[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6JKX6GY1EP82GCJ0BSWRCWS":3,"skill-same:01M6JKX6GY1EP82GCJ0BSWRCWS":75},{"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":23,"publishedAt":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":51,"ownerHtmlUrl":52,"ownerBlogUrl":53,"ownerDescription":6,"updatedAt":54,"install":55,"resources":68},"01M6JKX6GY1EP82GCJ0BSWRCWS","judgment-day",null,"Parallel adversarial review protocol that launches two independent blind judge sub-agents simultaneously to review the same target, synthesizes their findings, applies fixes, and re-judges until both pass or escalates after 2 iterations. Trigger: When user says \"judgment day\", \"judgment-day\", \"review adversarial\", \"dual review\", \"doble review\", \"juzgar\", \"que lo juzguen\".","LongLeo287\u002FOmniClaw","LongLeo287","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F141803367?v=4","01M6JK75C62VCNZKR5BRZ386YV","LongLeo","01M6JK75GQ78TSP1ZPXNKK3MCH",9,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fagent_teams_lite\u002Fpayload\u002Fskills\u002Fjudgment_day\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36],"judgment","judgment day","review","adversarial review","protocol","parallel","programming","user","trigger","judge","re","fixes","review adversarial","2026-11-10 10:12:30",false,"---\nname: judgment-day\ndescription: >\n  Parallel adversarial review protocol that launches two independent blind judge sub-agents\n  simultaneously to review the same target, synthesizes their findings, applies fixes,\n  and re-judges until both pass or escalates after 2 iterations.\n  Trigger: When user says \"judgment day\", \"judgment-day\", \"review adversarial\", \"dual review\",\n  \"doble review\", \"juzgar\", \"que lo juzguen\".\nlicense: Apache-2.0\nmetadata:\n  author: gentleman-programming\n  version: \"1.0\"\n---\n\n## When to Use\n\n- User explicitly asks for \"judgment day\", \"judgment-day\", or equivalent trigger phrases\n- After significant implementations before merging\n- When high-confidence review of code, features, or architecture is needed\n- When a single reviewer might miss edge cases or have blind spots\n- When the cost of a production bug is higher than the cost of two review rounds\n\n## Critical Patterns\n\n### Pattern 0: Skill Resolution (BEFORE launching judges)\n\nFollow the **Skill Resolver Protocol** (`_shared\u002Fskill-resolver.md`) before launching ANY sub-agent:\n\n1. Obtain the skill registry (engram → `.atl\u002Fskill-registry.md` from the project root → skip if none)\n2. Identify the target files\u002Fscope — what code will the judges review?\n3. Match relevant skills from the registry's **Compact Rules** by:\n   - **Code context**: file extensions\u002Fpaths of the target (e.g., `.tsx` → react-19, typescript)\n   - **Task context**: \"review code\" → framework\u002Flanguage skills; \"create PR\" → branch-pr skill\n4. Build a `## Project Standards (auto-resolved)` block with the matching compact rules\n5. Inject this block into BOTH Judge prompts AND the Fix Agent prompt (identical for all)\n\nThis ensures judges review against project-specific standards, not just generic best practices.\n\n**If no registry exists**: warn the user (\"No skill registry found — judges will review without project-specific standards. Run `skill-registry` to fix this.\") and proceed with generic review only.\n\n### Pattern 1: Parallel Blind Review\n\n- Launch **TWO** sub-agents via `delegate` (async, parallel — never sequential)\n- Each agent receives the **same target** but works **independently**\n- **Neither agent knows about the other** — no cross-contamination\n- Both use identical review criteria but may find different issues\n- NEVER do the review yourself as the orchestrator — your job is coordination only\n\n### Pattern 2: Verdict Synthesis\n\nThe **orchestrator** (NOT a sub-agent) compares results after both `delegation_read` calls return:\n\n```\nConfirmed   → found by BOTH agents          → high confidence, fix immediately\nSuspect A   → found ONLY by Judge A         → needs triage\nSuspect B   → found ONLY by Judge B         → needs triage\nContradiction → agents DISAGREE on the same thing → flag for manual decision\n```\n\nPresent findings as a structured verdict table (see Output Format).