[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NBJRC2WTJS7VC2TQTHWX4C":3,"skill-same:01M6NBJRC2WTJS7VC2TQTHWX4C":79},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":54,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M6NBJRC2WTJS7VC2TQTHWX4C","self-improvement",null,"What it does: Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.. When to use it: This is a converted skill from ClawHub, review its content for usage instructions.","frostmute\u002Fclaw2manus","frostmute","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F989225?v=4","01M6NBHXR4YSBQ7KYM0A0HVWY4","Jonathan J Wagner","01M6NBHXWB6K68MVTSPX5D563E",4,"MIT","https:\u002F\u002Fgithub.com\u002Ffrostmute\u002Fclaw2manus\u002Fblob\u002Fmain\u002Fexamples\u002Foutput\u002Fself-improving-agent\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"improvement","self improvement","self","use","capability","for","usage","errors","operation","learnings","task","review","recurring","command","tool","knowledge","continuous improvement","api","tasks","clawhub","2026-11-10 10:12:30",false,"---\nname: self-improvement\ndescription: 'What it does: Captures learnings, errors, and corrections to enable\n  continuous improvement. Use when: (1) A command or operation fails unexpectedly,\n  (2) User corrects Claude (''No, that''s wrong...'', ''Actually...''), (3) User requests\n  a capability that doesn''t exist, (4) An external API or tool fails, (5) Claude\n  realizes its knowledge is outdated or incorrect, (6) A better approach is discovered\n  for a recurring task. Also review learnings before major tasks.. When to use it:\n  This is a converted skill from ClawHub, review its content for usage instructions.'\n---\n\n# Self-Improvement Skill\n\nLog learnings and errors to markdown files for continuous improvement. Coding agents can later process these into fixes, and important learnings get promoted to project memory.\n\n## First-Use Initialisation\n\nBefore logging anything, ensure the `.learnings\u002F` directory and files exist in the project or workspace root. If any are missing, create them:\n\n```bash\nmkdir -p .learnings\n[ -f .learnings\u002FLEARNINGS.md ] || printf \"# Learnings\\n\\nCorrections, insights, and knowledge gaps captured during development.\\n\\n**Categories**: correction | insight | knowledge_gap | best_practice\\n\\n---\\n\" > .learnings\u002FLEARNINGS.md\n[ -f .learnings\u002FERRORS.md ] || printf \"# Errors\\n\\nCommand failures and integration errors.\\n\\n---\\n\" > .learnings\u002FERRORS.md\n[ -f .learnings\u002FFEATURE_REQUESTS.md ] || printf \"# Feature Requests\\n\\nCapabilities requested by the user.\\n\\n---\\n\" > .learnings\u002FFEATURE_REQUESTS.md\n```\n\nNever overwrite existing files. This is a no-op if `.learnings\u002F` is already initialised.\n\nDo not log secrets, tokens, private keys, environment variables, or full source\u002Fconfig files unless the user explicitly asks for that level of detail. Prefer short summaries or redacted excerpts over raw command output or full transcripts.\n\nIf you want automatic reminders or setup assistance, use the opt-in hook workflow described in [Hook Integration](#hook-integration).