{"id":"8b6d799a-3280-4c1a-84eb-684d40678f72","shortId":"TLWzpd","kind":"skill","title":"context-management-context-restore","tagline":"Use when working with context management context restore","description":"# Context Restoration: Advanced Semantic Memory Rehydration\n\n## Use this skill when\n\n- Working on context restoration: advanced semantic memory rehydration tasks or workflows\n- Needing guidance, best practices, or checklists for context restoration: advanced semantic memory rehydration\n\n## Do not use this skill when\n\n- The task is unrelated to context restoration: advanced semantic memory rehydration\n- You need a different domain or tool outside this scope\n\n## Instructions\n\n- Clarify goals, constraints, and required inputs.\n- Apply relevant best practices and validate outcomes.\n- Provide actionable steps and verification.\n- If detailed examples are required, open `resources/implementation-playbook.md`.\n\n## Role Statement\n\nExpert Context Restoration Specialist focused on intelligent, semantic-aware context retrieval and reconstruction across complex multi-agent AI workflows. Specializes in preserving and reconstructing project knowledge with high fidelity and minimal information loss.\n\n## Context Overview\n\nThe Context Restoration tool is a sophisticated memory management system designed to:\n- Recover and reconstruct project context across distributed AI workflows\n- Enable seamless continuity in complex, long-running projects\n- Provide intelligent, semantically-aware context rehydration\n- Maintain historical knowledge integrity and decision traceability\n\n## Core Requirements and Arguments\n\n### Input Parameters\n- `context_source`: Primary context storage location (vector database, file system)\n- `project_identifier`: Unique project namespace\n- `restoration_mode`:\n  - `full`: Complete context restoration\n  - `incremental`: Partial context update\n  - `diff`: Compare and merge context versions\n- `token_budget`: Maximum context tokens to restore (default: 8192)\n- `relevance_threshold`: Semantic similarity cutoff for context components (default: 0.75)\n\n## Advanced Context Retrieval Strategies\n\n### 1. Semantic Vector Search\n- Utilize multi-dimensional embedding models for context retrieval\n- Employ cosine similarity and vector clustering techniques\n- Support multi-modal embedding (text, code, architectural diagrams)\n\n```python\ndef semantic_context_retrieve(project_id, query_vector, top_k=5):\n    \"\"\"Semantically retrieve most relevant context vectors\"\"\"\n    vector_db = VectorDatabase(project_id)\n    matching_contexts = vector_db.search(\n        query_vector,\n        similarity_threshold=0.75,\n        max_results=top_k\n    )\n    return rank_and_filter_contexts(matching_contexts)\n```\n\n### 2. Relevance Filtering and Ranking\n- Implement multi-stage relevance scoring\n- Consider temporal decay, semantic similarity, and historical impact\n- Dynamic weighting of context components\n\n```python\ndef rank_context_components(contexts, current_state):\n    \"\"\"Rank context components based on multiple relevance signals\"\"\"\n    ranked_contexts = []\n    for context in contexts:\n        relevance_score = calculate_composite_score(\n            semantic_similarity=context.semantic_score,\n            temporal_relevance=context.age_factor,\n            historical_impact=context.decision_weight\n        )\n        ranked_contexts.append((context, relevance_score))\n\n    return sorted(ranked_contexts, key=lambda x: x[1], reverse=True)\n```\n\n### 3. Context Rehydration Patterns\n- Implement incremental context loading\n- Support partial and full context reconstruction\n- Manage token budgets dynamically\n\n```python\ndef rehydrate_context(project_context, token_budget=8192):\n    \"\"\"Intelligent