[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75AVHECYVM81PTGDM5WXPWS":3,"skill-same:01M75AVHECYVM81PTGDM5WXPWS":56},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":39,"ownerHtmlUrl":40,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":41,"install":42,"resources":55},"01M75AVHECYVM81PTGDM5WXPWS","hermes-agent",null,"Manage 0xRay framework from Hermes Agent via the native xray-hermes plugin. Covers the 4 plugin tools (validate, codex_check, health, hooks), lifecycle hooks, slash commands, bridge architecture, and CLI fallback.","0xRayAI\u002Fxray","0xRayAI","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F274879952?v=4","01M75AEEVWK4S4G4N25HAYGB9V","01M75AEEWMHN7H4PQVCJS2938J",2,"MIT","https:\u002F\u002Fgithub.com\u002F0xRayAI\u002Fxray\u002Fblob\u002Fmain\u002Fsrc\u002Fskills\u002Fhermes-agent\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: hermes-agent\ndescription: Manage 0xRay framework from Hermes Agent via the native xray-hermes plugin. Covers the 4 plugin tools (validate, codex_check, health, hooks), lifecycle hooks, slash commands, bridge architecture, and CLI fallback.\nversion: 2.1.0\nauthor: 0xRay AI\nmetadata:\n  hermes:\n    tags: [0xRay, Plugin, Validation, Codex, GitHooks, Bridge]\n    related_skills: []\n---\n\n# 0xRay Hermes Plugin (xray-hermes)\n\nNative Hermes plugin providing 0xRay framework integration — quality gates, codex enforcement, git hooks, and full pre\u002Fpost processing pipeline. Runs via a Node.js bridge to compiled framework components.\n\n## When to Use\n\n- User asks about 0xRay health, validation, or codex checks\n- User wants to install\u002Fmanage git hooks for automated enforcement\n- User asks about the plugin's tools, hooks, or slash commands\n- User asks about bridge errors or framework not loading\n- User wants to validate files before committing or pushing\n\n## Plugin Architecture\n\n```\n~\u002F.hermes\u002Fplugins\u002Fxray-hermes\u002F\n├── __init__.py         # Plugin registration, hooks, slash commands\n├── tools.py            # 4 tool handlers (validate, codex_check, health, hooks)\n├── schemas.py          # JSON schemas the LLM sees\n├── bridge.mjs          # Node.js bridge to compiled 0xRay framework\n├── plugin.yaml         # Plugin metadata (name, version, tools, hooks)\n├── types.py            # TypeScript-equivalent type definitions\n├── after-install.md    # Post-install instructions\n└── test_plugin.py      # Tests\n```\n\n**Bridge protocol:** JSON over stdin\u002Fstdout to `bridge.mjs` (Node.js). The bridge lazy-loads compiled framework modules from `dist\u002F`:\n- `dist\u002Fplugin\u002Fquality-gate.js` — codex violation detection\n- `dist\u002Fprocessors\u002Fprocessor-manager.js` — pre\u002Fpost processor pipeline\n- `dist\u002Fstate\u002Fstate-manager.js` — persistent state\n- `dist\u002Fcore\u002Ffeatures-config.js` — feature flags\n\n**Fallback:** When bridge is unavailable, tools fall back to `npx 0xray` CLI commands.\n\n**Config path resolution:** `XRAY_CONFIG_DIR\u002F` > `.xray\u002F` > built-in defaults.\n\n## 4 Tools\n\n### xray_validate\n\nRun pre-commit validation on files. Uses bridge quality gate + processor pipeline, falls back to CLI.\n\n```\nxray_validate(files=[\"src\u002Fmy-module.ts\"], operation=\"commit\")\nxray_validate(files=[\"src\u002Fauth.ts\", \"src\u002Fauth.test.ts\"], operation=\"modify\")\n```\n\nParameters:\n- `files` (required, array of strings) — file paths to validate\n- `operation` (string) — commit, create, modify, refactor (default: commit)\n\nReturns: pass\u002Ffail with per-file results and violations.