n\n> Systematic review of checklists, reference documents, and guides against authoritative vault knowledge bases to identify gaps, strengthen items, and ensure cross-reference consistency.\n\n## When to Use\n\n- User asks to \"audit\", \"review\", or \"check\" a checklist or reference document\n- User wants to verify a document against their vault (SWEBOK, CyBOK, career paths, etc.)\n- User wants to identify gaps, missing items, or outdated guidance in a structured document\n- The document has sections, checklists, tier matrices, or sanity checks that need verification\n- User asks to **apply** a checklist TO a project (\"check this checklist and apply it\") — the\n  checklist is the standard, the repo\u002Fapp is the target: use *Applying a Checklist to a Project* below\n\n## Audit Workflow\n\n### 1. Read the Target Document\n\n```bash\nread_file(path=\"\u003Ctarget-checklist-path>\")\n```\n\nUnderstand the document's structure, purpose, audience, and existing cross-references.\n\n### 2. Gather Vault References in Parallel\n\nRead all relevant knowledge base files that could inform the audit. Use `terminal` with `find` if directory structure is unclear:\n\n```bash\nfind \"F:\u002Fobsidian_note\u002Fswe-knowledge\u002Fcareer-path\u002F\u003Cdomain>\" -name \"*.md\" -type f | sort\n```\n\nBatch reads in parallel for efficiency. Target:\n- Career path overviews and capability notes for the domain\n- Relevant Body of Knowledge chapters (SWEBOK, CyBOK, DMBOK, SEBoK)\n- Any existing specialist notes that cover the same territory\n\n### 3. Compile Structured Findings\n\nCreate a findings table:\n\n| # | Finding | Source | Severity | Location |\n|---|---------|--------|----------|----------|\n\nSeverity levels:\n- 🔴 **Gap** — Critical missing item that violates authoritative source\n- 🟡 **Improve** — Existing item needs strengthening or clarification\n- 🟢 **Nice-to-have** — Optional enhancement\n- ✅ **Already Strong** — Leave unchanged\n\n### 4. Apply Patches Systematically\n\nFor each finding, use `patch` tool with `mode=replace`:\n\n1. **Add new items** at appropriate section with clear rationale\n2. **Strengthen existing items** — expand wording, add context\n3. **Update section titles** if they no longer reflect content\n4. **Maintain numbering** — keep sections sequential, no gaps\n\n### 5. Update Tier Matrix\n\nIf the document has a tier applicability matrix:\n- Add rows for new sections\n- Update column entries to reflect new items\n- Ensure row numbers match actual section numbers\n\n### 6. Update Sanity Checks\n\nAdd items for each new critical section item. Keep concise (10-15 items max). Each sanity item should map to a section item.\n\n### 7. Verify Cross-References\n\nCheck:\n- Section numbering is sequential (no gaps)\n- Internal references (§X) point to correct sections\n- Tier matrix rows match actual sections\n- External references ([[Release]], [[API Launch]]) still valid\n\n### 8. Final Verification Read\n\n```bash\nread_file(path=\"\u003Ctarget-checklist-path>\")\n```\n\nConfirm all patches applied correctly and document is internally consistent.\n\n### 9. Compile Summary Report\n\nProvide before\u002Fafter metrics, changes summary (✅ added, 🟡 improved, 🟢 untouched), cross-reference verification results, and final verdict with risk reduction statement.\n\n## Pitfalls\n\n- **Don't add redundancy** — if an item is already covered, strengthen the existing item, don't duplicate\n- **Don't over-audit** — if a section is already strong, leave it alone\n- **Don't break cross-references** — when adding items or renumbering, verify §X references still work\n- **Don't inflate sanity checks** — focused subset (10-15 items), not a parallel list\n- **Don't ignore tier matrices** — if the document has one, you MUST update it\n- **Don't invent authoritative sources** — only cite vault files you actually read\n- **Patch text must match exactly** — re-read sections before patching to avoid whitespace\u002Fmismatch errors\n\n## Examples\n\n### QA Checklist Audit (2026-08-06)\n\n**Target:** `checklist\u002Fqa-checklist\u002Fqa.md`\n**Vault refs:** 18 files from `career-path\u002F10_Quality_and_Test_Engineering\u002F` + SWEBOK Testing chapter\n**Key gaps closed:** Systematic