[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M737T68BNJCNYACFXT2BE7TE":3,"skill-same:01M737T68BNJCNYACFXT2BE7TE":49},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M737T68BNJCNYACFXT2BE7TE","context-engineering",null,"Use when context is growing large (50k+ tokens), performance is degrading, instructions are being ignored mid-conversation, or planning multi-agent workflows. Triggers on \"lost context\", forgotten instructions, or sessions exceeding 30 minutes.","roohe\u002Fagentic-super-skills","roohe","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99054084?v=4","01M734WCDFP6RZVT5CNM00QR26","01M734WCE4BD0T4NZS5PCV9V5F",10,"MIT","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fcontext-engineering\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: context-engineering\ndescription: Use when context is growing large (50k+ tokens), performance is degrading, instructions are being ignored mid-conversation, or planning multi-agent workflows. Triggers on \"lost context\", forgotten instructions, or sessions exceeding 30 minutes.\nlicense: MIT\nmetadata:\n  author: ClawFu\n  version: 1.0.0\n  mcp-server: \"@clawfu\u002Fmcp-skills\"\n---\n\n# Context Engineering\n\n## Overview\n\n**Core principle:** Context is a finite resource with diminishing returns. Find the smallest high-signal token set, not the largest.\n\n200K tokens is shared space: system prompt + conversation history + your processing. As context grows, performance degrades predictably.\n\n## When to Use\n\n- Session > 30 minutes or 50k+ tokens\n- Instructions being ignored or forgotten\n- Repeated clarifications needed\n- Planning multi-agent workflows\n- Preparing handoffs between sessions\n\n## Quick Reference\n\n| Problem | Symptom | Fix |\n|---------|---------|-----|\n| **Lost-in-middle** | Mid-conversation instructions ignored | Move critical info to start\u002Fend |\n| **Context poisoning** | Errors compounding, hallucinations referenced | Summarize and reset |\n| **Context distraction** | Irrelevant info degrading performance | Prune aggressively |\n| **Context confusion** | Conflicting guidance causing inconsistency | Consolidate instructions |\n\n## Degradation Patterns\n\n### 1. Lost-in-Middle Effect\n\nInformation in context middle gets **10-40% lower recall** than edges.\n\n```\n[START - High attention]\n  ↓\n[MIDDLE - Low attention zone]  ← Instructions here get ignored\n  ↓\n[END - High attention]\n```\n\n**Fix:** Strategic placement\n- Critical instructions → START (system prompt, first user message)\n- Recent decisions → END (last few messages)\n- Reference material → MIDDLE (acceptable for lookup, not instructions)\n\n### 2. Context Poisoning\n\nEarly hallucination gets referenced → compounds → becomes \"fact\".\n\n**Symptoms:**\n- Confident statements contradicting earlier facts\n- \"As we discussed...\" referencing things never said\n- Circular reasoning citing own previous errors\n\n**Fix:** Checkpoint and summarize\n```\nEvery 10-15 exchanges, create explicit checkpoint:\n\n\"Let me summarize what we've established:\n1. [Verified fact]\n2. [Verified fact]\n3. [Decision made]\n\nContinuing from here...\"\n```\n\n### 3. Context Distraction\n\nIrrelevant tokens compete for attention budget.\n\n**Symptoms:**\n- Responses reference unrelated earlier topics\n- Focus drifts from current task\n- Unnecessary caveats about old context\n\n**Fix:** Aggressive pruning\n- Use `\u002Fclear` + summary for fresh context\n- In multi-agent: give subagents ONLY relevant context\n- Remove resolved discussions from active consideration\n\n### 4. Context Confusion\n\nMultiple conflicting instructions create inconsistent behavior.\n\n**Symptoms:**\n- Alternating between approaches\n- \"On one hand... on the other hand...