{"id":"b78a5719-111e-442a-a452-352c26bb79ea","shortId":"XQ3t2w","kind":"skill","title":"recallmax","tagline":"FREE — God-tier long-context memory for AI agents. Injects 500K-1M clean tokens, auto-summarizes with tone/intent preservation, compresses 14-turn history into 800 tokens.","description":"# RecallMax — God-Tier Long-Context Memory\n\n## Overview\n\nRecallMax enhances AI agent memory capabilities dramatically. Inject 500K to 1M clean tokens of external context without hallucination drift. Auto-summarize conversations while preserving tone, sarcasm, and intent. Compress multi-turn histories into high-density token sequences.\n\nFree forever. Built by the Genesis Agent Marketplace.\n\n## Install\n\n```bash\nnpx skills add christopherlhammer11-ai/recallmax\n```\n\n## When to Use This Skill\n\n- Use when your agent loses context in long conversations (50+ turns)\n- Use when injecting large RAG/external documents into agent context\n- Use when you need to compress conversation history without losing meaning\n- Use when fact-checking claims across a long thread\n- Use for any agent that needs to remember everything\n\n## How It Works\n\n### Step 1: Context Injection\n\nRecallMax cleanly injects external context (documents, RAG results, prior conversations) into the agent's working memory. Unlike naive concatenation, it:\n- Deduplicates overlapping content\n- Preserves source attribution\n- Prevents hallucination drift from context pollution\n\n### Step 2: Adaptive Summarization\n\nAs conversations grow, RecallMax automatically summarizes older turns while preserving:\n- **Tone** — sarcasm, formality, urgency\n- **Intent** — what the user actually wants vs. what they said\n- **Key facts** — numbers, names, decisions, commitments\n- **Emotional register** — frustration, excitement, confusion\n\n### Step 3: History Compression\n\nCompress a 14-turn conversation history into ~800 high-density tokens that retain full semantic meaning. The compressed output can be re-expanded if needed.\n\n### Step 4: Fact Verification\n\nBuilt-in cross-reference checks for controversial or ambiguous claims within the conversation context. Flags contradictions and unsupported assertions.\n\n## Best Practices\n\n- ✅ Use RecallMax at the start of long-running agent sessions\n- ✅ Enable auto-summarization for conversations beyond 20 turns\n- ✅ Use compression before hitting context window limits\n- ✅ Let the fact verifier run on high-stakes outputs\n- ❌ Don't inject unvetted external content without dedup\n- ❌ Don't skip summarization and rely on raw truncation\n\n## Related Skills\n\n- `@tool-use-guardian` - Tool-call reliability wrapper (also free from Genesis Marketplace)\n\n## Links\n\n- **Repo:** https://github.com/christopherlhammer11-ai/recallmax\n- **Marketplace:** https://genesis-node-api.vercel.app\n- **Browse skills:** https://genesis-marketplace.vercel.app\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":["recallmax","antigravity","awesome","skills","sickn33","agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding","ai-workflows","antigravity-skills"],"capabilities":["skill","source-sickn33","skill-recallmax","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/recallmax","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 · 34583 github stars · SKILL.md body (2,852 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":"2026-04-22T18:52:07.233Z","embedding":null,"createdAt":"2026-04-18T21:43:24.852Z","updatedAt":"2026-04-22T18:52:07.233Z","lastSeenAt":"2026-04-22T18:52:07.233Z","tsv":"'/christopherlhammer11-ai/recallmax':363 '/recallmax':97 '1':157 '14':26,237 '1m':16,51 '2':193 '20':307 '3':232 '4':263 '50':112 '500k':15,49 '500k-1m':14 '800':30,242 'across':140 'actual':214 'adapt':194 'add':93 'agent':12,44,87,106,121,147,172,298 'ai':11,43,96 'also':354 'ambigu':276 'ask':402 'assert':286 'attribut':185 'auto':20,61,302 'auto-summar':19,60,301 'automat':200 'bash':90 'best':287 'beyond':306 'boundari':410 'brows':366 'built':83,267 'built-in':266 'call':351 'capabl':46 'check':138,272 