\n\n## Quick Reference\n\n| Situation | Action |\n| --- | --- |\n| Command\u002Foperation fails | Log to `.learnings\u002FERRORS.md` |\n| User corrects you | Log to `.learnings\u002FLEARNINGS.md` with category `correction` |\n| User wants missing feature | Log to `.learnings\u002FFEATURE_REQUESTS.md` |\n| API\u002Fexternal tool fails | Log to `.learnings\u002FERRORS.md` with integration details |\n| Knowledge was outdated | Log to `.learnings\u002FLEARNINGS.md` with category `knowledge_gap` |\n| Found better approach | Log to `.learnings\u002FLEARNINGS.md` with category `best_practice` |\n| Simplify\u002FHarden recurring patterns | Log\u002Fupdate `.learnings\u002FLEARNINGS.md` with `Source: simplify-and-harden` and a stable `Pattern-Key` |\n| Similar to existing entry | Link with **See Also**, consider priority bump |\n| Broadly applicable learning | Promote to `soul.md`, `subtasks.md`, and\u002For `.github\u002Fcopilot-instructions.md` |\n| Workflow improvements | Promote to `subtasks.md` (OpenClaw workspace) |\n| Tool gotchas | Promote to `TOOLS.md` (OpenClaw workspace) |\n| Behavioral patterns | Promote to `SOUL.md` (OpenClaw workspace) |\n\n## OpenClaw Setup (Recommended)\n\nOpenClaw is the primary platform for this skill. It uses workspace-based prompt injection with automatic skill loading.\n\n### Installation\n\n**Via ClawdHub (recommended):**\n\n```bash\nManus: To install skills, place them in `\u002Fhome\u002Fubuntu\u002Fskills\u002F` directory.\n```\n\n**Manual:**\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fpeterskoett\u002Fself-improving-agent.git \u002Fhome\u002Fubuntu\u002Fskills\u002Fself-improving-agent\n```\n\n### Workspace Structure\n\nOpenClaw injects these files into every session:\n\n```\n\u002Fhome\u002Fubuntu\u002Fworkspace\u002F\n├── subtasks.md\n├── SOUL.md\n├── TOOLS.md\n├── MEMORY.md\n├── memory\u002F\n│   └── YYYY-MM-DD.md\n└── .learnings\u002F\n    ├── LEARNINGS.md\n    ├── ERRORS.md\n    └── FEATURE_REQUESTS.md\n```\n\n### Promotion Targets\n\nWhen learnings prove broadly applicable, promote them to workspace files:\n\n| Learning Type | Promote To | Example |\n| --- | --- | --- |\n| Behavioral patterns | `SOUL.md` | \"Be concise, avoid disclaimers\" |\n| Workflow improvements | `subtasks.md` | \"Spawn sub-agents for long tasks\" |\n| Tool gotchas | `TOOLS.md` | \"Git push needs auth configured first\" |\n\n### Inter-Session Communication\n\nOpenClaw provides tools to share learnings across sessions:\n\n* **Manus: Use `shell` tool with `ps aux` or similar to list processes, or `gws` to list Google Workspace sessions.** — View active\u002Frecent sessions\n* **Manus: Session history is managed by the agent. Direct access to other session's history is not supported.** — Read another session's transcript\n* **Manus: Inter-agent communication is not directly supported via a 'send' tool. Consider using shared files or a message queue.** — Send a learning to another session\n* **Manus: To spawn sub-agents, define a new phase in the plan or use parallel processing for homogeneous tasks.** — Spawn a sub-agent for background work\n\nUse these only in trusted environments and only when the user explicitly wants cross-session sharing.\n\n## Generic Setup (Other Agents)\n\nFor Claude Code, Codex, Copilot, or other agents, create `.learnings\u002F` in the project or workspace root.\n\n## Logging Format\n\n### Learning Entry\n\nAppend to `.learnings\u002FLEARNINGS.md`:\n\n```md\n## [LRN-YYYYMMDD-XXX] category\n\n**Logged**: ISO-8601 timestamp\n**Priority**: low | medium | high | critical\n**Status**: pending\n**Area**: frontend | backend | infra | tests | docs | config\n\n### Summary\nOne-line description\n\n### Details\nFull context\n\n### Suggested Action\nSpecific fix or improvement\n\n### Metadata\n- Source: conversation | error | user_feedback\n- Related Files: path\u002Fto\u002Ffile.ext\n- Tags: tag1, tag2\n```\n\n### Error Entry\n\nAppend to `.learnings\u002FERRORS.md`:\n\n```md\n## [ERR-YYYYMMDD-XXX] skill_or_command_name\n\n**Logged**: ISO-8601 timestamp\n**Priority**: high\n**Status**: pending\n\n### Summary\nBrief description\n\n### Error\nActual error message\n\n### Context\n- Command attempted\n- Input\u002Fparameters\n- Environment details\n\n### Suggested