\n\n### xray_codex_check\n\nValidate code against the 69-term Universal Development Codex. Checks error-handling, type-safety, performance, security, architecture.\n\n```\nxray_codex_check(code=\"const x: any = foo()\", operation=\"create\")\nxray_codex_check(code=snippet, operation=\"modify\", focus_areas=[\"security\", \"error-handling\"])\n```\n\nParameters:\n- `code` (string) — code snippet to check. If omitted, returns framework health instead.\n- `operation` (required, string) — create, modify, refactor\n- `focus_areas` (array) — error-handling, type-safety, performance, security, architecture\n\nReturns: violations list with actionable remediation.\n\n### xray_health\n\nFramework health check. Returns version, loaded components, project root.\n\n```\nxray_health()\n```\n\nReturns: framework status, version, component availability, node version.\n\n### xray_hooks\n\nManage 0xRay git hooks (install, uninstall, list, status).\n\n```\nxray_hooks(action=\"install\")\nxray_hooks(action=\"status\")\nxray_hooks(action=\"list\")\nxray_hooks(action=\"uninstall\", hooks=[\"pre-commit\"])\n```\n\nParameters:\n- `action` (required, string) — install, uninstall, list, status\n- `hooks` (array) — which hooks to manage (default: all four)\n\nHooks available: pre-commit, post-commit, pre-push, post-push.\n\n| Hook | Type | What it does |\n|------|------|-------------|\n| `pre-commit` | Blocking | TypeScript check + Codex validation before commit |\n| `post-commit` | Non-blocking | Log archival + cleanup after commit |\n| `pre-push` | Blocking | Full validation suite before push |\n| `post-push` | Non-blocking | Comprehensive monitoring after push |\n\n## 2 Lifecycle Hooks\n\nThese fire automatically — no action needed from the user or agent.\n\n### pre_tool_call\n\nFires before ANY tool executes:\n1. Tracks session stats\n2. Logs tool-start event to `logs\u002Fframework\u002Fplugin-tool-events.log`\n3. For code-producing tools (write_file, patch, execute_code, write, edit): runs quality gate + pre-processors via bridge\n4. For other tools: nudges when a 0xRay MCP alternative exists (e.g., grep → search_codebase, eslint → xray_lint)\n\n### post_tool_call\n\nFires after ANY tool returns:\n1. Logs tool-complete event\n2. For code-producing tools: runs post-processors via bridge\n\n### on_session_start (graceful fallback)\n\nFires when a new session starts. Resets stats and logs to disk. Registration is wrapped in try\u002Fexcept for hosts that don't support it yet.\n\n## Slash Command\n\n```\n\u002Fxray status    — Plugin and framework health (calls bridge)\n\u002Fxray stats     — Session pipeline statistics\n\u002Fxray help      — Show available commands\n\u002Fsr status        — Alias\n```\n\n## Session Stats (tracked automatically)\n\nThe plugin tracks per-session counters visible via `\u002Fxray stats`:\n- total_tool_calls, code_operations, xray_mcp_calls, native_tool_calls\n- quality_gate_runs, quality_gate_blocks\n- pre_processor_runs, post_processor_runs\n- bridge_calls, bridge_errors\n\n## Logging\n\nAll logs go to `logs\u002Fframework\u002F` in the project root:\n\n| File | Content |\n|------|---------|\n| `activity.log` | All pipeline events (quality gates, processors, nudges, errors) |\n| `plugin-tool-events.log` | Tool start\u002Fcomplete events with durations |\n\n## Quick Decision Guide\n\n| User Says | Tool \u002F Command |\n|----------|---------------|\n| \"Is 0xRay working?\" | `xray_health()` or `\u002Fxray status` |\n| \"Check these files before I commit\" | `xray_validate(files=[...], operation=\"commit\")` |\n| \"Is this code codex compliant?