'christopherlhammer11':95 'christopherlhammer11-ai':94 'claim':139,277 'clarif':404 'clean':17,52,161 'clear':377 'commit':225 'compress':25,70,128,234,235,253,310 'concaten':178 'confus':230 'content':182,331 'context':8,38,56,108,122,158,164,190,281,313 'contradict':283 'controversi':274 'convers':63,111,129,169,197,239,280,305 'criteria':413 'cross':270 'cross-refer':269 'decis':224 'dedup':333 'dedupl':180 'densiti':78,245 'describ':381 'document':119,165 'dramat':47 'drift':59,188 'emot':226 'enabl':300 'enhanc':42 'environ':393 'environment-specif':392 'everyth':152 'excit':229 'expand':259 'expert':398 'extern':55,163,330 'fact':137,221,264,318 'fact-check':136 'flag':282 'forev':82 'formal':208 'free':2,81,355 'frustrat':228 'full':249 'genesi':86,357 'genesis-marketplace.vercel.app':368 'genesis-node-api.vercel.app':365 'github.com':362 'github.com/christopherlhammer11-ai/recallmax':361 'god':4,34 'god-tier':3,33 'grow':198 'guardian':348 'hallucin':58,187 'high':77,244,323 'high-dens':76,243 'high-stak':322 'histori':28,74,130,233,240 'hit':312 'inject':13,48,116,159,162,328 'input':407 'instal':89 'intent':69,210 'key':220 'larg':117 'let':316 'limit':315,369 'link':359 'long':7,37,110,142,296 'long-context':6,36 'long-run':295 'lose':107,132 'marketplac':88,358,364 'match':378 'mean':133,251 'memori':9,39,45,175 'miss':415 'multi':72 'multi-turn':71 'naiv':177 'name':223 'need':126,149,261 'npx':91 'number':222 'older':202 'output':254,325,387 'overlap':181 'overview':40 'permiss':408 'pollut':191 'practic':288 'preserv':24,65,183,205 'prevent':186 'prior':168 'rag':166 'rag/external':118 'raw':341 're':258 're-expand':257 'recallmax':1,32,41,160,199,290 'refer':271 'regist':227 'relat':343 'reli':339 'reliabl':352 'rememb':151 'repo':360 'requir':406 'result':167 'retain':248 'review':399 'run':297,320 'safeti':409 'said':219 'sarcasm':67,207 'scope':380 'semant':250 'sequenc':80 'session':299 'skill':92,102,344,367,372 'skill-recallmax' 'skip':336 'sourc':184 'source-sickn33' 'specif':394 'stake':324 'start':293 'step':156,192,231,262 'stop':400 'substitut':390 'success':412 'summar':21,62,195,201,303,337 'task':376 'test':396 'thread':143 'tier':5,35 'token':18,31,53,79,246 'tone':66,206 'tone/intent':23 'tool':346,350 'tool-cal':349 'tool-use-guardian':345 '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' 'treat':385 'truncat':342 'turn':27,73,113,203,238,308 'unlik':176 'unsupport':285 'unvet':329 'urgenc':209 'use':100,103,114,123,134,144,289,309,347,370 'user':213 'valid':395 'verif':265 'verifi':319 'vs':216 'want':215 'window':314 'within':278 'without':57,131,332 'work':155,174 'wrapper':353","prices":[{"id":"83d50a26-7cbb-41d9-b549-208622c0f607","listingId":"b78a5719-111e-442a-a452-352c26bb79ea","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":"2026-04-18T21:43:24.852Z"}],"sources":[{"listingId":"b78a5719-111e-442a-a452-352c26bb79ea","source":"github","sourceId":"sickn33/antigravity-awesome-skills/recallmax","sourceUrl":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/recallmax","isPrimary":false,"firstSeenAt":"2026-04-18T21:43:24.852Z","lastSeenAt":"2026-04-22T18:52:07.233Z"}],"details":{"listingId":"b78a5719-111e-442a-a452-352c26bb79ea","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"sickn33","slug":"recallmax","github":{"repo":"sickn33/antigravity-awesome-skills","stars":34583,"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":"2026-04-22T06:40:00Z","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":"e038b9037dc284d4713ab0d6471f2036eaad1565","skill_md_path":"skills/recallmax/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/recallmax"},"layout":"multi","source":"github","category":"antigravity-awesome-skills","frontmatter":{"name":"recallmax","description":"FREE — God-tier long-context memory for AI agents. Injects 500K-1M clean tokens, auto-summarizes with tone/intent preservation, compresses 14-turn history into 800 tokens."},"skills_sh_url":"https://skills.sh/sickn33/antigravity-awesome-skills/recallmax"},"updatedAt":"2026-04-22T18:52:07.233Z"}}