Fix\nPrevention strategy\n```\n\n### Feature Request Entry\n\nAppend to `.learnings\u002FFEATURE_REQUESTS.md`:\n\n```md\n## [REQ-YYYYMMDD-XXX] feature_name\n\n**Logged**: ISO-8601 timestamp\n**Priority**: low | medium | high\n**Status**: pending\n\n### Summary\nBrief description\n\n### Use Case\nWhy needed\n\n### Suggested Implementation\nHow to implement\n```\n","# Self-Improvement Skill\n\nLog learnings and errors to markdown files for continuous improvement. Coding agents can later process these into fixes, and important learnings get promoted to project memory.\n\n## First-Use Initialisation\n\nBefore logging anything, ensure the `.learnings\u002F` directory and files exist in the project or workspace root. If any are missing, create them:\n\n```bash\nmkdir -p .learnings\n[ -f .learnings\u002FLEARNINGS.md ] || printf \"# Learnings\\n\\nCorrections, insights, and knowledge gaps captured during development.\\n\\n**Categories**: correction | insight | knowledge_gap | best_practice\\n\\n---\\n\" > .learnings\u002FLEARNINGS.md\n[ -f .learnings\u002FERRORS.md ] || printf \"# Errors\\n\\nCommand failures and integration errors.\\n\\n---\\n\" > .learnings\u002FERRORS.md\n[ -f .learnings\u002FFEATURE_REQUESTS.md ] || printf \"# Feature Requests\\n\\nCapabilities requested by the user.\\n\\n---\\n\" > .learnings\u002FFEATURE_REQUESTS.md\n```\n\nNever overwrite existing files. This is a no-op if `.learnings\u002F` is already initialised.\n\nDo not log secrets, tokens, private keys, environment variables, or full source\u002Fconfig files unless the user explicitly asks for that level of detail. Prefer short summaries or redacted excerpts over raw command output or full transcripts.\n\nIf you want automatic reminders or setup assistance, use the opt-in hook workflow described in [Hook Integration](#hook-integration).\n\n## Quick Reference\n\n| Situation | Action |\n| --- | --- |\n| Command\u002Foperation fails | Log to `.learnings\u002FERRORS.md` |\n| User corrects you | Log to `.learnings\u002FLEARNINGS.md` with category `correction` |\n| User wants missing feature | Log to `.learnings\u002FFEATURE_REQUESTS.md` |\n| API\u002Fexternal tool fails | Log to `.learnings\u002FERRORS.md` with integration details |\n| Knowledge was outdated | Log to `.learnings\u002FLEARNINGS.md` with category `knowledge_gap` |\n| Found better approach | Log to `.learnings\u002FLEARNINGS.md` with category `best_practice` |\n| Simplify\u002FHarden recurring patterns | Log\u002Fupdate `.learnings\u002FLEARNINGS.md` with `Source: simplify-and-harden` and a stable `Pattern-Key` |\n| Similar to existing entry | Link with **See Also**, consider priority bump |\n| Broadly applicable learning | Promote to `soul.md`, `subtasks.md`, and\u002For `.github\u002Fcopilot-instructions.md` |\n| Workflow improvements | Promote to `subtasks.md` (OpenClaw workspace) |\n| Tool gotchas | Promote to `TOOLS.md` (OpenClaw workspace) |\n| Behavioral patterns | Promote to `SOUL.md` (OpenClaw workspace) |\n\n## OpenClaw Setup (Recommended)\n\nOpenClaw is the primary platform for this skill. It uses workspace-based prompt injection with automatic skill loading.\n\n### Installation\n\n**Via ClawdHub (recommended):**\n\n```bash\nManus: To install skills, place them in `\u002Fhome\u002Fubuntu\u002Fskills\u002F` directory.