test design, exploratory testing, shift-left, test oracles, regression strategy, RCA\n**Result:** 152 → 172 lines, added §7 Exploratory Testing, strengthened §1 with shift-left\n\n### Security Checklist Audit (2026-08-06)\n\n**Target:** `checklist\u002Fsecurity-checklist\u002Fsecurity.md`\n**Vault refs:** Security Engineer overview, CyBOK Software Security, CyBOK Secure SDL, QA Security Testing note\n**Key gaps closed:** CSRF, TOCTOU\u002Frace conditions, error leakage, IaC scanning, remediation SLAs, crypto API misuse, security champions, abuse cases, hallucination mitigation\n**Result:** 203 → 222 lines, 11 → 17 sanity items, full OWASP Top 10 coverage verified\n\n## Folder Expansion Workflow\n\nAfter auditing a checklist, check if its folder follows the vault pattern: **general checklist + technology-specific companions**. If the folder has only the general checklist, recommend expansion.\n\n### Identifying Expansion Candidates\n\n1. List all checklist folders: `find \"F:\u002Fobsidian_note\u002Fswe-knowledge\u002Fchecklist\" -type d`\n2. Count files per folder — folders with 3+ files have the pattern (e.g., `api-checklist\u002F` has `api.md` + `fastapi.md`, `spring-boot-api.md`, etc.)\n3. Folders with only 1 file are expansion candidates\n\n### Creating Technology-Specific Checklists\n\nUse `delegate_task` with `tasks` array (max 3 per batch due to `max_concurrent_children=3` limit). Batch remaining tasks in subsequent dispatches.\n\nEach technology checklist should include:\n- Setup & installation (language-specific package managers, dependencies)\n- Core concepts and lifecycle\n- Common patterns with real code examples\n- CI integration\n- Quick sanity check (10-15 items)\n- Tier applicability matrix (7 tiers matching vault convention)\n- Cross-references back to the general checklist\n\n### Delegation Pattern\n\n```\nBatch 1: delegate_task(tasks=[task1, task2, task3])  # max 3\nBatch 2: delegate_task(tasks=[task4, task5, task6])  # next 3\n...\nFinal items: write_file directly if subagents can't write\n```\n\n**Pitfall:** Subagents may report \"cannot write files\" in sandboxed environments. If so, use their detailed output as content and `write_file` directly.\n\n### Recommended Checklist Set by Domain\n\n| Domain | General | Technology-Specific Companions |\n|--------|---------|-------------------------------|\n| QA | `qa.md` | pytest, jest-vitest, junit, go-test, playwright, cypress, k6-performance, testcontainers, mutation-testing, accessibility-testing |\n| API | `api.md` | Framework-specific (already populated) |\n| Database | `database.md` | Engine-specific (already populated) |\n| Web | `web.md` | Framework-specific (already populated) |\n\n## Applying a Checklist to a Project (compliance assessment)\n\nTrigger: \"check this checklist and apply it\" — the checklist is the standard, the repo\u002Fapp is\nthe target. (Auditing the checklist FILE itself is the workflow above.)\n\n### Workflow\n\n1. **Read the checklist completely first** — it is the scope authority; its own tier matrix\n   decides how much rigor fits the target.\n2. **Tier call before checkboxes.** Using the checklist's scoping matrix, state: the product's\n   risk tier, the repo's real posture (environment model, CI reality), the adopted level (often\n   \"Tier N, adapted\") and the deltas — which sections are N\u002FA and WHY (e.g. no local webServer,\n   no mocking when the suite's purpose is integration evidence).\n3. **Assess section by section** with a fixed legend: ✅ done \u002F 🟡 partial \u002F ⬜ gap→planned \u002F\n   ➖ not applicable + reason \u002F 🔒 blocked on a named open question. Back every status with\n   evidence (command output, grep count, file:line) — no vibes.\n4. **Apply only safe quick wins now**: config defaults that remove observed flakiness, type-check\n   setup (`tsconfig.json` strict + `tsc --noEmit`), runbook\u002Fdebug docs, guard clauses on tests\n   that hang when data is absent. Do NOT mass-refactor working code mid-flight (full POM rewrites\n   etc.) — backlog those with rationale and risk.\n5. **Re-verify each applied item with a real command** (`tsc --noEmit`, `--list`, smoke run) and\n   quote the result in the assessment.