\" hedging\n- Ignoring some instructions to satisfy others\n\n**Fix:** Consolidate\n```\nBefore: \"Use TypeScript\" (message 3) + \"Keep it simple\" (message 12) + \"Add types everywhere\" (message 27)\n\nAfter: \"TypeScript with practical typing - types where they help, skip where obvious\"\n```\n\n## Optimization Techniques\n\n### Compaction\n\nWhen approaching limits, summarize context sections:\n\n```markdown\n## Session Summary (compacted)\n\n**Goal:** [One sentence]\n**Decisions made:**\n- [Decision 1]\n- [Decision 2]\n**Current state:** [What's done, what's next]\n**Key constraints:** [Still-active requirements]\n\n---\n[Continue with fresh context]\n```\n\n### Observation Masking\n\nReplace verbose tool outputs with compact references:\n\n```\nBefore: [500 lines of file content in context]\nAfter: \"Read src\u002Fapp\u002Fpage.tsx - React component with Hero, About, FAQ sections\"\n```\n\n### Context Partitioning (Multi-Agent)\n\nIsolate subtasks in separate agents with clean contexts:\n\n```\nMain Agent (orchestrator):\n  - High-level plan\n  - Synthesis of results\n\nSubagent 1 (search):        Subagent 2 (implement):\n  - Only search context       - Only implementation context\n  - Returns summary           - Returns code\n```\n\n**Rule:** Subagents get task + minimum required context, NOT full conversation history.\n\n## Practical Workflow\n\n### For Long Sessions (>1 hour)\n\n```dot\ndigraph context_management {\n  \"Every 15-20 min\" [shape=diamond];\n  \"Context healthy?\" [shape=diamond];\n  \"Continue\" [shape=box];\n  \"Create checkpoint summary\" [shape=box];\n  \"Consider \u002Fclear + summary\" [shape=box];\n\n  \"Every 15-20 min\" -> \"Context healthy?\";\n  \"Context healthy?\" -> \"Continue\" [label=\"yes\"];\n  \"Context healthy?\" -> \"Create checkpoint summary\" [label=\"degrading\"];\n  \"Create checkpoint summary\" -> \"Consider \u002Fclear + summary\";\n}\n```\n\n**Health check questions:**\n- Are recent instructions being followed?\n- Is focus staying on current task?\n- Are responses becoming vague or hedgy?\n\n### For Handoffs (\u002Fsave-session)\n\nCapture for next session:\n1. **Goal state** - What were we trying to achieve?\n2. **Current state** - What's done, what's broken?\n3. **Key decisions** - Why did we choose X over Y?\n4. **Active constraints** - What rules still apply?\n5. **Next steps** - Where to pick up?\n\n### For Subagents\n\n```markdown\n## Subagent Prompt Template\n\n**Task:** [Specific deliverable]\n**Context:** [ONLY what's needed - 50-200 words max]\n**Constraints:** [Hard requirements]\n**Output format:** [What to return]\n\n[Do NOT include: conversation history, resolved discussions, unrelated files]\n```\n\n## Anti-Patterns\n\n| Anti-Pattern | Why it fails | Better approach |\n|--------------|--------------|-----------------|\n| \"Include everything just in case\" | Dilutes attention, causes distraction | Include only what's needed NOW |\n| Repeating instructions every message | Wastes tokens, implies they weren't heard | Trust system prompt, reinforce only when ignored |\n| Long file dumps without summary | Lost-in-middle effect | Read → summarize → reference summary |\n| Keeping resolved threads active | Context confusion | Summarize resolution, move on |\n\n## Token Budget Guidelines\n\n| Context size | Expected quality | Action |\n|--------------|------------------|--------|\n| \u003C 20k | Optimal | Continue normally |\n| 20-50k | Good | Monitor for degradation |\n| 50-100k | Degrading | Active management needed |\n| 100-150k | Poor | Summarize and reset soon |\n| > 150k | Critical | Reset with checkpoint |\n\n## Key Insight\n\n> \"The goal isn't to use all 200K tokens. It's to use the fewest tokens that achieve your outcome.\"\n\nInformativity over exhaustiveness. Include what matters for current decisions, exclude everything else, and design systems that access additional information on demand.