[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M736XVPTKBCPZTYF8VEA1YBP":3,"skill-same:01M736XVPTKBCPZTYF8VEA1YBP":47},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"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":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M736XVPTKBCPZTYF8VEA1YBP","repl-code-execution",null,"Horonomos-laps\u002FYana-AI","Horonomos-laps","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F355299122?v=4","01M76B3QPXE88ET2SQPDPVATZT"," Horonomos-laps","01M72ZQRJPCYPSSWT4D00VJR2A",13,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frepl-code-execution\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: repl-code-execution\ndescription: REPL-driven dynamic code execution patterns for compiled languages. Incremental eval, state persistence between evaluations, error recovery, and sandboxed expression execution. Sources: evcxr\u002Fevcxr (Apache-2.0).\norigin: yana-ai — synthesized from evcxr\u002Fevcxr (Apache-2.0)\nlicense: Apache-2.0\nversion: 1.0.0\ncompatibility: yana-ai >= 1.3.49\n---\n\n# \u002Frepl-code-execution\n\n## When to Use\n\n- Build interactive REPL sessions for testing snippets without full compilation cycle\n- Incremental evaluation: execute lines and preserve variable state across calls\n- Agent-driven code probing: try expressions, inspect results, backtrack on error\n- Jupyter-style cell execution for compiled-language notebooks\n\n## Do NOT use for\n\n- Production code execution (use subprocess with strict sandboxing [[runtime-sandbox-runc]])\n- JavaScript eval (use vm.Script with [[runtime-metrics-meters]] for memory limits)\n\n---\n\n## Node.js REPL with persistent context\n\n```javascript\nimport repl from 'repl'\nimport vm   from 'vm'\n\n\u002F\u002F Start a REPL server with shared context\nconst replServer = repl.start({\n  prompt:  '> ',\n  useColors: true,\n  terminal: false,           \u002F\u002F disable TTY features for programmatic use\n  eval: customEval,\n})\n\n\u002F\u002F Inject shared state into REPL context\nreplServer.context.db     = dbConnection\nreplServer.context.agents = agentRegistry\n\nfunction customEval(cmd, context, filename, callback) {\n  try {\n    const result = vm.runInContext(cmd, context, {\n      filename,\n      timeout: 3000,           \u002F\u002F 3s hard limit per expression\n      breakOnSigint: true,\n    })\n    callback(null, result)\n  } catch (err) {\n    \u002F\u002F Recover from incomplete input (multi-line expressions)\n    if (isIncomplete(err)) {\n      callback(new repl.Recoverable(err))\n    } else {\n      callback(null, `[error] ${err.message}`)\n    }\n  }\n}\n\nfunction isIncomplete(err: Error): boolean {\n  return err.message.includes('Unexpected end of input') ||\n         err.message.includes('Unexpected token')\n}\n```\n\n---\n\n## Sandboxed expression evaluation (one-shot)\n\n```javascript\nimport vm from 'vm'\n\nfunction evalExpression(code: string, context: Record\u003Cstring, unknown> = {}): unknown {\n  const sandbox = vm.createContext({\n    console: { log: (...a) => results.push(a) },\n    ...context,\n  })\n  const results: unknown[][] = []\n\n  const script = new vm.Script(code, { filename: 'repl-eval' })\n  const value  = script.runInContext(sandbox, { timeout: 2000 })\n\n  return { value, logs: results }\n}\n\n\u002F\u002F Usage:\nconst { value, logs } = evalExpression('1 + 2 * Math.PI', { Math })\n\u002F\u002F value = 7.283...\n```\n\n---\n\n## Incremental state REPL (evcxr-style session)\n\n```typescript\n\u002F\u002F Stateful session: each submission builds on previous bindings\nclass ReplSession {\n  private ctx = vm.createContext({ require, console, process })\n  private history: string[] = []\n\n  eval(code: string): { result: unknown; error?: string } {\n    this.history.push(code)\n    try {\n      const script = new vm.Script(code)\n      const result = script.runInContext(this.ctx, { timeout: 5000 })\n      return { result }\n    } catch (err: any) {\n      return { result: undefined, error: err.message }\n    }\n  }\n\n  reset() {\n    this.ctx = vm.createContext({ require, console, process })\n    this.history = []\n  }\n}\n\nconst session = new ReplSession()\nsession.eval('const x = 42')\nsession.eval('const y = x * 2')      \u002F\u002F x is available from previous eval\nconst { result } = session.eval('y') \u002F\u002F → 84\n```\n\n---\n\n## Anti-Fake-Pass Checklist\n\n```\n❌ vm.runInContext without timeout → infinite loop hangs the process\n❌ vm.createContext with full global → sandbox escape via process.exit or require\n❌ No error recovery → multi-line input discarded on partial parse\n❌ Shared context between untrusted sessions → state pollution across users\n❌ eval() instead of vm.Script → no timeout, no sandbox boundary\n❌ REPL context mutation without clone → downstream sessions see dirty state\n```\n","# \u002Frepl-code-execution\n\n## When to Use\n\n- Build interactive REPL sessions for testing snippets without full compilation cycle\n- Incremental evaluation: execute lines and preserve variable state across calls\n- Agent-driven code probing: try expressions, inspect results, backtrack on error\n- Jupyter-style cell execution for compiled-language notebooks\n\n## Do NOT use for\n\n- Production code execution (use subprocess with strict sandboxing [[runtime-sandbox-runc]])\n- JavaScript eval (use vm.Script with [[runtime-metrics-meters]] for memory limits)\n\n---\n\n## Node.js REPL with persistent context\n\n```javascript\nimport repl from 'repl'\nimport vm   from 'vm'\n\n\u002F\u002F Start a REPL server with shared context\nconst replServer = repl.start({\n  prompt:  '> ',\n  useColors: true,\n  terminal: false,           \u002F\u002F disable TTY features for programmatic use\n  eval: customEval,\n})\n\n\u002F\u002F Inject shared state into REPL context\nreplServer.context.db     = dbConnection\nreplServer.context.agents = agentRegistry\n\nfunction