\n6. **Checklist-discovered gaps become NEW questions** in the project's question doc (next number;\n   update localized copies + stale counts too) — applying a checklist reliably surfaces scope\n   gaps nobody asked about yet.\n7. **Output shape**: `NN_\u003Ctopic>_checklist_assessment.md` in the project's docs folder (next\n   number in the set), an index row, applied items logged in the decisions log, and sections for\n   \"applied now\", \"backlog (unblocked)\", \"blocked on team answers\".\n\n### Application pitfalls\n\n- **Never silently contradict a recorded team decision** (e.g. an evidence-capture policy). If\n  the checklist says X and the team decided Y, record a documented deviation with the decision\n  reference — do not quietly \"comply\" with the checklist.\n- A N\u002FA status without a stated reason is noise — attach the reason every time.\n- ✅ requires verification in the repo (grep\u002Fcount\u002Frun); \"obviously fine\" is not evidence.\n- After edits, re-check count-bearing text the doc set states elsewhere (N questions, N docs).\n\n## Related Skills\n\n- `playwright-suite-health-review` — deep review\u002Ftriage of E2E suites (a natural application target)\n- `dogfood` — Exploratory QA of live web apps (different: audits documents, not running systems)\n- `spec-driven-code-review` — Code review against specs (different: audits checklists, not code)\n- `requesting-code-review` — How to request reviews (different: performs audits, not requests them)\n","# Checklist Audit\n\n> Systematic review of checklists, reference documents, and guides against authoritative vault knowledge bases to identify gaps, strengthen items, and ensure cross-reference consistency.\n\n## When to Use\n\n- User asks to \"audit\", \"review\", or \"check\" a checklist or reference document\n- User wants to verify a document against their vault (SWEBOK, CyBOK, career paths, etc.)\n- User wants to identify gaps, missing items, or outdated guidance in a structured document\n- The document has sections, checklists, tier matrices, or sanity checks that need verification\n- User asks to **apply** a checklist TO a project (\"check this checklist and apply it\") — the\n  checklist is the standard, the repo\u002Fapp is the target: use *Applying a Checklist to a Project* below\n\n## Audit Workflow\n\n### 1. Read the Target Document\n\n```bash\nread_file(path=\"\u003Ctarget-checklist-path>\")\n```\n\nUnderstand the document's structure, purpose, audience, and existing cross-references.\n\n### 2. Gather Vault References in Parallel\n\nRead all relevant knowledge base files that could inform the audit. Use `terminal` with `find` if directory structure is unclear:\n\n```bash\nfind \"F:\u002Fobsidian_note\u002Fswe-knowledge\u002Fcareer-path\u002F\u003Cdomain>\" -name \"*.md\" -type f | sort\n```\n\nBatch reads in parallel for efficiency. Target:\n- Career path overviews and capability notes for the domain\n- Relevant Body of Knowledge chapters (SWEBOK, CyBOK, DMBOK, SEBoK)\n- Any existing specialist notes that cover the same territory\n\n### 3. Compile Structured Findings\n\nCreate a findings table:\n\n| # | Finding | Source | Severity | Location |\n|---|---------|--------|----------|----------|\n\nSeverity levels:\n- 🔴 **Gap** — Critical missing item that violates authoritative source\n- 🟡 **Improve** — Existing item needs strengthening or clarification\n- 🟢 **Nice-to-have** — Optional enhancement\n- ✅ **Already Strong** — Leave unchanged\n\n### 4. Apply Patches Systematically\n\nFor each finding, use `patch` tool with `mode=replace`:\n\n1. **Add new items** at appropriate section with clear rationale\n2. **Strengthen existing items** — expand wording, add context\n3. **Update section titles** if they no longer reflect content\n4. **Maintain numbering** — keep sections sequential, no gaps\n\n### 5. Update Tier Matrix\n\nIf the document has a tier applicability matrix:\n- Add rows for new sections\n- Update column entries to reflect new items\n- Ensure row numbers match actual section numbers\n\n### 6. Update Sanity Checks\n\nAdd items for each new critical section item. Keep concise (10-15 items max). Each sanity item should map to a section item.