\n\n### Pattern 3: Fix and Re-judge\n\n1. If **confirmed issues** exist → delegate a **Fix Agent** (separate delegation)\n2. After Fix Agent completes → re-launch **both judges in parallel** (same blind protocol, fresh delegates)\n3. **Max 2 fix iterations.** If still failing → JUDGMENT: ESCALATED — report to user with full history\n4. If both judges return clean → JUDGMENT: APPROVED ✅\n\n---\n\n## Decision Tree\n\n```\nUser asks for \"judgment day\"\n│\n├── Target is specific files\u002Ffeature\u002Fcomponent?\n│   ├── YES → continue\n│   └── NO → ask user to specify scope before proceeding\n│\n▼\nResolve skills (Pattern 0): read registry → match by code + task context → build Project Standards block\n▼\nLaunch Judge A + Judge B in parallel (delegate, async) — with Project Standards injected\n▼\nWait for both to complete (delegation_read both)\n▼\nSynthesize verdict\n│\n├── No issues found?\n│   └── JUDGMENT: APPROVED ✅ (stop here)\n│\n├── Issues found (confirmed, suspect, or contradictions)?\n│   └── Delegate Fix Agent with confirmed issues list\n│       ▼\n│       Wait for Fix Agent to complete\n│       ▼\n│       Re-launch Judge A + Judge B in parallel (Round 2)\n│       ▼\n│       Synthesize verdict\n│       │\n│       ├── Clean → JUDGMENT: APPROVED ✅\n│       │\n│       └── Still issues → Delegate Fix Agent again (Round 3 \u002F iteration 2)\n│           ▼\n│           Re-launch Judge A + Judge B in parallel (Round 3)\n│           ▼\n│           Synthesize verdict\n│           │\n│           ├── Clean → JUDGMENT: APPROVED ✅\n│           └── Still issues → JUDGMENT: ESCALATED ⚠️ (report to user)\n```\n\n---\n\n## Sub-Agent Prompt Templates\n\n### Judge Prompt (use for BOTH Judge A and Judge B — identical)\n\n```\nYou are an adversarial code reviewer. Your ONLY job is to find problems.\n\n## Target\n{describe target: files, feature, architecture, component}\n\n{if compact rules were resolved in Pattern 0, inject the following block — otherwise OMIT this entire section}\n## Project Standards (auto-resolved)\n{paste matching compact rules blocks from the skill registry}\n\n## Review Criteria\n- Correctness: Does the code do what it claims? Are there logical errors?\n- Edge cases: What inputs or states aren't handled?\n- Error handling: Are errors caught, propagated, and logged properly?\n- Performance: Any N+1 queries, inefficient loops, unnecessary allocations?\n- Security: Any injection risks, exposed secrets, improper auth checks?\n- Naming & conventions: Does it follow the project's established patterns AND the Project Standards above?\n{if user provided custom criteria, add here}\n\n## Return Format\nReturn a structured list of findings ONLY. No praise, no approval.\n\nEach finding:\n- Severity: CRITICAL | WARNING | SUGGESTION\n- File: path\u002Fto\u002Ffile.ext (line N if applicable)\n- Description: What is wrong and why it matters\n- Suggested fix: one-line description of the fix (not code, just intent)\n\nAlways include at the end: **Skill Resolution**: {injected|fallback-registry|fallback-path|none} — {details}\n\nIf you find NO issues, return:\nVERDICT: CLEAN — No issues found.\n\n## Instructions\nBe thorough and adversarial. Assume the code has bugs until proven otherwise.\nYour job is to find problems, NOT to approve. Do not summarize. Do not praise.\n```\n\n### Fix Agent Prompt\n\n```\nYou are a surgical fix agent. You apply ONLY the confirmed issues listed below.