[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73F8AK8WDPT8ADRWB8BPFGE":3,"skill-same:01M73F8AK8WDPT8ADRWB8BPFGE":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},"01M73F8AK8WDPT8ADRWB8BPFGE","prometheus-ai-telemetry",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\u002Fcore\u002Fskills\u002Fprometheus-ai-telemetry\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: prometheus-ai-telemetry\ndescription: Prometheus metrics for LLM\u002FAI inference telemetry. Token throughput counters, KV-cache hit\u002Fmiss rates, latency histograms, model queue depth gauges, and Grafana dashboard patterns. Sources: prometheus\u002Fclient_golang (Apache-2.0).\norigin: yana-ai — synthesized from prometheus\u002Fclient_golang (Apache-2.0), prom-client (Apache-2.0)\nlicense: Apache-2.0\nversion: 1.0.0\ncompatibility: yana-ai >= 1.3.51\n---\n\n# \u002Fprometheus-ai-telemetry\n\n## When to Use\n\n- Expose tokens\u002Fs, TTFT, queue depth from LLM inference engines to Grafana\n- Alert when cache hit rate drops below 60% (indicates prompt change degrading prefix caching)\n- Track per-model cost: tokens consumed × price\u002Ftoken over time\n- Detect inference regressions: p99 latency spike after model update\n\n## Do NOT use for\n\n- Application-level metrics unrelated to AI (use [[statsd-metrics-streaming]])\n- One-shot benchmarks (use [[mlperf-inference-benchmarks]])\n\n---\n\n## Core AI metrics to instrument\n\n```\nCounters (monotonically increasing):\n  llm_tokens_total{model, type=\"input|output\"}    — total tokens processed\n  llm_requests_total{model, status=\"ok|error\"}     — request count\n  llm_cost_usd_total{model}                        — estimated cost\n\nHistograms (latency distribution):\n  llm_ttft_seconds{model}          — Time to First Token\n  llm_e2e_latency_seconds{model}   — end-to-end request latency\n  llm_tokens_per_second{model}     — generation throughput\n\nGauges (current value):\n  llm_active_requests{model}       — in-flight requests\n  llm_queue_depth{model}           — waiting requests\n  llm_kv_cache_hit_rate{model}     — prefix cache efficiency (0–1)\n  llm_gpu_memory_used_bytes{gpu}   — VRAM utilization\n```\n\n---\n\n## Node.js instrumentation (prom-client)\n\n```javascript\nimport { Registry, Counter, Histogram, Gauge } from 'prom-client'\n\nconst registry = new Registry()\n\nconst tokenCounter = new Counter({\n  name:    'llm_tokens_total',\n  help:    'Total tokens processed',\n  labelNames: ['model', 'type'],\n  registers: [registry],\n})\n\nconst ttftHistogram = new Histogram({\n  name:    'llm_ttft_seconds',\n  help:    'Time to first token latency in seconds',\n  labelNames: ['model'],\n  buckets: [0.05, 0.1, 0.25, 0.5, 1.0, 2.0, 5.0],\n  registers: [registry],\n})\n\nconst activeRequests = new Gauge({\n  name:    'llm_active_requests',\n  help:    'Currently in-flight LLM requests',\n  labelNames: ['model'],\n  registers: [registry],\n})\n\n\u002F\u002F Instrument an inference call\nasync function instrumentedInfer(model: string, prompt: string): Promise\u003Cstring> {\n  const start = Date.now()\n  activeRequests.inc({ model })\n\n  try {\n    let firstToken = false\n    let result     = ''\n\n    for await (const token of streamInfer(model, prompt)) {\n      if (!firstToken) {\n        ttftHistogram.observe({ model }, (Date.now() - start) \u002F 1000)\n        firstToken = true\n      }\n      result += token\n      tokenCounter.inc({ model, type: 'output' })\n    }\n\n    tokenCounter.inc({ model, type: 'input' }, estimateTokens(prompt))\n    return result\n  } finally {\n    activeRequests.dec({ model })\n  }\n}\n\n\u002F\u002F Expose \u002Fmetrics endpoint\nimport express from 'express'\nconst app = express()\napp.get('\u002Fmetrics', async (req, res) => {\n  res.set('Content-Type', registry.contentType)\n  res.send(await registry.metrics())\n})\n```\n\n---\n\n## Grafana alert rules\n\n```yaml\n# alerts.yaml — alert on AI infra degradation\ngroups:\n  - name: yamtam-ai\n    rules:\n      - alert: HighTTFT\n        expr: histogram_quantile(0.99, rate(llm_ttft_seconds_bucket[5m])) > 2.0\n        for: 2m\n        labels:     { severity: warning }\n        annotations:\n          summary: \"p99 TTFT > 2s for {{ $labels.model }}\"\n\n      - alert: LowCacheHitRate\n        expr: llm_kv_cache_hit_rate \u003C 0.5\n        for: 5m\n        labels:     { severity: warning }\n        annotations:\n          summary: \"KV cache hit rate \u003C 50% — prefix caching degraded\"\n\n      - alert: HighQueueDepth\n        expr: llm_queue_depth > 50\n        for: 1m\n        labels:     { severity: critical }\n        annotations:\n          summary: \"Inference queue backlog > 50 — scale up or throttle\"\n```\n\n---\n\n## Anti-Fake-Pass Checklist\n\n```\n❌ Not labeling by model → all models merged in one metric, can't diagnose regressions\n❌ Histogram buckets too coarse (e.g., [1, 5, 10]) → can't distinguish 50ms from 999ms\n❌ Counter reset on process restart → rate() will show negative spike; use increase() for totals\n❌ Gauge for tokens (should be Counter) → gauge can decrease; tokens only increase\n❌ \u002Fmetrics endpoint not secured → exposes system internals; add IP allowlist