[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73C20A88NGSN2QBAS56XMCP":3,"skill-same:01M73C20A88NGSN2QBAS56XMCP":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},"01M73C20A88NGSN2QBAS56XMCP","hermes-system-prompt-tiers",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\u002Fhermes-system-prompt-tiers\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: hermes-system-prompt-tiers\ndescription: Build system prompts in three tiers — stable (identity+tools, prefix-cache-friendly), context (session CWD files), volatile (memory+date-only) — to maximize upstream prompt cache reuse across turns. Source: NousResearch\u002Fhermes-agent (MIT).\norigin: NousResearch\u002Fhermes-agent (MIT) — agent\u002Fsystem_prompt.py\nlicense: MIT\nversion: 1.0.0\ncompatibility: yana-ai >= 1.3.54\n---\n\n## Implementation (architecture ported, content not — added 2026-06-19)\n\nMost of the original file's *content* (SOUL.md identity, kanban worker\nguidance, nous subscription prompts) is hermes-product-specific with no\nYana AI equivalent. What's ported is the architecture: the 3-tier\nstable\u002Fcontext\u002Fvolatile builder with cache-until-invalidated semantics,\nthe platform-hint override resolver (ported close to verbatim — it was\nalready pure), and the model-family-guidance matching pattern.\n\n- Module: `core\u002Flib\u002Fhermes_adapted\u002Fsystem_prompt.py`\n- Tests:  `tests\u002Ftest_hermes_system_prompt.py` (8 passing)\n\nYana AI supplies its own tier-section callables and guidance text; this\nmodule only provides the assembly\u002Fcaching\u002Foverride mechanics.\n\n# \u002Fhermes-system-prompt-tiers\n\n## When to Use\n\n- Building a multi-turn agent where system prompt is rebuilt each turn (kills cache)\n- Optimizing Claude API cost by maximizing prefix cache hits\n- System prompt contains both stable identity and volatile per-turn state\n- Yana AI or any long-running session with 20+ turns\n\n## Do NOT use for\n\n- Single-turn completions (no cache warmth benefit)\n- System prompts under ~200 tokens (cache overhead not worth it)\n- See also: [[hermes-context-compressor]] — compression rebuilds only stable tier\n\n---\n\n## The Problem\n\nRebuilding the system prompt with a different timestamp or memory snapshot every turn\ninvalidates the upstream prefix cache → every turn pays full input token cost.\n\n---\n\n## Three-Tier Architecture\n\n```\n┌─────────────────────────────────────────────────────────┐\n│  STABLE TIER  — rebuilt only after compression         │\n│  • Agent identity (SOUL.md or default persona)         │\n│  • Tool descriptions (static JSON)                     │\n│  • Model-specific instructions (Gemini quirks, etc.)   │\n│  • Skills prompt                                       │\n│  • Environment hints (OS, shell, CWD type)             │\n│  → Prefix cache reuse: ALL turns in session            │\n├─────────────────────────────────────────────────────────┤\n│  CONTEXT TIER  — session-stable, CWD-dependent         │\n│  • Caller-supplied system_message                      │\n│  • Context files found in CWD: AGENTS.md, CLAUDE.md,  │\n│    .cursorrules, etc.                                  │\n│  → Prefix cache reuse: until user changes CWD         │\n├─────────────────────────────────────────────────────────┤\n│  VOLATILE TIER  — per-session, never cached            │\n│  • Memory snapshot (from MemoryManager)                │\n│  • USER.md profile                                     │\n│  • Date only: \"2026-06-08\" — NOT \"13:58\" (key!)       │\n│  • Session ID, model name, provider name               │\n│  → No cache: changes per session                       │\n└─────────────────────────────────────────────────────────┘\n```\n\n**Key insight:** Date uses day precision, not minute. A timestamp like `13:58`\ninvalidates the stable prefix every minute. `2026-06-08` is byte-stable all day.