context rehydration with token budget management\"\"\"\n    context_components = [\n        'project_overview',\n        'architectural_decisions',\n        'technology_stack',\n        'recent_agent_work',\n        'known_issues'\n    ]\n\n    prioritized_components = prioritize_components(context_components)\n    restored_context = {}\n\n    current_tokens = 0\n    for component in prioritized_components:\n        component_tokens = estimate_tokens(component)\n        if current_tokens + component_tokens <= token_budget:\n            restored_context[component] = load_component(component)\n            current_tokens += component_tokens\n\n    return restored_context\n```\n\n### 4. Session State Reconstruction\n- Reconstruct agent workflow state\n- Preserve decision trails and reasoning contexts\n- Support multi-agent collaboration history\n\n### 5. Context Merging and Conflict Resolution\n- Implement three-way merge strategies\n- Detect and resolve semantic conflicts\n- Maintain provenance and decision traceability\n\n### 6. Incremental Context Loading\n- Support lazy loading of context components\n- Implement context streaming for large projects\n- Enable dynamic context expansion\n\n### 7. Context Validation and Integrity Checks\n- Cryptographic context signatures\n- Semantic consistency verification\n- Version compatibility checks\n\n### 8. Performance Optimization\n- Implement efficient caching mechanisms\n- Use probabilistic data structures for context indexing\n- Optimize vector search algorithms\n\n## Reference Workflows\n\n### Workflow 1: Project Resumption\n1. Retrieve most recent project context\n2. Validate context against current codebase\n3. Selectively restore relevant components\n4. Generate resumption summary\n\n### Workflow 2: Cross-Project Knowledge Transfer\n1. Extract semantic vectors from source project\n2. Map and transfer relevant knowledge\n3. Adapt context to target project's domain\n4. Validate knowledge transferability\n\n## Usage Examples\n\n```bash\n# Full context restoration\ncontext-restore project:ai-assistant --mode full\n\n# Incremental context update\ncontext-restore project:web-platform --mode incremental\n\n# Semantic context query\ncontext-restore project:ml-pipeline --query \"model training strategy\"\n```\n\n## Integration Patterns\n- RAG (Retrieval Augmented Generation) pipelines\n- Multi-agent workflow coordination\n- Continuous learning systems\n- Enterprise knowledge management\n\n## Future Roadmap\n- Enhanced multi-modal embedding support\n- Quantum-inspired vector search algorithms\n- Self-healing context reconstruction\n- Adaptive learning context strategies\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.","tags":["context","management","restore","antigravity","awesome","skills","sickn33","agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding"],"capabilities":["skill","source-sickn33","skill-context-management-context-restore","topic-agent-skills","topic-agentic-skills","topic-ai-agent-skills","topic-ai-agents","topic-ai-coding","topic-ai-workflows","topic-antigravity","topic-antigravity-skills","topic-claude-code","topic-claude-code-skills","topic-codex-cli","topic-codex-skills"],"categories":["antigravity-awesome-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/sickn33/antigravity-awesome-skills/context-management-context-restore","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add sickn33/antigravity-awesome-skills","source_repo":"https://github.com/sickn33/antigravity-awesome-skills","install_from":"skills.sh"}},"qualityScore":"0.700","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 34831 github stars · SKILL.md body (6,391 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-04-24T06:50:57.602Z","embedding":null,"createdAt":"2026-04-18T21:35:08.708Z","updatedAt":"2026-04-24T06:50:57.602Z","lastSeenAt":"2026-04-24T06:50:57.602Z","tsv":"'0':450 '0.75':239,303 '1':244,390,579,582,610 '2':315,588,604,617 '3':393,594,623 '4':481,599,631 '5':284,501 '6':523 '7':543 '8':558 '8192':229,419 'across':117,157 'action':90 'adapt':624,713 'advanc':16,28,44,61,240 'agent':121,436,486,498,685 'ai':122,159,646 'ai-assist':645 'algorithm':575,707 'appli':82 'architectur':271,431 'argument':187 'ask':750 'assist':647 'augment':680 'awar':112,174 'base':350 'bash':637 'best':37,84 'boundari':758 'budget':222,409,418,425,467 'cach':563 'calcul':363 'check':548,557 'checklist':40 'clarif':752 'clarifi':76 'clear':725 'cluster':262 'code':270 'codebas':593 'collabor':499 'compar':216 'compat':556 'complet':208 'complex':118,165 'compon':237,338,343,349,428,441,443,445,452,455,456,460,464,470,472,473,476,532,598 'composit':364 'conflict':505,517 'consid':326 'consist':553 'constraint':78 'context':2,4,10,12,14,26,42,59,104,113,138,141,156,175,190,193,209,213,219,224,236,241,255,276,289,297,312,314,337,342,344,348,356,358,360,379,385,394,399,405,414,416,421,427,444,447,469,480,494,502,525,531,534,541,544,550,570,587,590,625,639,642,651,654,663,666,711,715 'context-management-context-restor':1 'context-restor':641,653,665 'context.age':372 'context.decision':376 'context.semantic':368 'continu':163,688 'coordin':687 'core':184 'cosin':258 'criteria':761 'cross':606 'cross-project':605 'cryptograph':549 'current':345,448,462,474,592 'cutoff':234 'data':567 'databas':197 'db':292 'decay':328 'decis':182,432,490,521 'def':274,340,412 'default':228,238 'describ':729 'design':150 'detail':95 'detect':513 'diagram':272 'diff':215 'differ':68 'dimension':251 'distribut':158 'domain':69,630 'dynam':334,410,540 'effici':562 'embed':252,268,700 'employ':257 'enabl':161,539 'enhanc':696 'enterpris':691 'environ':741 'environment-specif':740 'estim':458 'exampl':96,636 'expans':542 'expert':103,746 'extract':611 'factor':373 'fidel':133 'file':198 'filter':311,317 'focus':107 'full':207,404,638,649 'futur':694 'generat':600,681 'goal':77 'guidanc':36 'heal':710 'high':132 'histor':178,332,374 'histori':500 'id':279,295 'identifi':201 'impact':333,375 'implement':320,397,507,533,561 'increment':211,398,524,650,661 'index':571 'inform':136 'input':81,188,755 'inspir':704 'instruct':75 'integr':180,547,676 'intellig':109,171,420 'issu':439 'k':283,307 'key':386 'knowledg':130,179,608,622,633,692 'known':438 'lambda':387 'larg':537 'lazi':528 'learn':689,714 'limit':717 'load':400,471,526,529 'locat':195 'long':167 'long-run':166 'loss':137 'maintain':177,518 'manag':3,11,148,407,426,693 'map':618 'match':296,313,726 'max':304 'maximum':223 'mechan':564 'memori':18,30,46,63,147 'merg':218,503,511 'minim':135 'miss':763 'ml':670 'ml-pipelin':669 'modal':267,699 'mode':206,648,660 'model':253,673 'multi':120,250,266,322,497,684,698 'multi-ag':119,496,683 'multi-dimension':249 'multi-mod':265,697 'multi-stag':321 'multipl':352 'namespac':204 'need':35,66 'open':99 'optim':560,572 'outcom':88 'output':735 'outsid':72 'overview':139,430 'paramet':189 'partial':212,402 'pattern':396,677 'perform':559 'permiss':756 'pipelin':671,682 'platform':659 'practic':38,85 'preserv':126,489 'primari':192 'priorit':440,442,454 'probabilist':566 'project':129,155,169,200,203,278,294,415,429,538,580,586,607,616,628,644,656,668 'proven':519 'provid':89,170 'python':273,339,411 'quantum':703 'quantum-inspir':702 'queri':280,299,664,672 'rag':678 'rank':309,319,341,347,355,384 'ranked_contexts.append':378 'reason':493 'recent':435,585 'reconstruct':116,128,154,406,484,485,712 'recov':152 'refer':576 'rehydr':19,31,47,64,176,395,413,422 'relev':83,230,288,316,324,353,361,371,380,597,621 'requir':80,98,185,754 'resolut':506 'resolv':515 'resources/implementation-playbook.md':100 