\n\n## Confirmed Issues to Fix\n{paste the confirmed findings table from the verdict synthesis}\n\n{if compact rules were resolved in Pattern 0, inject the following block — otherwise OMIT this entire section}\n## Project Standards (auto-resolved)\n{paste matching compact rules blocks from the skill registry}\n\n## Context\n- Original review criteria: {paste same criteria used for judges}\n- Target: {same target description}\n\n## Instructions\n- Fix ONLY the confirmed issues listed above\n- Do NOT refactor beyond what is strictly needed to fix each issue\n- Do NOT change code that was not flagged\n- After each fix, note: file changed, line changed, what was done\n\nReturn a summary:\n## Fixes Applied\n- [file:line] — {what was fixed}\n\n**Skill Resolution**: {injected|fallback-registry|fallback-path|none} — {details}\n```\n\n---\n\n## Output Format\n\n```markdown\n## Judgment Day — {target}\n\n### Round {N} — Verdict\n\n| Finding | Judge A | Judge B | Severity | Status |\n|---------|---------|---------|----------|--------|\n| Missing null check in auth.go:42 | ✅ | ✅ | CRITICAL | Confirmed |\n| Race condition in worker.go:88 | ✅ | ❌ | WARNING | Suspect (A only) |\n| Naming mismatch in handler.go:15 | ❌ | ✅ | SUGGESTION | Suspect (B only) |\n| Error swallowed in db.go:201 | ✅ | ✅ | CRITICAL | Confirmed |\n\n**Confirmed issues**: 2 CRITICAL\n**Suspect issues**: 1 WARNING, 1 SUGGESTION\n**Contradictions**: none\n\n### Fixes Applied (Round {N})\n- `auth.go:42` — Added nil check before dereferencing user pointer\n- `db.go:201` — Propagated error instead of silently returning nil\n\n### Round {N+1} — Re-judgment\n- Judge A: PASS ✅ — No issues found\n- Judge B: PASS ✅ — No issues found\n\n---\n\n### JUDGMENT: APPROVED ✅\nBoth judges pass clean. The target is cleared for merge.\n```\n\n### Escalation Format (after 2 failed iterations)\n\n```markdown\n## Judgment Day — {target}\n\n### JUDGMENT: ESCALATED ⚠️\n\nAfter 2 fix iterations, both judges still report issues.\nManual review required before proceeding.\n\n### Remaining Issues\n| Finding | Judge A | Judge B | Severity |\n|---------|---------|---------|----------|\n| {description} | ✅ | ✅ | CRITICAL |\n\n### History\n- Round 1: {N} confirmed issues found\n- Fix 1: applied {list}\n- Round 2: {N} issues remain\n- Fix 2: applied {list}\n- Round 3: {N} issues remain → escalated\n\nRecommend: human review of the remaining issues above before re-running judgment day.\n```\n\n---\n\n## Language\n\n- **Spanish input → Rioplatense**: \"Juicio iniciado\", \"Los jueces están trabajando en paralelo...\", \"Los jueces coinciden\", \"Juicio terminado — Aprobado\", \"Escalado — necesita revisión humana\"\n- **English input**: \"Judgment initiated\", \"Both judges are working in parallel...\", \"Both judges agree\", \"Judgment complete — Approved\", \"Escalated — requires human review\"\n\n---\n\n## Rules\n\n- The **orchestrator NEVER reviews code itself** — it only launches judges, reads results, and synthesizes\n- Judges MUST be launched as `delegate` (async) so they run in **parallel**\n- The **Fix Agent is a separate delegation** — never use one of the judges as the fixer\n- If user provides **custom review criteria**, include them in BOTH judge prompts (identical)\n- If target scope is **unclear**, stop and ask before launching — partial reviews are useless\n- **Max 2 fix iterations** — on the third failure, escalate with full report, do not loop forever\n- Always wait for BOTH judges to complete before synthesizing — never accept a partial verdict\n- Suspect findings (only one judge) are reported but NOT automatically fixed — triage and escalate to user if needed\n\n---\n\n## Commands\n\n```bash\n# No CLI commands — this is a pure orchestration protocol.\n# Execution happens via delegate() and delegation_read() tool calls.