\" | `xray_codex_check(code=..., operation=\"create\")` |\n| \"Set up git hooks\" | `xray_hooks(action=\"install\")` |\n| \"What hooks are installed?\" | `xray_hooks(action=\"status\")` |\n| \"Show session stats\" | `\u002Fxray stats` |\n| \"Why is the bridge failing?\" | Check `xray_health()` → if `framework: \"not_loaded\"`, verify `dist\u002F` symlink |\n\n## Bridge Commands (internal)\n\nThese are called by the Python tools via `bridge.mjs`, not directly by the LLM:\n\n| Command | What it does |\n|---------|-------------|\n| `health` | Framework health check |\n| `validate` | Run quality gate on files |\n| `codex-check` | Check code against codex rules |\n| `pre-process` | Quality gate + pre-processors before tool |\n| `post-process` | Post-processors after tool |\n| `hooks` | Git hook management |\n| `stats` | Bridge\u002Fframework statistics |\n\nBridge can be invoked directly for debugging:\n```bash\necho '{\"command\":\"health\"}' | node ~\u002F.hermes\u002Fplugins\u002Fxray-hermes\u002Fbridge.mjs\nnode ~\u002F.hermes\u002Fplugins\u002Fxray-hermes\u002Fbridge.mjs health --cwd \u002Fpath\u002Fto\u002Fproject\n```\n\n## Relationship to MCP Servers\n\nThe plugin and MCP servers are complementary:\n- **Plugin tools** = offline-first, always available, lightweight (validate, codex check, health, hooks)\n- **MCP servers** = deeper analysis requiring running Node.js (lint, security scan, architecture assessment, orchestration, codebase search)\n\nThe plugin's pre_tool_call hook nudges when an MCP alternative exists (e.g., \"use mcp_xray_lint_lint instead of raw eslint\"). This is advisory, not blocking.\n\n## Pitfalls\n\n- Plugin requires restart after install\u002Fedit: Hermes loads plugins once at session start.\n- Bridge needs `dist\u002F` symlink: The bridge loads compiled `.js` from `dist\u002F` → `node_modules\u002F0xray\u002Fdist\u002F`. If the symlink breaks, bridge returns `framework: \"not_loaded\"`.\n- `xray_codex_check` without `code` param returns health, not a codex check. Pass `code` for actual validation.\n- CLI fallback requires `npx 0xray` in PATH. If bridge fails and CLI isn't available, tools return errors.\n- Quality gate blocks are logged but NOT enforced (advisory). The tool returns violations; the agent decides what to do.\n- Git hooks use symlinks from `.git\u002Fhooks\u002F` → `hooks\u002F`. If the `hooks\u002F` directory doesn't exist in the project, `xray_hooks(action=\"install\")` skips those hooks.\n- Project root detection walks up from CWD looking for `node_modules\u002F0xray`, `.xray\u002Ffeatures.json`, or `package.json`. Override with `XRAY_PROJECT_ROOT` env var.\n- `logs\u002Fframework\u002F` is created automatically. Never breaks the agent if permissions fail.\n","# 0xRay Hermes Plugin (xray-hermes)\n\nNative Hermes plugin providing 0xRay framework integration — quality gates, codex enforcement, git hooks, and full pre\u002Fpost processing pipeline. Runs via a Node.js bridge to compiled framework components.