\n\n---\n\n## What Claude Does vs What You Decide\n\n| Claude handles | You provide |\n|---------------|-------------|\n| Monitoring context health | Decision to reset or continue |\n| Creating checkpoint summaries | Validation that summary is accurate |\n| Pruning irrelevant content | Judgment on what's still needed |\n| Structuring subagent prompts | Strategic task decomposition |\n| Detecting degradation patterns | Timing of interventions |\n\n---\n\n## Skill Boundaries\n\n### This skill excels for:\n- Long sessions (>30 min, >50k tokens)\n- Multi-agent workflows with handoffs\n- Complex projects spanning multiple sessions\n- Debugging \"forgotten instruction\" issues\n\n### This skill is NOT ideal for:\n- Short, focused interactions → Not needed\n- Single-turn queries → Overhead unnecessary\n- Tasks with naturally bounded context → Already constrained\n\n---\n\n## Skill Metadata\n\n```yaml\nname: context-engineering\ncategory: meta\nversion: 2.0\nauthor: GUIA\nsource_expert: Anthropic research, NeoLabHQ context-engineering-kit\ndifficulty: advanced\nmode: centaur\ntags: [context, tokens, memory, multi-agent, handoff, optimization]\ncreated: 2026-02-03\nupdated: 2026-02-03\n```\n","# Context Engineering\n\n## Overview\n\n**Core principle:** Context is a finite resource with diminishing returns. Find the smallest high-signal token set, not the largest.\n\n200K tokens is shared space: system prompt + conversation history + your processing. As context grows, performance degrades predictably.\n\n## When to Use\n\n- Session > 30 minutes or 50k+ tokens\n- Instructions being ignored or forgotten\n- Repeated clarifications needed\n- Planning multi-agent workflows\n- Preparing handoffs between sessions\n\n## Quick Reference\n\n| Problem | Symptom | Fix |\n|---------|---------|-----|\n| **Lost-in-middle** | Mid-conversation instructions ignored | Move critical info to start\u002Fend |\n| **Context poisoning** | Errors compounding, hallucinations referenced | Summarize and reset |\n| **Context distraction** | Irrelevant info degrading performance | Prune aggressively |\n| **Context confusion** | Conflicting guidance causing inconsistency | Consolidate instructions |\n\n## Degradation Patterns\n\n### 1. Lost-in-Middle Effect\n\nInformation in context middle gets **10-40% lower recall** than edges.\n\n```\n[START - High attention]\n  ↓\n[MIDDLE - Low attention zone]  ← Instructions here get ignored\n  ↓\n[END - High attention]\n```\n\n**Fix:** Strategic placement\n- Critical instructions → START (system prompt, first user message)\n- Recent decisions → END (last few messages)\n- Reference material → MIDDLE (acceptable for lookup, not instructions)\n\n### 2. Context Poisoning\n\nEarly hallucination gets referenced → compounds → becomes \"fact\".\n\n**Symptoms:**\n- Confident statements contradicting earlier facts\n- \"As we discussed...\" referencing things never said\n- Circular reasoning citing own previous errors\n\n**Fix:** Checkpoint and summarize\n```\nEvery 10-15 exchanges, create explicit checkpoint:\n\n\"Let me summarize what we've established:\n1. [Verified fact]\n2. [Verified fact]\n3. [Decision made]\n\nContinuing from here...\"\n```\n\n### 3. Context Distraction\n\nIrrelevant tokens compete for attention budget.\n\n**Symptoms:**\n- Responses reference unrelated earlier topics\n- Focus drifts from current task\n- Unnecessary caveats about old context\n\n**Fix:** Aggressive pruning\n- Use `\u002Fclear` + summary for fresh context\n- In multi-agent: give subagents ONLY relevant context\n- Remove resolved discussions from active consideration\n\n### 4. Context Confusion\n\nMultiple conflicting instructions create inconsistent behavior.\n\n**Symptoms:**\n- Alternating between approaches\n- \"On one hand... on the other hand...\" hedging\n- Ignoring some instructions to satisfy others\n\n**Fix:** Consolidate\n```\nBefore: \"Use TypeScript\" (message 3) + \"Keep it simple\" (message 12) + \"Add types everywhere\" (message 27)\n\nAfter: \"TypeScript with practical typing - types where they help, skip where obvious\"\n```\n\n## Optimization Techniques\n\n### Compaction\n\nWhen approaching limits, summarize context sections:\n\n```markdown\n## Session Summary (compacted)\n\n**Goal:** [One sentence]\n**Decisions made:**\n- [Decision 1]\n- [Decision 2]\n**Current state:** [What's done, what's next]\n**Key constraints:** [Still-active requirements]\n\n---\n[Continue with fresh context]\n```\n\n### Observation Masking\n\nReplace