\n```\n","## When to Use\n\n- User explicitly asks for \"judgment day\", \"judgment-day\", or equivalent trigger phrases\n- After significant implementations before merging\n- When high-confidence review of code, features, or architecture is needed\n- When a single reviewer might miss edge cases or have blind spots\n- When the cost of a production bug is higher than the cost of two review rounds\n\n## Critical Patterns\n\n### Pattern 0: Skill Resolution (BEFORE launching judges)\n\nFollow the **Skill Resolver Protocol** (`_shared\u002Fskill-resolver.md`) before launching ANY sub-agent:\n\n1. Obtain the skill registry (engram → `.atl\u002Fskill-registry.md` from the project root → skip if none)\n2. Identify the target files\u002Fscope — what code will the judges review?\n3. Match relevant skills from the registry's **Compact Rules** by:\n   - **Code context**: file extensions\u002Fpaths of the target (e.g., `.tsx` → react-19, typescript)\n   - **Task context**: \"review code\" → framework\u002Flanguage skills; \"create PR\" → branch-pr skill\n4. Build a `## Project Standards (auto-resolved)` block with the matching compact rules\n5. Inject this block into BOTH Judge prompts AND the Fix Agent prompt (identical for all)\n\nThis ensures judges review against project-specific standards, not just generic best practices.\n\n**If no registry exists**: warn the user (\"No skill registry found — judges will review without project-specific standards. Run `skill-registry` to fix this.\") and proceed with generic review only.\n\n### Pattern 1: Parallel Blind Review\n\n- Launch **TWO** sub-agents via `delegate` (async, parallel — never sequential)\n- Each agent receives the **same target** but works **independently**\n- **Neither agent knows about the other** — no cross-contamination\n- Both use identical review criteria but may find different issues\n- NEVER do the review yourself as the orchestrator — your job is coordination only\n\n### Pattern 2: Verdict Synthesis\n\nThe **orchestrator** (NOT a sub-agent) compares results after both `delegation_read` calls return:\n\n```\nConfirmed   → found by BOTH agents          → high confidence, fix immediately\nSuspect A   → found ONLY by Judge A         → needs triage\nSuspect B   → found ONLY by Judge B         → needs triage\nContradiction → agents DISAGREE on the same thing → flag for manual decision\n```\n\nPresent findings as a structured verdict table (see Output Format).\n\n### Pattern 3: Fix and Re-judge\n\n1. If **confirmed issues** exist → delegate a **Fix Agent** (separate delegation)\n2. After Fix Agent completes → re-launch **both judges in parallel** (same blind protocol, fresh delegates)\n3. **Max 2 fix iterations.** If still failing → JUDGMENT: ESCALATED — report to user with full history\n4. If both judges return clean → JUDGMENT: APPROVED ✅\n\n---\n\n## Decision Tree\n\n```\nUser asks for \"judgment day\"\n│\n├── Target is specific files\u002Ffeature\u002Fcomponent?\n│   ├── YES → continue\n│   └── NO → ask user to specify scope before proceeding\n│\n▼\nResolve skills (Pattern 0): read registry → match by code + task context → build Project Standards block\n▼\nLaunch Judge A + Judge B in parallel (delegate, async) — with Project Standards injected\n▼\nWait for both to complete (delegation_read both)\n▼\nSynthesize verdict\n│\n├── No issues found?\n│   └── JUDGMENT: APPROVED ✅ (stop here)\n│\n├── Issues found (confirmed, suspect, or contradictions)?\n│   └── Delegate Fix Agent with confirmed issues list\n│       ▼\n│       Wait for Fix Agent to complete\n│       ▼\n│       Re-launch Judge A + Judge B in parallel (Round 2)\n│       ▼\n│       Synthesize verdict\n│       │\n│       ├── Clean → JUDGMENT: APPROVED ✅\n│       │\n│       └── Still issues → Delegate Fix Agent again (Round 3 \u002F iteration 2)\n│           ▼\n│           Re-launch Judge A + Judge B in parallel (Round 3)\n│           ▼\n│           Synthesize verdict\n│           │\n│           ├── Clean → JUDGMENT: APPROVED ✅\n│           └── Still issues → JUDGMENT: ESCALATED ⚠️ (report to user)\n```\n\n---\n\n## Sub-Agent Prompt Templates\n\n### Judge Prompt (use for BOTH Judge A and Judge B — identical)\n\n```\nYou are an adversarial code reviewer. Your ONLY job is to find problems.