\n```\n\n**Manual:**\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fpeterskoett\u002Fself-improving-agent.git \u002Fhome\u002Fubuntu\u002Fskills\u002Fself-improving-agent\n```\n\n### Workspace Structure\n\nOpenClaw injects these files into every session:\n\n```\n\u002Fhome\u002Fubuntu\u002Fworkspace\u002F\n├── subtasks.md\n├── SOUL.md\n├── TOOLS.md\n├── MEMORY.md\n├── memory\u002F\n│   └── YYYY-MM-DD.md\n└── .learnings\u002F\n    ├── LEARNINGS.md\n    ├── ERRORS.md\n    └── FEATURE_REQUESTS.md\n```\n\n### Promotion Targets\n\nWhen learnings prove broadly applicable, promote them to workspace files:\n\n| Learning Type | Promote To | Example |\n| --- | --- | --- |\n| Behavioral patterns | `SOUL.md` | \"Be concise, avoid disclaimers\" |\n| Workflow improvements | `subtasks.md` | \"Spawn sub-agents for long tasks\" |\n| Tool gotchas | `TOOLS.md` | \"Git push needs auth configured first\" |\n\n### Inter-Session Communication\n\nOpenClaw provides tools to share learnings across sessions:\n\n* **Manus: Use `shell` tool with `ps aux` or similar to list processes, or `gws` to list Google Workspace sessions.** — View active\u002Frecent sessions\n* **Manus: Session history is managed by the agent. Direct access to other session's history is not supported.** — Read another session's transcript\n* **Manus: Inter-agent communication is not directly supported via a 'send' tool. Consider using shared files or a message queue.** — Send a learning to another session\n* **Manus: To spawn sub-agents, define a new phase in the plan or use parallel processing for homogeneous tasks.** — Spawn a sub-agent for background work\n\nUse these only in trusted environments and only when the user explicitly wants cross-session sharing.\n\n## Generic Setup (Other Agents)\n\nFor Claude Code, Codex, Copilot, or other agents, create `.learnings\u002F` in the project or workspace root.\n\n## Logging Format\n\n### Learning Entry\n\nAppend to `.learnings\u002FLEARNINGS.md`:\n\n```md\n## [LRN-YYYYMMDD-XXX] category\n\n**Logged**: ISO-8601 timestamp\n**Priority**: low | medium | high | critical\n**Status**: pending\n**Area**: frontend | backend | infra | tests | docs | config\n\n### Summary\nOne-line description\n\n### Details\nFull context\n\n### Suggested Action\nSpecific fix or improvement\n\n### Metadata\n- Source: conversation | error | user_feedback\n- Related Files: path\u002Fto\u002Ffile.ext\n- Tags: tag1, tag2\n```\n\n### Error Entry\n\nAppend to `.learnings\u002FERRORS.md`:\n\n```md\n## [ERR-YYYYMMDD-XXX] skill_or_command_name\n\n**Logged**: ISO-8601 timestamp\n**Priority**: high\n**Status**: pending\n\n### Summary\nBrief description\n\n### Error\nActual error message\n\n### Context\n- Command attempted\n- Input\u002Fparameters\n- Environment details\n\n### Suggested Fix\nPrevention strategy\n```\n\n### Feature Request Entry\n\nAppend to `.learnings\u002FFEATURE_REQUESTS.md`:\n\n```md\n## [REQ-YYYYMMDD-XXX] feature_name\n\n**Logged**: ISO-8601 timestamp\n**Priority**: low | medium | high\n**Status**: pending\n\n### Summary\nBrief description\n\n### Use Case\nWhy needed\n\n### Suggested Implementation\nHow to implement\n```\n",{"name":5,"description":7},"main","0c871403571744bbdc3d3e138daf5655566d581e","examples\u002Foutput\u002Fself-improving-agent",0,"https:\u002F\u002Fgithub.com\u002Ffrostmute\u002Fclaw2manus","https:\u002F\u002Ffrostmute.github.io\u002Fclaw2manus\u002F","https:\u002F\u002Fgithub.com\u002Ffrostmute","https:\u002F\u002Fjjwagner.vercel.app","Two decades of professional creative experience as the foundation for self-taught open-source development and system architecture design.","2026-10-19 16:36:39",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add frostmute\u002Fclaw2manus --skill self-improvement",{"tool":65,"command":66},"bunx","bunx skills add frostmute\u002Fclaw2manus --skill self-improvement",{"tool":68,"command":69},"pnpm","pnpm dlx skills add frostmute\u002Fclaw2manus --skill