\n\n---\n\n## Implementation\n\n```python\nfrom dataclasses import dataclass\nfrom datetime import date\nfrom pathlib import Path\n\nCONTEXT_FILE_NAMES = [\"AGENTS.md\", \"CLAUDE.md\", \".cursorrules\", \"SYSTEM.md\"]\n\n@dataclass\nclass SystemPromptParts:\n    stable:   str\n    context:  str\n    volatile: str\n\n    def assemble(self) -> str:\n        parts = [p for p in (self.stable, self.context, self.volatile) if p]\n        return \"\\n\\n\".join(parts)\n\n\nclass SystemPromptBuilder:\n    def __init__(self, agent_identity: str, tool_descriptions: str):\n        self._identity  = agent_identity\n        self._tools     = tool_descriptions\n        self._cached:   str | None = None          # full assembled prompt\n        self._stable:   str | None = None\n\n    # ── Stable tier ──────────────────────────────────────────────────────────\n    def _build_stable(self, skills_prompt: str = \"\", env_hint: str = \"\") -> str:\n        parts = [self._identity, self._tools]\n        if skills_prompt: parts.append(skills_prompt)\n        if env_hint:      parts.append(env_hint)\n        return \"\\n\\n\".join(p for p in parts if p)\n\n    # ── Context tier ─────────────────────────────────────────────────────────\n    def _build_context(self, cwd: Path, caller_system: str = \"\") -> str:\n        parts = []\n        if caller_system:\n            parts.append(caller_system)\n        for fname in CONTEXT_FILE_NAMES:\n            fpath = cwd \u002F fname\n            if fpath.exists():\n                try:\n                    content = fpath.read_text(encoding=\"utf-8\").strip()\n                    if content:\n                        parts.append(f\"# {fname}\\n{content}\")\n                except OSError:\n                    pass\n        return \"\\n\\n\".join(parts)\n\n    # ── Volatile tier ────────────────────────────────────────────────────────\n    def _build_volatile(self, memory_block: str = \"\",\n                        session_id: str = \"\", model: str = \"\") -> str:\n        # DATE ONLY — not hour\u002Fminute (prefix cache stability)\n        today = date.today().isoformat()   # \"2026-06-08\"\n        parts = [f\"Date: {today}\"]\n        if session_id: parts.append(f\"Session: {session_id}\")\n        if model:      parts.append(f\"Model: {model}\")\n        if memory_block:\n            parts.append(memory_block)     # already wrapped in \u003Cmemory-context>\n        return \"\\n\".join(parts)\n\n    # ── Public API ───────────────────────────────────────────────────────────\n    def build(self, *, cwd: Path, skills_prompt: str = \"\",\n              caller_system: str = \"\", env_hint: str = \"\",\n              memory_block: str = \"\", session_id: str = \"\",\n              model: str = \"\") -> str:\n        if self._cached:\n            return self._cached\n\n        parts = SystemPromptParts(\n            stable   = self._build_stable(skills_prompt, env_hint),\n            context  = self._build_context(cwd, caller_system),\n            volatile = self._build_volatile(memory_block, session_id, model),\n        )\n        self._cached = parts.assemble()\n        return self._cached\n\n    def invalidate(self) -> None:\n        \"\"\"Call after compression — forces stable tier rebuild next turn.\"\"\"\n        self._cached = None\n        self._stable = None\n```\n\n---\n\n## Wiring in Yana AI (TypeScript sketch)\n\n```typescript\nconst builder = new SystemPromptBuilder(SOUL_MD, formatToolsAsJSON(tools))\n\n\u002F\u002F Build once per session — cache naturally\nconst systemPrompt = builder.build({\n  cwd:          process.cwd(),\n  skillsPrompt: loadSkillsPrompt(),\n  memoryBlock:  await memoryManager.buildSystemPrompt(),\n  sessionId:    sessionId,\n  model:        \"claude-sonnet-4-6\",\n})\n\n\u002F\u002F Every turn: reuse cached prompt\nconst response = await anthropic.messages.create({\n  system:   systemPrompt,   \u002F\u002F same string each turn → prefix cache hit\n  messages: conversationHistory,\n  model:    \"claude-sonnet-4-6\",\n})\n\n\u002F\u002F After compression fires → invalidate + rebuild\nbuilder.invalidate()\n```\n\n---\n\n## Cache hit verification (Anthropic API)\n\n```typescript\n\u002F\u002F Check usage.cache_read_input_tokens in response\nif (response.usage.cache_read_input_tokens > 0) {\n  console.log(`Cache hit: ${response.usage.cache_read_input_tokens} tokens saved`)\n}\n```\n\n---\n\n## Anti-Fake-Pass Checklist\n\n```\n❌ Timestamp includes hours\u002Fminutes — invalidates prefix cache every minute\n❌ Stable tier rebuilt on every turn \"for freshness\" — no cache benefit at all\n❌ Memory block injected into stable tier — volatile content poisons cache\n❌ Context files re-read from disk every turn — I\u002FO waste + cache miss\n❌ invalidate() never called after compression — stale stable prompt persists\n❌ Tool descriptions differ per-turn (model-specific flags toggled) — cache miss\n```\n","## Implementation (architecture ported, content not — added 2026-06-19)\n\nMost of the original file's *content* (SOUL.md identity, kanban worker\nguidance, nous subscription prompts) is hermes-product-specific with no\nYana AI equivalent. What's ported is the architecture: the 3-tier\nstable\u002Fcontext\u002Fvolatile builder with cache-until-invalidated semantics,\nthe platform-hint override resolver (ported close to verbatim — it was\nalready pure), and the model-family-guidance matching pattern.