\n\n## When to Use\n\n- User asks about 0xRay health, validation, or codex checks\n- User wants to install\u002Fmanage git hooks for automated enforcement\n- User asks about the plugin's tools, hooks, or slash commands\n- User asks about bridge errors or framework not loading\n- User wants to validate files before committing or pushing\n\n## Plugin Architecture\n\n```\n~\u002F.hermes\u002Fplugins\u002Fxray-hermes\u002F\n├── __init__.py         # Plugin registration, hooks, slash commands\n├── tools.py            # 4 tool handlers (validate, codex_check, health, hooks)\n├── schemas.py          # JSON schemas the LLM sees\n├── bridge.mjs          # Node.js bridge to compiled 0xRay framework\n├── plugin.yaml         # Plugin metadata (name, version, tools, hooks)\n├── types.py            # TypeScript-equivalent type definitions\n├── after-install.md    # Post-install instructions\n└── test_plugin.py      # Tests\n```\n\n**Bridge protocol:** JSON over stdin\u002Fstdout to `bridge.mjs` (Node.js). The bridge lazy-loads compiled framework modules from `dist\u002F`:\n- `dist\u002Fplugin\u002Fquality-gate.js` — codex violation detection\n- `dist\u002Fprocessors\u002Fprocessor-manager.js` — pre\u002Fpost processor pipeline\n- `dist\u002Fstate\u002Fstate-manager.js` — persistent state\n- `dist\u002Fcore\u002Ffeatures-config.js` — feature flags\n\n**Fallback:** When bridge is unavailable, tools fall back to `npx 0xray` CLI commands.\n\n**Config path resolution:** `XRAY_CONFIG_DIR\u002F` > `.xray\u002F` > built-in defaults.\n\n## 4 Tools\n\n### xray_validate\n\nRun pre-commit validation on files. Uses bridge quality gate + processor pipeline, falls back to CLI.\n\n```\nxray_validate(files=[\"src\u002Fmy-module.ts\"], operation=\"commit\")\nxray_validate(files=[\"src\u002Fauth.ts\", \"src\u002Fauth.test.ts\"], operation=\"modify\")\n```\n\nParameters:\n- `files` (required, array of strings) — file paths to validate\n- `operation` (string) — commit, create, modify, refactor (default: commit)\n\nReturns: pass\u002Ffail with per-file results and violations.\n\n### xray_codex_check\n\nValidate code against the 69-term Universal Development Codex. Checks error-handling, type-safety, performance, security, architecture.\n\n```\nxray_codex_check(code=\"const x: any = foo()\", operation=\"create\")\nxray_codex_check(code=snippet, operation=\"modify\", focus_areas=[\"security\", \"error-handling\"])\n```\n\nParameters:\n- `code` (string) — code snippet to check. If omitted, returns framework health instead.\n- `operation` (required, string) — create, modify, refactor\n- `focus_areas` (array) — error-handling, type-safety, performance, security, architecture\n\nReturns: violations list with actionable remediation.\n\n### xray_health\n\nFramework health check. Returns version, loaded components, project root.\n\n```\nxray_health()\n```\n\nReturns: framework status, version, component availability, node version.\n\n### xray_hooks\n\nManage 0xRay git hooks (install, uninstall, list, status).\n\n```\nxray_hooks(action=\"install\")\nxray_hooks(action=\"status\")\nxray_hooks(action=\"list\")\nxray_hooks(action=\"uninstall\", hooks=[\"pre-commit\"])\n```\n\nParameters:\n- `action` (required, string) — install, uninstall, list, status\n- `hooks` (array) — which hooks to manage (default: all four)\n\nHooks available: pre-commit, post-commit, pre-push, post-push.\n\n| Hook | Type | What it does |\n|------|------|-------------|\n| `pre-commit` | Blocking | TypeScript check + Codex validation before commit |\n| `post-commit` | Non-blocking | Log archival + cleanup after commit |\n| `pre-push` | Blocking | Full validation suite before push |\n| `post-push` | Non-blocking | Comprehensive monitoring after push |\n\n## 2 Lifecycle Hooks\n\nThese fire automatically — no action needed from the user or agent.