self-improvement","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ffrostmute\u002Fclaw2manus\u002Fblob\u002Fmain\u002Fexamples\u002Foutput\u002Fself-improving-agent\u002FSKILL.md",true,[73],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"CONVERSION_REPORT.md","REFERENCE","参考文档",1462,"https:\u002F\u002Fgithub.com\u002Ffrostmute\u002Fclaw2manus\u002Fblob\u002Fmain\u002Fexamples\u002Foutput\u002Fself-improving-agent\u002FCONVERSION_REPORT.md",[80,91,101,114,137,145],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":87,"publishedAt":44},"01M6NBKDE93JDEXVW10CGQ6SRC","beta-skill","A beta skill by author-b","https:\u002F\u002Fgithub.com\u002Ffrostmute\u002Fclaw2manus\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fintegration_repo\u002Fauthor-b\u002Fskill-beta\u002FSKILL.md",[86],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[88,89,90],"beta","beta skill","author",{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":98,"publishedAt":44},"01M6NBK8N734FNRW2AFAS3ETM6","alpha-skill","An alpha skill by author-a","https:\u002F\u002Fgithub.com\u002Ffrostmute\u002Fclaw2manus\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fintegration_repo\u002Fauthor-a\u002Fskill-alpha\u002FSKILL.md",[97],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[99,100,90],"alpha","alpha skill",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":108,"publishedAt":44},"01M6NBJYHAW6FD6D4H9XM9W7CV","gamma-skill","Yet another skill, sharing an author with alpha-skill","https:\u002F\u002Fgithub.com\u002Ffrostmute\u002Fclaw2manus\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fintegration_repo\u002Fauthor-a\u002Fanother-one\u002FSKILL.md",[107],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[109,110,99,111,112,113,90],"gamma","gamma skill","sharing","another skill","with",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":121,"publishedAt":44},"01M6NBJMBDNBAFP3VRCYN464PG","pwnclaw-security-scan","What it does: Test your AI agent for security vulnerabilities using PwnClaw. Runs 50+ attacks (prompt injection, jailbreaks, social engineering, MCP poisoning, and more) and provides fix instructions. Use when your agent needs a security check or hardening.. When to use it: This is a converted skill from ClawHub, review its content for usage instructions.","https:\u002F\u002Fgithub.com\u002Ffrostmute\u002Fclaw2manus\u002Fblob\u002Fmain\u002Fexamples\u002Foutput\u002Fpwnclaw-security-scan\u002FSKILL.md",[120],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[122,123,124,125,126,35,27,127,128,129,130,131,132,43,133,134,135,30,29,136],"scan","security scan","pwnclaw security scan","security","prompt injection","fix","check","prompt","test","ai agent","more","social","social engineering","attacks","MCP",{"skillNo":138,"name":5,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":44},"01M6NBJ476MQBPWP984C4RXR18","Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.","https:\u002F\u002Fgithub.com\u002Ffrostmute\u002Fclaw2manus\u002Fblob\u002Fmain\u002Fexamples\u002Finput\u002Fself-improving-agent\u002FSKILL.md",[],[25,26,24,29,35,42,41,40,39,38,37,36,27,34,33,32,31,143,144,28],"requests","external api",{"skillNo":146,"name":116,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":151,"publishedAt":44},"01M6NBJ04MWB5H2XK62HGEAPPH","Test your AI agent for security vulnerabilities using PwnClaw. Runs 50+ attacks (prompt injection, jailbreaks, social engineering, MCP poisoning, and more) and provides fix instructions. Use when your agent needs a security check or hardening.","https:\u002F\u002Fgithub.com\u002Ffrostmute\u002Fclaw2manus\u002Fblob\u002Fmain\u002Fexamples\u002Finput\u002Fpwnclaw-security-scan\u002FSKILL.md",[150],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[122,124,125,123,127,29,132,135,134,133,152,27,153,128,129,130,131,154,126,136],"security check","instructions","vulnerabilities"]