\n\n## Target\n{describe target: files, feature, architecture, component}\n\n{if compact rules were resolved in Pattern 0, inject the following block — otherwise OMIT this entire section}\n## Project Standards (auto-resolved)\n{paste matching compact rules blocks from the skill registry}\n\n## Review Criteria\n- Correctness: Does the code do what it claims? Are there logical errors?\n- Edge cases: What inputs or states aren't handled?\n- Error handling: Are errors caught, propagated, and logged properly?\n- Performance: Any N+1 queries, inefficient loops, unnecessary allocations?\n- Security: Any injection risks, exposed secrets, improper auth checks?\n- Naming & conventions: Does it follow the project's established patterns AND the Project Standards above?\n{if user provided custom criteria, add here}\n\n## Return Format\nReturn a structured list of findings ONLY. No praise, no approval.\n\nEach finding:\n- Severity: CRITICAL | WARNING | SUGGESTION\n- File: path\u002Fto\u002Ffile.ext (line N if applicable)\n- Description: What is wrong and why it matters\n- Suggested fix: one-line description of the fix (not code, just intent)\n\nAlways include at the end: **Skill Resolution**: {injected|fallback-registry|fallback-path|none} — {details}\n\nIf you find NO issues, return:\nVERDICT: CLEAN — No issues found.\n\n## Instructions\nBe thorough and adversarial. Assume the code has bugs until proven otherwise.\nYour job is to find problems, NOT to approve. Do not summarize. Do not praise.\n```\n\n### Fix Agent Prompt\n\n```\nYou are a surgical fix agent. You apply ONLY the confirmed issues listed below.\n\n## Confirmed Issues to Fix\n{paste the confirmed findings table from the verdict synthesis}\n\n{if compact rules were resolved in Pattern 0, inject the following block — otherwise OMIT this entire section}\n## Project Standards (auto-resolved)\n{paste matching compact rules blocks from the skill registry}\n\n## Context\n- Original review criteria: {paste same criteria used for judges}\n- Target: {same target description}\n\n## Instructions\n- Fix ONLY the confirmed issues listed above\n- Do NOT refactor beyond what is strictly needed to fix each issue\n- Do NOT change code that was not flagged\n- After each fix, note: file changed, line changed, what was done\n\nReturn a summary:\n## Fixes Applied\n- [file:line] — {what was fixed}\n\n**Skill Resolution**: {injected|fallback-registry|fallback-path|none} — {details}\n```\n\n---\n\n## Output Format\n\n```markdown\n## Judgment Day — {target}\n\n### Round {N} — Verdict\n\n| Finding | Judge A | Judge B | Severity | Status |\n|---------|---------|---------|----------|--------|\n| Missing null check in auth.go:42 | ✅ | ✅ | CRITICAL | Confirmed |\n| Race condition in worker.go:88 | ✅ | ❌ | WARNING | Suspect (A only) |\n| Naming mismatch in handler.go:15 | ❌ | ✅ | SUGGESTION | Suspect (B only) |\n| Error swallowed in db.go:201 | ✅ | ✅ | CRITICAL | Confirmed |\n\n**Confirmed issues**: 2 CRITICAL\n**Suspect issues**: 1 WARNING, 1 SUGGESTION\n**Contradictions**: none\n\n### Fixes Applied (Round {N})\n- `auth.go:42` — Added nil check before dereferencing user pointer\n- `db.go:201` — Propagated error instead of silently returning nil\n\n### Round {N+1} — Re-judgment\n- Judge A: PASS ✅ — No issues found\n- Judge B: PASS ✅ — No issues found\n\n---\n\n### JUDGMENT: APPROVED ✅\nBoth judges pass clean. The target is cleared for merge.\n```\n\n### Escalation Format (after 2 failed iterations)\n\n```markdown\n## Judgment Day — {target}\n\n### JUDGMENT: ESCALATED ⚠️\n\nAfter 2 fix iterations, both judges still report issues.\nManual review required before proceeding.\n\n### Remaining Issues\n| Finding | Judge A | Judge B | Severity |\n|---------|---------|---------|----------|\n| {description} | ✅ | ✅ | CRITICAL |\n\n### History\n- Round 1: {N} confirmed issues found\n- Fix 1: applied {list}\n- Round 2: {N} issues remain\n- Fix 2: applied {list}\n- Round 3: {N} issues remain → escalated\n\nRecommend: human review of the remaining issues above before re-running judgment day.