or basic auth\n❌ Not recording input tokens separately → cost estimation impossible without input count\n```\n","# \u002Fprometheus-ai-telemetry\n\n## When to Use\n\n- Expose tokens\u002Fs, TTFT, queue depth from LLM inference engines to Grafana\n- Alert when cache hit rate drops below 60% (indicates prompt change degrading prefix caching)\n- Track per-model cost: tokens consumed × price\u002Ftoken over time\n- Detect inference regressions: p99 latency spike after model update\n\n## Do NOT use for\n\n- Application-level metrics unrelated to AI (use [[statsd-metrics-streaming]])\n- One-shot benchmarks (use [[mlperf-inference-benchmarks]])\n\n---\n\n## Core AI metrics to instrument\n\n```\nCounters (monotonically increasing):\n  llm_tokens_total{model, type=\"input|output\"}    — total tokens processed\n  llm_requests_total{model, status=\"ok|error\"}     — request count\n  llm_cost_usd_total{model}                        — estimated cost\n\nHistograms (latency distribution):\n  llm_ttft_seconds{model}          — Time to First Token\n  llm_e2e_latency_seconds{model}   — end-to-end request latency\n  llm_tokens_per_second{model}     — generation throughput\n\nGauges (current value):\n  llm_active_requests{model}       — in-flight requests\n  llm_queue_depth{model}           — waiting requests\n  llm_kv_cache_hit_rate{model}     — prefix cache efficiency (0–1)\n  llm_gpu_memory_used_bytes{gpu}   — VRAM utilization\n```\n\n---\n\n## Node.js instrumentation (prom-client)\n\n```javascript\nimport { Registry, Counter, Histogram, Gauge } from 'prom-client'\n\nconst registry = new Registry()\n\nconst tokenCounter = new Counter({\n  name:    'llm_tokens_total',\n  help:    'Total tokens processed',\n  labelNames: ['model', 'type'],\n  registers: [registry],\n})\n\nconst ttftHistogram = new Histogram({\n  name:    'llm_ttft_seconds',\n  help:    'Time to first token latency in seconds',\n  labelNames: ['model'],\n  buckets: [0.05, 0.1, 0.25, 0.5, 1.0, 2.0, 5.0],\n  registers: [registry],\n})\n\nconst activeRequests = new Gauge({\n  name:    'llm_active_requests',\n  help:    'Currently in-flight LLM requests',\n  labelNames: ['model'],\n  registers: [registry],\n})\n\n\u002F\u002F Instrument an inference call\nasync function instrumentedInfer(model: string, prompt: string): Promise\u003Cstring> {\n  const start = Date.now()\n  activeRequests.inc({ model })\n\n  try {\n    let firstToken = false\n    let result     = ''\n\n    for await (const token of streamInfer(model, prompt)) {\n      if (!firstToken) {\n        ttftHistogram.observe({ model }, (Date.now() - start) \u002F 1000)\n        firstToken = true\n      }\n      result += token\n      tokenCounter.inc({ model, type: 'output' })\n    }\n\n    tokenCounter.inc({ model, type: 'input' }, estimateTokens(prompt))\n    return result\n  } finally {\n    activeRequests.dec({ model })\n  }\n}\n\n\u002F\u002F Expose \u002Fmetrics endpoint\nimport express from 'express'\nconst app = express()\napp.get('\u002Fmetrics', async (req, res) => {\n  res.set('Content-Type', registry.contentType)\n  res.send(await registry.metrics())\n})\n```\n\n---\n\n## Grafana alert rules\n\n```yaml\n# alerts.yaml — alert on AI infra degradation\ngroups:\n  - name: yamtam-ai\n    rules:\n      - alert: HighTTFT\n        expr: histogram_quantile(0.99, rate(llm_ttft_seconds_bucket[5m])) > 2.0\n        for: 2m\n        labels:     { severity: warning }\n        annotations:\n          summary: \"p99 TTFT > 2s for {{ $labels.model }}\"\n\n      - alert: LowCacheHitRate\n        expr: llm_kv_cache_hit_rate \u003C 0.5\n        for: 5m\n        labels:     { severity: warning }\n        annotations:\n          summary: \"KV cache hit rate \u003C 50% — prefix caching degraded\"\n\n      - alert: HighQueueDepth\n        expr: llm_queue_depth > 50\n        for: 1m\n        labels:     { severity: critical }\n        annotations:\n          summary: \"Inference queue backlog > 50 — scale up or throttle\"\n```\n\n---\n\n## Anti-Fake-Pass Checklist\n\n```\n❌ Not labeling by model → all models merged in one metric, can't diagnose regressions\n❌ Histogram buckets too coarse (e.g., [1, 5, 10]) → can't distinguish 50ms from 999ms\n❌ Counter reset on process restart → rate() will show negative spike; use increase() for totals\n❌ Gauge for tokens (should be Counter) → gauge can decrease; tokens only increase\n❌ \u002Fmetrics endpoint not secured → exposes system internals; add IP allowlist or basic auth\n❌ Not recording input tokens separately → cost estimation impossible without input count\n```\n",{},"main","481dcd7dd2e288b9d627a2bd017db70e64e6c6fa","core\u002Fskills\u002Fprometheus-ai-telemetry",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.","2026-11-13 13:15:29",{"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 prometheus-ai-telemetry",{"tool":39,"command":40},"bunx","bunx skills add Horonomos-laps\u002FYana-AI --skill prometheus-ai-telemetry",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Horonomos-laps\u002FYana-AI --skill prometheus-ai-telemetry","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fprometheus-ai-telemetry\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",[],[]]