\n\n### pre_tool_call\n\nFires before ANY tool executes:\n1. Tracks session stats\n2. Logs tool-start event to `logs\u002Fframework\u002Fplugin-tool-events.log`\n3. For code-producing tools (write_file, patch, execute_code, write, edit): runs quality gate + pre-processors via bridge\n4. For other tools: nudges when a 0xRay MCP alternative exists (e.g., grep → search_codebase, eslint → xray_lint)\n\n### post_tool_call\n\nFires after ANY tool returns:\n1. Logs tool-complete event\n2. For code-producing tools: runs post-processors via bridge\n\n### on_session_start (graceful fallback)\n\nFires when a new session starts. Resets stats and logs to disk. Registration is wrapped in try\u002Fexcept for hosts that don't support it yet.\n\n## Slash Command\n\n```\n\u002Fxray status    — Plugin and framework health (calls bridge)\n\u002Fxray stats     — Session pipeline statistics\n\u002Fxray help      — Show available commands\n\u002Fsr status        — Alias\n```\n\n## Session Stats (tracked automatically)\n\nThe plugin tracks per-session counters visible via `\u002Fxray stats`:\n- total_tool_calls, code_operations, xray_mcp_calls, native_tool_calls\n- quality_gate_runs, quality_gate_blocks\n- pre_processor_runs, post_processor_runs\n- bridge_calls, bridge_errors\n\n## Logging\n\nAll logs go to `logs\u002Fframework\u002F` in the project root:\n\n| File | Content |\n|------|---------|\n| `activity.log` | All pipeline events (quality gates, processors, nudges, errors) |\n| `plugin-tool-events.log` | Tool start\u002Fcomplete events with durations |\n\n## Quick Decision Guide\n\n| User Says | Tool \u002F Command |\n|----------|---------------|\n| \"Is 0xRay working?\" | `xray_health()` or `\u002Fxray status` |\n| \"Check these files before I commit\" | `xray_validate(files=[...], operation=\"commit\")` |\n| \"Is this code codex compliant?\" | `xray_codex_check(code=..., operation=\"create\")` |\n| \"Set up git hooks\" | `xray_hooks(action=\"install\")` |\n| \"What hooks are installed?\" | `xray_hooks(action=\"status\")` |\n| \"Show session stats\" | `\u002Fxray stats` |\n| \"Why is the bridge failing?\" | Check `xray_health()` → if `framework: \"not_loaded\"`, verify `dist\u002F` symlink |\n\n## Bridge Commands (internal)\n\nThese are called by the Python tools via `bridge.mjs`, not directly by the LLM:\n\n| Command | What it does |\n|---------|-------------|\n| `health` | Framework health check |\n| `validate` | Run quality gate on files |\n| `codex-check` | Check code against codex rules |\n| `pre-process` | Quality gate + pre-processors before tool |\n| `post-process` | Post-processors after tool |\n| `hooks` | Git hook management |\n| `stats` | Bridge\u002Fframework statistics |\n\nBridge can be invoked directly for debugging:\n```bash\necho '{\"command\":\"health\"}' | node ~\u002F.hermes\u002Fplugins\u002Fxray-hermes\u002Fbridge.mjs\nnode ~\u002F.hermes\u002Fplugins\u002Fxray-hermes\u002Fbridge.mjs health --cwd \u002Fpath\u002Fto\u002Fproject\n```\n\n## Relationship to MCP Servers\n\nThe plugin and MCP servers are complementary:\n- **Plugin tools** = offline-first, always available, lightweight (validate, codex check, health, hooks)\n- **MCP servers** = deeper analysis requiring running Node.js (lint, security scan, architecture assessment, orchestration, codebase search)\n\nThe plugin's pre_tool_call hook nudges when an MCP alternative exists (e.g., \"use mcp_xray_lint_lint instead of raw eslint\"). This is advisory, not blocking.\n\n## Pitfalls\n\n- Plugin requires restart after install\u002Fedit: Hermes loads plugins once at session start.\n- Bridge needs `dist\u002F` symlink: The bridge loads compiled `.js` from `dist\u002F` → `node_modules\u002F0xray\u002Fdist\u002F`. If the symlink breaks, bridge returns `framework: \"not_loaded\"`.