\n```\n\n---\n\n## Language\n\n- **Spanish input → Rioplatense**: \"Juicio iniciado\", \"Los jueces están trabajando en paralelo...\", \"Los jueces coinciden\", \"Juicio terminado — Aprobado\", \"Escalado — necesita revisión humana\"\n- **English input**: \"Judgment initiated\", \"Both judges are working in parallel...\", \"Both judges agree\", \"Judgment complete — Approved\", \"Escalated — requires human review\"\n\n---\n\n## Rules\n\n- The **orchestrator NEVER reviews code itself** — it only launches judges, reads results, and synthesizes\n- Judges MUST be launched as `delegate` (async) so they run in **parallel**\n- The **Fix Agent is a separate delegation** — never use one of the judges as the fixer\n- If user provides **custom review criteria**, include them in BOTH judge prompts (identical)\n- If target scope is **unclear**, stop and ask before launching — partial reviews are useless\n- **Max 2 fix iterations** — on the third failure, escalate with full report, do not loop forever\n- Always wait for BOTH judges to complete before synthesizing — never accept a partial verdict\n- Suspect findings (only one judge) are reported but NOT automatically fixed — triage and escalate to user if needed\n\n---\n\n## Commands\n\n```bash\n# No CLI commands — this is a pure orchestration protocol.\n# Execution happens via delegate() and delegation_read() tool calls.\n```\n",{"name":5,"license":15,"metadata":42,"description":45},{"author":43,"version":44},"gentleman-programming","1.0","Parallel adversarial review protocol that launches two independent blind judge sub-agents simultaneously to review the same target, synthesizes their findings, applies fixes, and re-judges until both pass or escalates after 2 iterations. Trigger: When user says \"judgment day\", \"judgment-day\", \"review adversarial\", \"dual review\", \"doble review\", \"juzgar\", \"que lo juzguen\".\n","main","c173cdffe08e788a99b91928a831b476b8434838","ecosystem\u002Fskills\u002Fagent_teams_lite\u002Fpayload\u002Fskills\u002Fjudgment_day",0,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw","https:\u002F\u002Fportfolio-longleo.vercel.app\u002Flabs\u002Fomniclaw.html","https:\u002F\u002Fgithub.com\u002FLongLeo287","https:\u002F\u002Fwww.facebook.com\u002FResourceRookie2023","2026-09-30 00:58:05",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add LongLeo287\u002FOmniClaw --skill judgment-day",{"tool":61,"command":62},"bunx","bunx skills add LongLeo287\u002FOmniClaw --skill judgment-day",{"tool":64,"command":65},"pnpm","pnpm dlx skills add LongLeo287\u002FOmniClaw --skill judgment-day","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fagent_teams_lite\u002Fpayload\u002Fskills\u002Fjudgment_day\u002FSKILL.md",true,[69],{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"_DIR_IDENTITY.md","REFERENCE","参考文档",347,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fagent_teams_lite\u002Fpayload\u002Fskills\u002Fjudgment_day\u002F_DIR_IDENTITY.md",[76,116,138,166,182,209],{"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":80,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":95,"publishedAt":37},"01M6JR0KQP4MHT32TN40D9CBFX","UI-UX Pro Max","Advanced UI\u002FUX analysis and generation skills with data-driven patterns. Python scripts (core.py, search.py) for systematic UI pattern extraction, design system generation, and component search from curated data sources.","MIT","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fui_components\u002Fui_ux_pro_max\u002FSKILL.md",[83,86,87,92],{"categoryNo":84,"categoryName":85,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",{"categoryNo":93,"categoryName":94,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000033","数据分析师",[96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115],"ux","ui","ui ux pro max","max","pro","ui ux","design","component","search","analysis","team","rd","ui-ux","active","systematic","scripts","pattern extraction","sources","advanced","data-driven",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":80,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":123,"publishedAt":37},"01M6JR0EF5AEQHP2FSTB57H05P","shadcn-ui","Expert guidance for integrating and building applications with shadcn\u002Fui components, including component discovery, installation, customization, and best practices.