\n\n### 7. Verify Cross-References\n\nCheck:\n- Section numbering is sequential (no gaps)\n- Internal references (§X) point to correct sections\n- Tier matrix rows match actual sections\n- External references ([[Release]], [[API Launch]]) still valid\n\n### 8. Final Verification Read\n\n```bash\nread_file(path=\"\u003Ctarget-checklist-path>\")\n```\n\nConfirm all patches applied correctly and document is internally consistent.\n\n### 9. Compile Summary Report\n\nProvide before\u002Fafter metrics, changes summary (✅ added, 🟡 improved, 🟢 untouched), cross-reference verification results, and final verdict with risk reduction statement.\n\n## Pitfalls\n\n- **Don't add redundancy** — if an item is already covered, strengthen the existing item, don't duplicate\n- **Don't over-audit** — if a section is already strong, leave it alone\n- **Don't break cross-references** — when adding items or renumbering, verify §X references still work\n- **Don't inflate sanity checks** — focused subset (10-15 items), not a parallel list\n- **Don't ignore tier matrices** — if the document has one, you MUST update it\n- **Don't invent authoritative sources** — only cite vault files you actually read\n- **Patch text must match exactly** — re-read sections before patching to avoid whitespace\u002Fmismatch errors\n\n## Examples\n\n### QA Checklist Audit (2026-08-06)\n\n**Target:** `checklist\u002Fqa-checklist\u002Fqa.md`\n**Vault refs:** 18 files from `career-path\u002F10_Quality_and_Test_Engineering\u002F` + SWEBOK Testing chapter\n**Key gaps closed:** Systematic test design, exploratory testing, shift-left, test oracles, regression strategy, RCA\n**Result:** 152 → 172 lines, added §7 Exploratory Testing, strengthened §1 with shift-left\n\n### Security Checklist Audit (2026-08-06)\n\n**Target:** `checklist\u002Fsecurity-checklist\u002Fsecurity.md`\n**Vault refs:** Security Engineer overview, CyBOK Software Security, CyBOK Secure SDL, QA Security Testing note\n**Key gaps closed:** CSRF, TOCTOU\u002Frace conditions, error leakage, IaC scanning, remediation SLAs, crypto API misuse, security champions, abuse cases, hallucination mitigation\n**Result:** 203 → 222 lines, 11 → 17 sanity items, full OWASP Top 10 coverage verified\n\n## Folder Expansion Workflow\n\nAfter auditing a checklist, check if its folder follows the vault pattern: **general checklist + technology-specific companions**. If the folder has only the general checklist, recommend expansion.\n\n### Identifying Expansion Candidates\n\n1. List all checklist folders: `find \"F:\u002Fobsidian_note\u002Fswe-knowledge\u002Fchecklist\" -type d`\n2. Count files per folder — folders with 3+ files have the pattern (e.g., `api-checklist\u002F` has `api.md` + `fastapi.md`, `spring-boot-api.md`, etc.)\n3. Folders with only 1 file are expansion candidates\n\n### Creating Technology-Specific Checklists\n\nUse `delegate_task` with `tasks` array (max 3 per batch due to `max_concurrent_children=3` limit). Batch remaining tasks in subsequent dispatches.\n\nEach technology checklist should include:\n- Setup & installation (language-specific package managers, dependencies)\n- Core concepts and lifecycle\n- Common patterns with real code examples\n- CI integration\n- Quick sanity check (10-15 items)\n- Tier applicability matrix (7 tiers matching vault convention)\n- Cross-references back to the general checklist\n\n### Delegation Pattern\n\n```\nBatch 1: delegate_task(tasks=[task1, task2, task3])  # max 3\nBatch 2: delegate_task(tasks=[task4, task5, task6])  # next 3\n...\nFinal items: write_file directly if subagents can't write\n```\n\n**Pitfall:** Subagents may report \"cannot write files\" in sandboxed environments. If so, use their detailed output as content and `write_file` directly.\n\n### Recommended Checklist Set by Domain\n\n| Domain | General | Technology-Specific Companions |\n|--------|---------|-------------------------------|\n| QA | `qa.md` | pytest, jest-vitest, junit, go-test, playwright, cypress, k6-performance, testcontainers, mutation-testing, accessibility-testing |\n| API | `api.md` | Framework-specific (already populated) |\n| Database | `database.md` | Engine-specific (already populated) |\n| Web | `web.md` | Framework-specific (already populated) |\n\n## Applying a Checklist to a Project (compliance assessment)\n\nTrigger: \"check this checklist and apply it\" — the checklist is the standard, the repo\u002Fapp is\nthe target. (Auditing the checklist FILE itself is the workflow above.)