\n\n- Module: `core\u002Flib\u002Fhermes_adapted\u002Fsystem_prompt.py`\n- Tests:  `tests\u002Ftest_hermes_system_prompt.py` (8 passing)\n\nYana AI supplies its own tier-section callables and guidance text; this\nmodule only provides the assembly\u002Fcaching\u002Foverride mechanics.\n\n# \u002Fhermes-system-prompt-tiers\n\n## When to Use\n\n- Building a multi-turn agent where system prompt is rebuilt each turn (kills cache)\n- Optimizing Claude API cost by maximizing prefix cache hits\n- System prompt contains both stable identity and volatile per-turn state\n- Yana AI or any long-running session with 20+ turns\n\n## Do NOT use for\n\n- Single-turn completions (no cache warmth benefit)\n- System prompts under ~200 tokens (cache overhead not worth it)\n- See also: [[hermes-context-compressor]] — compression rebuilds only stable tier\n\n---\n\n## The Problem\n\nRebuilding the system prompt with a different timestamp or memory snapshot every turn\ninvalidates the upstream prefix cache → every turn pays full input token cost.\n\n---\n\n## Three-Tier Architecture\n\n```\n┌─────────────────────────────────────────────────────────┐\n│  STABLE TIER  — rebuilt only after compression         │\n│  • Agent identity (SOUL.md or default persona)         │\n│  • Tool descriptions (static JSON)                     │\n│  • Model-specific instructions (Gemini quirks, etc.)   │\n│  • Skills prompt                                       │\n│  • Environment hints (OS, shell, CWD type)             │\n│  → Prefix cache reuse: ALL turns in session            │\n├─────────────────────────────────────────────────────────┤\n│  CONTEXT TIER  — session-stable, CWD-dependent         │\n│  • Caller-supplied system_message                      │\n│  • Context files found in CWD: AGENTS.md, CLAUDE.md,  │\n│    .cursorrules, etc.                                  │\n│  → Prefix cache reuse: until user changes CWD         │\n├─────────────────────────────────────────────────────────┤\n│  VOLATILE TIER  — per-session, never cached            │\n│  • Memory snapshot (from MemoryManager)                │\n│  • USER.md profile                                     │\n│  • Date only: \"2026-06-08\" — NOT \"13:58\" (key!)       │\n│  • Session ID, model name, provider name               │\n│  → No cache: changes per session                       │\n└─────────────────────────────────────────────────────────┘\n```\n\n**Key insight:** Date uses day precision, not minute. A timestamp like `13:58`\ninvalidates the stable prefix every minute. `2026-06-08` is byte-stable all day.\n\n---\n\n## Implementation\n\n```python\nfrom dataclasses import dataclass\nfrom datetime import date\nfrom pathlib import Path\n\nCONTEXT_FILE_NAMES = [\"AGENTS.md\", \"CLAUDE.md\", \".cursorrules\", \"SYSTEM.md\"]\n\n@dataclass\nclass SystemPromptParts:\n    stable:   str\n    context:  str\n    volatile: str\n\n    def assemble(self) -> str:\n        parts = [p for p in (self.stable, self.context, self.volatile) if p]\n        return \"\\n\\n\".join(parts)\n\n\nclass SystemPromptBuilder:\n    def __init__(self, agent_identity: str, tool_descriptions: str):\n        self._identity  = agent_identity\n        self._tools     = tool_descriptions\n        self._cached:   str | None = None          # full assembled prompt\n        self._stable:   str | None = None\n\n    # ── Stable tier ──────────────────────────────────────────────────────────\n    def _build_stable(self, skills_prompt: str = \"\", env_hint: str = \"\") -> str:\n        parts = [self._identity, self._tools]\n        if skills_prompt: parts.append(skills_prompt)\n        if env_hint:      parts.append(env_hint)\n        return \"\\n\\n\".join(p for p in parts