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fui_components\u002Fshadcn_ui\u002FSKILL.md",[122],{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},[124,97,125,126,103,127,128,129,130,106,131,132,133,109,134,135,136,137],"shadcn","shadcn ui","components","core","best practices","applications","discovery","customization","guidance","expert","installation","ui components","with","for",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":80,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":147,"publishedAt":37},"01M6JR08F51BEN17RHFYX65WVE","zustand_store_ts","Create Zustand stores with TypeScript, subscribeWithSelector middleware, and proper state\u002Faction separation. Use when building React state management, creating global stores, or implementing reactive state patterns with Zustand.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fzustand_store_ts\u002FSKILL.md",[144],{"categoryNo":145,"categoryName":146,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,136,164,165],"zustand store ts","zustand","store","typescript","microsoft","react","create","state management","state","react state management","management","global","use","patterns","separation","middleware","action","implementing",{"skillNo":167,"name":149,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":80,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":171,"publishedAt":37},"01M6JR00TDMVAFFCZXZ04AN7Q7","Zustand state management guide. Use when working with store code (src\u002Fstore\u002F**), implementing actions, managing state, or creating slices. Triggers on Zustand store development, state management questions, or action implementation.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fzustand\u002FSKILL.md",[],[149,172,155,173,156,174,175,158,176,160,177,178,179,150,136,180,181,164,165],"development","code","actions","src","guide","implementation","zustand state","triggers","questions","zustand state management",{"skillNo":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":80,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":192,"publishedAt":37},"01M6JQZSWV4KWJP112G6XHEP44","youtube_summarizer","Automatically fetch YouTube video transcripts, generate structured summaries, and send full transcripts to messaging platforms. Detects YouTube URLs and provides metadata, key insights, and downloadable transcripts.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fyoutube_summarizer\u002FSKILL.md",[188,191],{"categoryNo":189,"categoryName":190,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208],"youtube","youtube summarizer","summarizer","generate","metadata","messaging","Video","fetch","telegram","transcription","summarization","structured","full","insights","transcripts","summaries",{"skillNo":210,"name":211,"nameZh":6,"description":212,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":80,"licenseFileUrl":6,"sourceHtmlUrl":213,"categories":214,"keywords":215,"publishedAt":37},"01M6JQZN3QJB6B77JGKJD62DQT","youtube_clipper","YouTube 视频智能剪辑工具。下载视频和字幕，AI 分析生成精细章节（几分钟级别）， 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频，并生成总结文案。 使用场景：当用户需要剪辑 YouTube 视频、生成短视频片段、制作双语字幕版本时。 关键词：视频剪辑、YouTube、字幕翻译、双语字幕、视频下载、clip video","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fyoutube_clipper\u002FSKILL.md",[],[193,216,217,199,218,219,220,221,222,223,224,225,226,227,228,229,230],"clipper","youtube clipper","Bash","下载","视频","生成","关键词","翻译","read","write","clip","总结","工具","文案","sonnet"]