\n\n### Workflow\n\n1. **Read the checklist completely first** — it is the scope authority; its own tier matrix\n   decides how much rigor fits the target.\n2. **Tier call before checkboxes.** Using the checklist's scoping matrix, state: the product's\n   risk tier, the repo's real posture (environment model, CI reality), the adopted level (often\n   \"Tier N, adapted\") and the deltas — which sections are N\u002FA and WHY (e.g. no local webServer,\n   no mocking when the suite's purpose is integration evidence).\n3. **Assess section by section** with a fixed legend: ✅ done \u002F 🟡 partial \u002F ⬜ gap→planned \u002F\n   ➖ not applicable + reason \u002F 🔒 blocked on a named open question. Back every status with\n   evidence (command output, grep count, file:line) — no vibes.\n4. **Apply only safe quick wins now**: config defaults that remove observed flakiness, type-check\n   setup (`tsconfig.json` strict + `tsc --noEmit`), runbook\u002Fdebug docs, guard clauses on tests\n   that hang when data is absent. Do NOT mass-refactor working code mid-flight (full POM rewrites\n   etc.) — backlog those with rationale and risk.\n5. **Re-verify each applied item with a real command** (`tsc --noEmit`, `--list`, smoke run) and\n   quote the result in the assessment.\n6. **Checklist-discovered gaps become NEW questions** in the project's question doc (next number;\n   update localized copies + stale counts too) — applying a checklist reliably surfaces scope\n   gaps nobody asked about yet.\n7. **Output shape**: `NN_\u003Ctopic>_checklist_assessment.md` in the project's docs folder (next\n   number in the set), an index row, applied items logged in the decisions log, and sections for\n   \"applied now\", \"backlog (unblocked)\", \"blocked on team answers\".\n\n### Application pitfalls\n\n- **Never silently contradict a recorded team decision** (e.g. an evidence-capture policy). If\n  the checklist says X and the team decided Y, record a documented deviation with the decision\n  reference — do not quietly \"comply\" with the checklist.\n- A N\u002FA status without a stated reason is noise — attach the reason every time.\n- ✅ requires verification in the repo (grep\u002Fcount\u002Frun); \"obviously fine\" is not evidence.\n- After edits, re-check count-bearing text the doc set states elsewhere (N questions, N docs).\n\n## Related Skills\n\n- `playwright-suite-health-review` — deep review\u002Ftriage of E2E suites (a natural application target)\n- `dogfood` — Exploratory QA of live web apps (different: audits documents, not running systems)\n- `spec-driven-code-review` — Code review against specs (different: audits checklists, not code)\n- `requesting-code-review` — How to request reviews (different: performs audits, not requests them)\n",{"name":5,"tags":24,"created":31,"difficulty":32,"description":7},[25,26,27,28,29,30],"checklist","audit","review","vault","knowledge-base","gap-analysis",1785974400000,"senior","main","2988869c5a7d7be2225c9ea7a54a4a56a59b0d45","workflow\u002Fqa\u002Fchecklist-audit",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":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add oat431\u002Fhermes_config_backup --skill checklist-audit",{"tool":48,"command":49},"bunx","bunx skills add oat431\u002Fhermes_config_backup --skill checklist-audit",{"tool":51,"command":52},"pnpm","pnpm dlx skills add oat431\u002Fhermes_config_backup --skill checklist-audit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Foat431\u002Fhermes_config_backup\u002Fblob\u002Fmain\u002Fworkflow\u002Fqa\u002Fchecklist-audit\u002FSKILL.md",true,[],[57,65,72,79,86,93],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"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":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"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":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":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":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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",[],[]]