[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ED8NWQFFXF0AF774N1PXBV":3,"skill-same:01M7ED8NWQFFXF0AF774N1PXBV":61},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":6,"ownerDescription":45,"updatedAt":46,"install":47,"resources":60},"01M7ED8NWQFFXF0AF774N1PXBV","recursive-context-pruning-token-budgeting",null,"Optimizes AI agent performance by pruning redundant context, managing token usage, and enforcing ultra-concise, direct-to-value responses.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Frecursive-context-pruning-token-budgeting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: recursive-context-pruning-token-budgeting\ndescription: \"Optimizes AI agent performance by pruning redundant context, managing token usage, and enforcing ultra-concise, direct-to-value responses.\"\ncategory: prompt-engineering\nrisk: safe\nsource: self\nsource_repo: Kench001\u002Fantigravity-awesome-skills\nsource_type: self\ndate_added: \"2026-05-03\"\nauthor: Kench001\ntags: [efficiency, token-optimization, brevity, context-management]\ntools: [claude, cursor, gemini]\n# Optional: declare the upstream license if source_repo is set\n# license: \"MIT\"\n# license_source: \"https:\u002F\u002Fgithub.com\u002Fowner\u002Frepo\u002Fblob\u002Fmain\u002FLICENSE\"\n---\n\n# Recursive Context Pruning & Token Budgeting\n\n## Overview\n\nThis skill implements a \"Gatekeeper\" logic to prevent context window bloat and unnecessary token expenditure. It ensures the agent only processes relevant data shards and adheres to an Atomic Precision protocol—delivering functional answers with zero conversational filler. By recursively summarizing state and stripping \"bridge phrases,\" it maximizes the longevity and speed of long-running development workflows.\n\n## When to Use This Skill\n\n- Use when building multi-step agents to prevent repetition and \"memory drift\" in long conversations.\n- Use when working with large document sets or codebases to avoid dumping entire files into the prompt.\n- Use when you need purely functional output (code\u002Flogic) without \"Sure! Here is your...\" intros.\n\n## How It Works\n\n### Step 1: Metadata Sharding\n\nScan the available data for headers, summaries, and key indicators. Create a \"map\" of the context rather than injecting the full source. Never pull the entire file into the prompt unless a specific, narrowed fragment is requested.\n\n### Step 2: Token Budget Allocation\n\nCalculate a \"Safe Response Limit\" based on the current context window. Allocate 30% for current logic processing, 20% for immediate output, and 50% for a future context buffer.\n\n### Step 3: Atomic Output Filtering\n\nStrip all \"Bridge Phrases\" (e.g., \"I've updated the code,\" \"Based on your request,\" \"Sure\"). Start the response immediately with the solution or the code block.\n\n### Step 4: Ambiguity Check\n\nBefore executing Step 3, scan for missing critical variables (e.g., specific file names or environment types). If the prompt is too ambiguous, bypass the atomic output and generate exactly one concise question to resolve the blocker.\n\n### Step 5: Abstractive Compression\n\nSummarize the current turn into a \"compressed state string\" (e.g., `[Project: Feasify | State: Auth-Fixed | Remaining-Tasks: 2]`) to discard redundant conversational data before the next prompt.\n\n## Examples\n\n### Example 1: Filtered Code Output (No Filler)\n\n```text\nUser: \"Update the Firebase config to use environment variables.\"\n```\n\n```javascript\nconst firebaseConfig = {\n  apiKey: process.env.VITE_FIREBASE_API_KEY,\n  authDomain: process.env.VITE_FIREBASE_AUTH_DOMAIN,\n  projectId: process.env.VITE_FIREBASE_PROJECT_ID\n};\n```\n\n### Example 2: Essential Clarification\n\n```text\nUser: \"Deploy the function.\"\n```\n\n```text\n\"Specify environment: production or staging?\"\n```\n\n## Best Practices\n\n- ✅ **Direct Start:** Place the code or answer at the very first character of the response.\n- ✅ **Summarize-as-you-go:** Turn 10 pages of discussion into 5 bullet points for the next turn.\n- ✅ **Omit Signatures:** Never end with \"Let me know if you need more help.\"\n- ❌ **No Bridge Phrases:** Avoid \"Here is the code,\" \"Sure,\" or \"I can help with that.\"\n- ❌ **No Guessing:** If input is missing, ask immediately rather than wasting tokens on a generic guess.\n\n## Limitations\n\n- This skill does not replace environment-specific validation, testing, or expert review.\n- Extreme brevity can occasionally hide important nuances; use concise inline comments (`\u002F\u002F crucial step`) for critical notes.\n\n## Security & Safety Notes\n\n- Never prune safety headers, environment-specific security constraints, or system-level instructions during the compression stage.\n- Maintain original system instructions at the \"Root\" of the context to prevent context-loss-based jailbreaks.\n\n## Common Pitfalls\n\n- **Problem:** The response is so brief it lacks the context needed for implementation.\n  **Solution:** Use concise inline code comments instead of separate paragraphs of text.\n\n- **Problem:** The agent loses the overarching goal due to over-compression.\n  **Solution:** Always pin the \"Primary Objective\" to the top of every pruned prompt.\n\n## Related Skills\n\n- `@atomic-precision-response` - Specifically for removing conversational filler.\n- `@context-sharding` - For managing large-scale documentation mapping.