customEval(cmd, context, filename, callback) {\n  try {\n    const result = vm.runInContext(cmd, context, {\n      filename,\n      timeout: 3000,           \u002F\u002F 3s hard limit per expression\n      breakOnSigint: true,\n    })\n    callback(null, result)\n  } catch (err) {\n    \u002F\u002F Recover from incomplete input (multi-line expressions)\n    if (isIncomplete(err)) {\n      callback(new repl.Recoverable(err))\n    } else {\n      callback(null, `[error] ${err.message}`)\n    }\n  }\n}\n\nfunction isIncomplete(err: Error): boolean {\n  return err.message.includes('Unexpected end of input') ||\n         err.message.includes('Unexpected token')\n}\n```\n\n---\n\n## Sandboxed expression evaluation (one-shot)\n\n```javascript\nimport vm from 'vm'\n\nfunction evalExpression(code: string, context: Record\u003Cstring, unknown> = {}): unknown {\n  const sandbox = vm.createContext({\n    console: { log: (...a) => results.push(a) },\n    ...context,\n  })\n  const results: unknown[][] = []\n\n  const script = new vm.Script(code, { filename: 'repl-eval' })\n  const value  = script.runInContext(sandbox, { timeout: 2000 })\n\n  return { value, logs: results }\n}\n\n\u002F\u002F Usage:\nconst { value, logs } = evalExpression('1 + 2 * Math.PI', { Math })\n\u002F\u002F value = 7.283...\n```\n\n---\n\n## Incremental state REPL (evcxr-style session)\n\n```typescript\n\u002F\u002F Stateful session: each submission builds on previous bindings\nclass ReplSession {\n  private ctx = vm.createContext({ require, console, process })\n  private history: string[] = []\n\n  eval(code: string): { result: unknown; error?: string } {\n    this.history.push(code)\n    try {\n      const script = new vm.Script(code)\n      const result = script.runInContext(this.ctx, { timeout: 5000 })\n      return { result }\n    } catch (err: any) {\n      return { result: undefined, error: err.message }\n    }\n  }\n\n  reset() {\n    this.ctx = vm.createContext({ require, console, process })\n    this.history = []\n  }\n}\n\nconst session = new ReplSession()\nsession.eval('const x = 42')\nsession.eval('const y = x * 2')      \u002F\u002F x is available from previous eval\nconst { result } = session.eval('y') \u002F\u002F → 84\n```\n\n---\n\n## Anti-Fake-Pass Checklist\n\n```\n❌ vm.runInContext without timeout → infinite loop hangs the process\n❌ vm.createContext with full global → sandbox escape via process.exit or require\n❌ No error recovery → multi-line input discarded on partial parse\n❌ Shared context between untrusted sessions → state pollution across users\n❌ eval() instead of vm.Script → no timeout, no sandbox boundary\n❌ REPL context mutation without clone → downstream sessions see dirty state\n```\n",{},"main","481dcd7dd2e288b9d627a2bd017db70e64e6c6fa",".claude\u002Fskills\u002Frepl-code-execution",2,"https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI","https:\u002F\u002Fyana.vutam.link\u002F","https:\u002F\u002Fgithub.com\u002FHoronomos-laps","https:\u002F\u002Fyana.vutam.link","An open-source governed runtime & execution environment for multi-agent AI systems.","2026-11-14 13:24:09",{"source":7,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Horonomos-laps\u002FYana-AI --skill repl-code-execution",{"tool":39,"command":40},"bunx","bunx skills add Horonomos-laps\u002FYana-AI --skill repl-code-execution",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Horonomos-laps\u002FYana-AI --skill repl-code-execution","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frepl-code-execution\u002FSKILL.md",true,[],[48,56,63,71,79,87],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":52,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":18},"01M735GKET5YVYKAY62W2P5YXB","openai--sentry--sentry","Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.","MIT","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fopenai--sentry--sentry\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":18},"01M73DCAP83T17HY7SMGK7MGFE","ito-basket-compare","Compare Itô prediction-market baskets against a user's knowledge base, portfolio notes, financial context, watchlist, or research thesis. Use for read-only basket comparison and gap analysis without investment advice or live trading.","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fito-basket-compare\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":67,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":18},"01M734CYEMZFDR3KH6SW0JP8TD","implementing-network-traffic-baselining","Build network traffic baselines from NetFlow\u002FIPFIX data using Python pandas for statistical analysis, z-score anomaly detection, and hourly\u002Fdaily traffic pattern profiling","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":75,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M73ASZ6NJRJM44Z2P84NGQ3Q","detecting-evasion-techniques-in-endpoint-logs","Detects defense evasion techniques used by adversaries in endpoint logs including log tampering, timestomping, process injection, and security tool disabling. Use when investigating suspicious endpoint behavior, building detection rules for evasion tactics, or conducting threat hunting for stealthy adversary activity. Activates for requests involving evasion detection, defense evasion analysis, log tampering detection, or MITRE ATT&CK TA0005.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":83,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M734AFNXD06Z78QRK0VKGT7Q","implementing-microsegmentation-with-guardicore","Implementing microsegmentation using Akamai Guardicore Segmentation to map application dependencies, create granular network policies, visualize east-west traffic flows, and enforce least-privilege communication between workloads across data centers and cloud.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M736TK27QMCXK0DVCH25SJN5","ramdisk-tmpfs-patterns","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Framdisk-tmpfs-patterns\u002FSKILL.md",[],[]]