if p)\n\n    # ── Context tier ─────────────────────────────────────────────────────────\n    def _build_context(self, cwd: Path, caller_system: str = \"\") -> str:\n        parts = []\n        if caller_system:\n            parts.append(caller_system)\n        for fname in CONTEXT_FILE_NAMES:\n            fpath = cwd \u002F fname\n            if fpath.exists():\n                try:\n                    content = fpath.read_text(encoding=\"utf-8\").strip()\n                    if content:\n                        parts.append(f\"# {fname}\\n{content}\")\n                except OSError:\n                    pass\n        return \"\\n\\n\".join(parts)\n\n    # ── Volatile tier ────────────────────────────────────────────────────────\n    def _build_volatile(self, memory_block: str = \"\",\n                        session_id: str = \"\", model: str = \"\") -> str:\n        # DATE ONLY — not hour\u002Fminute (prefix cache stability)\n        today = date.today().isoformat()   # \"2026-06-08\"\n        parts = [f\"Date: {today}\"]\n        if session_id: parts.append(f\"Session: {session_id}\")\n        if model:      parts.append(f\"Model: {model}\")\n        if memory_block:\n            parts.append(memory_block)     # already wrapped in \u003Cmemory-context>\n        return \"\\n\".join(parts)\n\n    # ── Public API ───────────────────────────────────────────────────────────\n    def build(self, *, cwd: Path, skills_prompt: str = \"\",\n              caller_system: str = \"\", env_hint: str = \"\",\n              memory_block: str = \"\", session_id: str = \"\",\n              model: str = \"\") -> str:\n        if self._cached:\n            return self._cached\n\n        parts = SystemPromptParts(\n            stable   = self._build_stable(skills_prompt, env_hint),\n            context  = self._build_context(cwd, caller_system),\n            volatile = self._build_volatile(memory_block, session_id, model),\n        )\n        self._cached = parts.assemble()\n        return self._cached\n\n    def invalidate(self) -> None:\n        \"\"\"Call after compression — forces stable tier rebuild next turn.\"\"\"\n        self._cached = None\n        self._stable = None\n```\n\n---\n\n## Wiring in Yana AI (TypeScript sketch)\n\n```typescript\nconst builder = new SystemPromptBuilder(SOUL_MD, formatToolsAsJSON(tools))\n\n\u002F\u002F Build once per session — cache naturally\nconst systemPrompt = builder.build({\n  cwd:          process.cwd(),\n  skillsPrompt: loadSkillsPrompt(),\n  memoryBlock:  await memoryManager.buildSystemPrompt(),\n  sessionId:    sessionId,\n  model:        \"claude-sonnet-4-6\",\n})\n\n\u002F\u002F Every turn: reuse cached prompt\nconst response = await anthropic.messages.create({\n  system:   systemPrompt,   \u002F\u002F same string each turn → prefix cache hit\n  messages: conversationHistory,\n  model:    \"claude-sonnet-4-6\",\n})\n\n\u002F\u002F After compression fires → invalidate + rebuild\nbuilder.invalidate()\n```\n\n---\n\n## Cache hit verification (Anthropic API)\n\n```typescript\n\u002F\u002F Check usage.cache_read_input_tokens in response\nif (response.usage.cache_read_input_tokens > 0) {\n  console.log(`Cache hit: ${response.usage.cache_read_input_tokens} tokens saved`)\n}\n```\n\n---\n\n## Anti-Fake-Pass Checklist\n\n```\n❌ Timestamp includes hours\u002Fminutes — invalidates prefix cache every minute\n❌ Stable tier rebuilt on every turn \"for freshness\" — no cache benefit at all\n❌ Memory block injected into stable tier — volatile content poisons cache\n❌ Context files re-read from disk every turn — I\u002FO waste + cache miss\n❌ invalidate() never called after compression — stale stable prompt persists\n❌ Tool descriptions differ per-turn (model-specific flags toggled) — cache miss\n```\n",{},"main","481dcd7dd2e288b9d627a2bd017db70e64e6c6fa","core\u002Fskills\u002Fhermes-system-prompt-tiers",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 hermes-system-prompt-tiers",{"tool":39,"command":40},"bunx","bunx skills add Horonomos-laps\u002FYana-AI --skill hermes-system-prompt-tiers",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Horonomos-laps\u002FYana-AI --skill hermes-system-prompt-tiers","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fhermes-system-prompt-tiers\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",[],[]]