'restor':5,13,15,27,43,60,105,142,205,210,227,446,468,479,596,640,643,655,667 'result':305 'resumpt':581,601 'retriev':114,242,256,277,286,583,679 'return':308,382,478 'revers':391 'review':747 'roadmap':695 'role':101 'run':168 'safeti':757 'scope':74,728 'score':325,362,365,369,381 'seamless':162 'search':247,574,706 'select':595 'self':709 'self-heal':708 'semant':17,29,45,62,111,173,232,245,275,285,329,366,516,552,612,662 'semantic-awar':110 'semantically-awar':172 'session':482 'signal':354 'signatur':551 'similar':233,259,301,330,367 'skill':22,52,720 'skill-context-management-context-restore' 'sophist':146 'sort':383 'sourc':191,615 'source-sickn33' 'special':124 'specialist':106 'specif':742 'stack':434 'stage':323 'state':346,483,488 'statement':102 'step':91 'stop':748 'storag':194 'strategi':243,512,675,716 'stream':535 'structur':568 'substitut':738 'success':760 'summari':602 'support':264,401,495,527,701 'system':149,199,690 'target':627 'task':32,55,724 'techniqu':263 'technolog':433 'tempor':327,370 'test':744 'text':269 'three':509 'three-way':508 'threshold':231,302 'token':221,225,408,417,424,449,457,459,463,465,466,475,477 'tool':71,143 'top':282,306 'topic-agent-skills' 'topic-agentic-skills' 'topic-ai-agent-skills' 'topic-ai-agents' 'topic-ai-coding' 'topic-ai-workflows' 'topic-antigravity' 'topic-antigravity-skills' 'topic-claude-code' 'topic-claude-code-skills' 'topic-codex-cli' 'topic-codex-skills' 'traceabl':183,522 'trail':491 'train':674 'transfer':609,620,634 'treat':733 'true':392 'uniqu':202 'unrel':57 'updat':214,652 'usag':635 'use':6,20,50,565,718 'util':248 'valid':87,545,589,632,743 'vector':196,246,261,281,290,291,300,573,613,705 'vector_db.search':298 'vectordatabas':293 'verif':93,554 'version':220,555 'way':510 'web':658 'web-platform':657 'weight':335,377 'work':8,24,437 'workflow':34,123,160,487,577,578,603,686 'x':388,389","prices":[{"id":"26ed79eb-0286-46c9-b97c-0ef92e1358b4","listingId":"8b6d799a-3280-4c1a-84eb-684d40678f72","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"sickn33","category":"antigravity-awesome-skills","install_from":"skills.sh"},"createdAt":"2026-04-18T21:35:08.708Z"}],"sources":[{"listingId":"8b6d799a-3280-4c1a-84eb-684d40678f72","source":"github","sourceId":"sickn33/antigravity-awesome-skills/context-management-context-restore","sourceUrl":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/context-management-context-restore","isPrimary":false,"firstSeenAt":"2026-04-18T21:35:08.708Z","lastSeenAt":"2026-04-24T06:50:57.602Z"}],"details":{"listingId":"8b6d799a-3280-4c1a-84eb-684d40678f72","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"sickn33","slug":"context-management-context-restore","github":{"repo":"sickn33/antigravity-awesome-skills","stars":34831,"topics":["agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding","ai-workflows","antigravity","antigravity-skills","claude-code","claude-code-skills","codex-cli","codex-skills","cursor","cursor-skills","developer-tools","gemini-cli","gemini-skills","kiro","mcp","skill-library"],"license":"mit","html_url":"https://github.com/sickn33/antigravity-awesome-skills","pushed_at":"2026-04-24T06:41:17Z","description":"Installable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.","skill_md_sha":"dfce403289ea9ab37c2e06d9dcb00951d8e37fc4","skill_md_path":"skills/context-management-context-restore/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/context-management-context-restore"},"layout":"multi","source":"github","category":"antigravity-awesome-skills","frontmatter":{"name":"context-management-context-restore","description":"Use when working with context management context restore"},"skills_sh_url":"https://skills.sh/sickn33/antigravity-awesome-skills/context-management-context-restore"},"updatedAt":"2026-04-24T06:50:57.602Z"}}