verbose tool outputs with compact references:\n\n```\nBefore: [500 lines of file content in context]\nAfter: \"Read src\u002Fapp\u002Fpage.tsx - React component with Hero, About, FAQ sections\"\n```\n\n### Context Partitioning (Multi-Agent)\n\nIsolate subtasks in separate agents with clean contexts:\n\n```\nMain Agent (orchestrator):\n  - High-level plan\n  - Synthesis of results\n\nSubagent 1 (search):        Subagent 2 (implement):\n  - Only search context       - Only implementation context\n  - Returns summary           - Returns code\n```\n\n**Rule:** Subagents get task + minimum required context, NOT full conversation history.\n\n## Practical Workflow\n\n### For Long Sessions (>1 hour)\n\n```dot\ndigraph context_management {\n  \"Every 15-20 min\" [shape=diamond];\n  \"Context healthy?\" [shape=diamond];\n  \"Continue\" [shape=box];\n  \"Create checkpoint summary\" [shape=box];\n  \"Consider \u002Fclear + summary\" [shape=box];\n\n  \"Every 15-20 min\" -> \"Context healthy?\";\n  \"Context healthy?\" -> \"Continue\" [label=\"yes\"];\n  \"Context healthy?\" -> \"Create checkpoint summary\" [label=\"degrading\"];\n  \"Create checkpoint summary\" -> \"Consider \u002Fclear + summary\";\n}\n```\n\n**Health check questions:**\n- Are recent instructions being followed?\n- Is focus staying on current task?\n- Are responses becoming vague or hedgy?\n\n### For Handoffs (\u002Fsave-session)\n\nCapture for next session:\n1. **Goal state** - What were we trying to achieve?\n2. **Current state** - What's done, what's broken?\n3. **Key decisions** - Why did we choose X over Y?\n4. **Active constraints** - What rules still apply?\n5. **Next steps** - Where to pick up?\n\n### For Subagents\n\n```markdown\n## Subagent Prompt Template\n\n**Task:** [Specific deliverable]\n**Context:** [ONLY what's needed - 50-200 words max]\n**Constraints:** [Hard requirements]\n**Output format:** [What to return]\n\n[Do NOT include: conversation history, resolved discussions, unrelated files]\n```\n\n## Anti-Patterns\n\n| Anti-Pattern | Why it fails | Better approach |\n|--------------|--------------|-----------------|\n| \"Include everything just in case\" | Dilutes attention, causes distraction | Include only what's needed NOW |\n| Repeating instructions every message | Wastes tokens, implies they weren't heard | Trust system prompt, reinforce only when ignored |\n| Long file dumps without summary | Lost-in-middle effect | Read → summarize → reference summary |\n| Keeping resolved threads active | Context confusion | Summarize resolution, move on |\n\n## Token Budget Guidelines\n\n| Context size | Expected quality | Action |\n|--------------|------------------|--------|\n| \u003C 20k | Optimal | Continue normally |\n| 20-50k | Good | Monitor for degradation |\n| 50-100k | Degrading | Active management needed |\n| 100-150k | Poor | Summarize and reset soon |\n| > 150k | Critical | Reset with checkpoint |\n\n## Key Insight\n\n> \"The goal isn't to use all 200K tokens. It's to use the fewest tokens that achieve your outcome.\"\n\nInformativity over exhaustiveness. Include what matters for current decisions, exclude everything else, and design systems that access additional information on demand.\n\n---\n\n## What Claude Does vs What You Decide\n\n| Claude handles | You provide |\n|---------------|-------------|\n| Monitoring context health | Decision to reset or continue |\n| Creating checkpoint summaries | Validation that summary is accurate |\n| Pruning irrelevant content | Judgment on what's still needed |\n| Structuring subagent prompts | Strategic task decomposition |\n| Detecting degradation patterns | Timing of interventions |\n\n---\n\n## Skill Boundaries\n\n### This skill excels for:\n- Long sessions (>30 min, >50k tokens)\n- Multi-agent workflows with handoffs\n- Complex projects spanning multiple sessions\n- Debugging \"forgotten instruction\" issues\n\n### This skill is NOT ideal for:\n- Short, focused interactions → Not needed\n- Single-turn queries → Overhead unnecessary\n- Tasks with naturally bounded