\n\n","# Recursive Context Pruning & Token Budgeting\n\n## Overview\n\nThis skill implements a \"Gatekeeper\" logic to prevent context window bloat and unnecessary token expenditure. It ensures the agent only processes relevant data shards and adheres to an Atomic Precision protocol—delivering functional answers with zero conversational filler. By recursively summarizing state and stripping \"bridge phrases,\" it maximizes the longevity and speed of long-running development workflows.\n\n## When to Use This Skill\n\n- Use when building multi-step agents to prevent repetition and \"memory drift\" in long conversations.\n- Use when working with large document sets or codebases to avoid dumping entire files into the prompt.\n- Use when you need purely functional output (code\u002Flogic) without \"Sure! Here is your...\" intros.\n\n## How It Works\n\n### Step 1: Metadata Sharding\n\nScan the available data for headers, summaries, and key indicators. Create a \"map\" of the context rather than injecting the full source. Never pull the entire file into the prompt unless a specific, narrowed fragment is requested.\n\n### Step 2: Token Budget Allocation\n\nCalculate a \"Safe Response Limit\" based on the current context window. Allocate 30% for current logic processing, 20% for immediate output, and 50% for a future context buffer.\n\n### Step 3: Atomic Output Filtering\n\nStrip all \"Bridge Phrases\" (e.g., \"I've updated the code,\" \"Based on your request,\" \"Sure\"). Start the response immediately with the solution or the code block.\n\n### Step 4: Ambiguity Check\n\nBefore executing Step 3, scan for missing critical variables (e.g., specific file names or environment types). If the prompt is too ambiguous, bypass the atomic output and generate exactly one concise question to resolve the blocker.\n\n### Step 5: Abstractive Compression\n\nSummarize the current turn into a \"compressed state string\" (e.g., `[Project: Feasify | State: Auth-Fixed | Remaining-Tasks: 2]`) to discard redundant conversational data before the next prompt.\n\n## Examples\n\n### Example 1: Filtered Code Output (No Filler)\n\n```text\nUser: \"Update the Firebase config to use environment variables.\"\n```\n\n```javascript\nconst firebaseConfig = {\n  apiKey: process.env.VITE_FIREBASE_API_KEY,\n  authDomain: process.env.VITE_FIREBASE_AUTH_DOMAIN,\n  projectId: process.env.VITE_FIREBASE_PROJECT_ID\n};\n```\n\n### Example 2: Essential Clarification\n\n```text\nUser: \"Deploy the function.\"\n```\n\n```text\n\"Specify environment: production or staging?\"\n```\n\n## Best Practices\n\n- ✅ **Direct Start:** Place the code or answer at the very first character of the response.\n- ✅ **Summarize-as-you-go:** Turn 10 pages of discussion into 5 bullet points for the next turn.\n- ✅ **Omit Signatures:** Never end with \"Let me know if you need more help.\"\n- ❌ **No Bridge Phrases:** Avoid \"Here is the code,\" \"Sure,\" or \"I can help with that.\"\n- ❌ **No Guessing:** If input is missing, ask immediately rather than wasting tokens on a generic guess.\n\n## Limitations\n\n- This skill does not replace environment-specific validation, testing, or expert review.\n- Extreme brevity can occasionally hide important nuances; use concise inline comments (`\u002F\u002F crucial step`) for critical notes.\n\n## Security & Safety Notes\n\n- Never prune safety headers, environment-specific security constraints, or system-level instructions during the compression stage.\n- Maintain original system instructions at the \"Root\" of the context to prevent context-loss-based jailbreaks.\n\n## Common Pitfalls\n\n- **Problem:** The response is so brief it lacks the context needed for implementation.\n  **Solution:** Use concise inline code comments instead of separate paragraphs of text.\n\n- **Problem:** The agent loses the overarching goal due to over-compression.\n  **Solution:** Always pin the \"Primary Objective\" to the top of every pruned prompt.\n\n## Related Skills\n\n- `@atomic-precision-response` - Specifically for removing conversational filler.\n- `@context-sharding` - For managing large-scale documentation mapping.\n\n",{"name":5,"risk":24,"tags":25,"tools":30,"author":34,"source":35,"category":36,"date_added":37,"description":7,"source_repo":38,"source_type":35},"safe",[26,27,28,29],"efficiency","token-optimization","brevity","context-management",[31,32,33],"claude","cursor","gemini","Kench001","self","prompt-engineering","2026-05-03","Kench001\u002Fantigravity-awesome-skills","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","03-逆向工程\u002Frecursive-context-pruning-token-budgeting",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill recursive-context-pruning-token-budgeting",{"tool":53,"command":54},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill recursive-context-pruning-token-budgeting",{"tool":56,"command":57},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill recursive-context-pruning-token-budgeting","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Frecursive-context-pruning-token-budgeting\u002FSKILL.md",true,[],[62,70,75,82,89,96],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":69},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":71,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":69},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":69},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":69},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":69},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":69},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]