\n- `xray_codex_check` without `code` param returns health, not a codex check. Pass `code` for actual validation.\n- CLI fallback requires `npx 0xray` in PATH. If bridge fails and CLI isn't available, tools return errors.\n- Quality gate blocks are logged but NOT enforced (advisory). The tool returns violations; the agent decides what to do.\n- Git hooks use symlinks from `.git\u002Fhooks\u002F` → `hooks\u002F`. If the `hooks\u002F` directory doesn't exist in the project, `xray_hooks(action=\"install\")` skips those hooks.\n- Project root detection walks up from CWD looking for `node_modules\u002F0xray`, `.xray\u002Ffeatures.json`, or `package.json`. Override with `XRAY_PROJECT_ROOT` env var.\n- `logs\u002Fframework\u002F` is created automatically. Never breaks the agent if permissions fail.\n",{"name":5,"author":23,"version":24,"metadata":25,"description":7},"0xRay AI","2.1.0",{"hermes":26},{"tags":27,"related_skills":34},[28,29,30,31,32,33],"0xRay","Plugin","Validation","Codex","GitHooks","Bridge",[],"main","232f39ec089591afb70f9327b481e7428162a97e","src\u002Fskills\u002Fhermes-agent",3,"https:\u002F\u002Fgithub.com\u002F0xRayAI\u002Fxray","https:\u002F\u002Fgithub.com\u002F0xRayAI","2026-11-13 22:20:55",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add 0xRayAI\u002Fxray --skill hermes-agent",{"tool":48,"command":49},"bunx","bunx skills add 0xRayAI\u002Fxray --skill hermes-agent",{"tool":51,"command":52},"pnpm","pnpm dlx skills add 0xRayAI\u002Fxray --skill hermes-agent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F0xRayAI\u002Fxray\u002Fblob\u002Fmain\u002Fsrc\u002Fskills\u002Fhermes-agent\u002FSKILL.md",true,[],[57,64,71,78,85,92],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":18},"01M75AXZY4TX8Z6WF2G4EKYMAA","xray-orchestrator","Main orchestration skill for xray agents.\nProvides commands to coordinate agent work and invoke xray APIs\nthrough the local HTTP API server.","https:\u002F\u002Fgithub.com\u002F0xRayAI\u002Fxray\u002Fblob\u002Fmain\u002Fsrc\u002Fskills\u002Fxray-orchestrator\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":18},"01M75AXT1TB9SX9JVSP16C85BP","ui-ux-design","User interface and user experience design with mobile-first approach, cognitive simplicity, and accessibility-first principles","https:\u002F\u002Fgithub.com\u002F0xRayAI\u002Fxray\u002Fblob\u002Fmain\u002Fsrc\u002Fskills\u002Fui-ux-design\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":18},"01M75AXQERT17BTCCY7Y1HPXTA","testing-strategy","Design comprehensive testing strategies and optimize test coverage","https:\u002F\u002Fgithub.com\u002F0xRayAI\u002Fxray\u002Fblob\u002Fmain\u002Fsrc\u002Fskills\u002Ftesting-strategy\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M75AXM7TRVQXXKT0C287VWN7","testing-best-practices","Testing best practices and quality assurance","https:\u002F\u002Fgithub.com\u002F0xRayAI\u002Fxray\u002Fblob\u002Fmain\u002Fsrc\u002Fskills\u002Ftesting-best-practices\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":18},"01M75AXHAJZK2JBVG638K3RZ5F","tech-writer","Documentation writer for API docs, READMEs, ADRs, changelogs, and developer experience","https:\u002F\u002Fgithub.com\u002F0xRayAI\u002Fxray\u002Fblob\u002Fmain\u002Fsrc\u002Fskills\u002Ftech-writer\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":18},"01M75AXE7P5MX15WA16TGFKJQG","strategist","Strategic guidance and complex problem-solving with architectural decision-making and risk analysis","https:\u002F\u002Fgithub.com\u002F0xRayAI\u002Fxray\u002Fblob\u002Fmain\u002Fsrc\u002Fskills\u002Fstrategist\u002FSKILL.md",[],[]]