context → Already constrained\n\n---\n\n## Skill Metadata\n\n```yaml\nname: context-engineering\ncategory: meta\nversion: 2.0\nauthor: GUIA\nsource_expert: Anthropic research, NeoLabHQ context-engineering-kit\ndifficulty: advanced\nmode: centaur\ntags: [context, tokens, memory, multi-agent, handoff, optimization]\ncreated: 2026-02-03\nupdated: 2026-02-03\n```\n",{"name":5,"license":14,"metadata":23,"description":7},{"author":24,"version":25,"mcp-server":26},"ClawFu","1.0.0","@clawfu\u002Fmcp-skills","master","f483e54f3ad5f202a77d45f2e57f8d970b71195f","skills_library\u002Fcontext-engineering",2,"https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills","https:\u002F\u002Fgithub.com\u002Froohe","yoou.link","2026-05-19 15:56:07",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add roohe\u002Fagentic-super-skills --skill context-engineering",{"tool":41,"command":42},"bunx","bunx skills add roohe\u002Fagentic-super-skills --skill context-engineering",{"tool":44,"command":45},"pnpm","pnpm dlx skills add roohe\u002Fagentic-super-skills --skill context-engineering","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fcontext-engineering\u002FSKILL.md",true,[],[50,57,64,71,78,85],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":18},"01M73D865CZME2FCMKA4PQM348","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fzarr-python\u002FSKILL.md",[],[],{"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},"01M73D7Z64J4ABWZJD7P44XBBF","youtube-downloader","Download and process YouTube content for research. Use when: downloading competitor videos for analysis; extracting audio for podcasts; getting transcripts for content repurposing; archiving webinars; research content curation","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fyoutube-downloader\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},"01M73D7K8778TGZV3GJFR3703D","yc-pitch-deck","Create a compelling startup pitch deck that follows the structure proven to raise billions from top investors. Master the YC and Sequoia formats that get founders funded. Use when: **Fundraising** to create investor pitch decks; **YC application** to structure your narrative; **Demo Day prep** to craft your 2-minute pitch; **Angel investors** to communicate your opportunity; **Partnership pitches** to structure compelling asks","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fyc-pitch-deck\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},"01M73D70KJSE0E8Z28YMNNRT04","x-twitter-scraper","Use when the user needs X (Twitter) data or confirmation-gated X actions through Xquik: tweet search, user lookup, follower extraction, media download, monitoring, webhooks, MCP, SDKs, posting, likes, DMs, and profile updates. Requires a Xquik API key. Never ask for X login material.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fx-twitter-scraper\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},"01M73D6ED01GV077R7K4NZNFZJ","write-vignette","Create R package vignettes using R Markdown or Quarto. Covers vignette setup, YAML configuration, code chunk options, building and testing, and CRAN requirements for vignettes. Use when adding a Getting Started tutorial, documenting complex workflows spanning multiple functions, creating domain-specific guides, or when CRAN submission requires user-facing documentation beyond function help pages.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fwrite-vignette\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},"01M73D69YJR0BK3NFHE0CYG3EF","write-validation-documentation","Write IQ\u002FOQ\u002FPQ validation documentation for computerized systems in regulated environments. Covers protocols, reports, test scripts, deviation handling, and approval workflows. Use when validating R or other software for regulated use, preparing for a regulatory audit, documenting qualification of computing environments, or creating and updating validation protocols and reports for new or re-qualified systems.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fwrite-validation-documentation\u002FSKILL.md",[],[]]