{"id":"a18f33fe-43ad-4e16-8e3d-8c1214522479","shortId":"6EEW9Q","kind":"skill","title":"caveman","tagline":"Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says \"caveman mode\", \"talk like caveman\", \"use caveman\", \"less tokens\", \"be brief\", or invokes /caveman.","description":"Respond terse like smart caveman. All technical substance stay. Only fluff die.\n\n## Persistence\n\nACTIVE EVERY RESPONSE once triggered. No revert after many turns. No filler drift. Still active if unsure. Off only when user says \"stop caveman\" or \"normal mode\".\n\n## Rules\n\nDrop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries (sure/certainly/of course/happy to), hedging. Fragments OK. Short synonyms (big not extensive, fix not \"implement a solution for\"). Abbreviate common terms (DB/auth/config/req/res/fn/impl). Strip conjunctions. Use arrows for causality (X -> Y). One word when one word enough.\n\nTechnical terms stay exact. Code blocks unchanged. Errors quoted exact.\n\nPattern: `[thing] [action] [reason]. [next step].`\n\nNot: \"Sure! I'd be happy to help you with that. The issue you're experiencing is likely caused by...\"\nYes: \"Bug in auth middleware. Token expiry check use `<` not `<=`. Fix:\"\n\n### Examples\n\n**\"Why React component re-render?\"**\n\n> Inline obj prop -> new ref -> re-render. `useMemo`.\n\n**\"Explain database connection pooling.\"**\n\n> Pool = reuse DB conn. Skip handshake -> fast under load.\n\n## Auto-Clarity Exception\n\nDrop caveman temporarily for: security warnings, irreversible action confirmations, multi-step sequences where fragment order risks misread, user asks to clarify or repeats question. Resume caveman after clear part done.\n\nExample -- destructive op:\n\n> **Warning:** This will permanently delete all rows in the `users` table and cannot be undone.\n>\n> ```sql\n> DROP TABLE users;\n> ```\n>\n> Caveman resume. Verify backup exist first.","tags":["caveman","agent","skills","helderberto","agent-skills","ai-tools","antigravity","claude-code","cursor","developer-tools","gemini-cli","markdown"],"capabilities":["skill","source-helderberto","skill-caveman","topic-agent-skills","topic-ai-tools","topic-antigravity","topic-claude-code","topic-cursor","topic-developer-tools","topic-gemini-cli","topic-markdown","topic-plugin","topic-sdlc","topic-skills","topic-tracer-bullet"],"categories":["agent-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/helderberto/agent-skills/caveman","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add helderberto/agent-skills","source_repo":"https://github.com/helderberto/agent-skills","install_from":"skills.sh"}},"qualityScore":"0.454","qualityRationale":"deterministic score 0.45 from registry signals: · indexed on github topic:agent-skills · 8 github stars · SKILL.md body (1,605 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":"2026-05-18T19:09:11.911Z","embedding":null,"createdAt":"2026-05-18T13:14:51.726Z","updatedAt":"2026-05-18T19:09:11.911Z","lastSeenAt":"2026-05-18T19:09:11.911Z","tsv":"'/caveman':39 '75':10 'a/an/the':83 'abbrevi':104 'accuraci':21 'action':134,209 'activ':53,67 'arrow':111 'articl':14,82 'ask':221 'auth':161 'auto':199 'auto-clar':198 'backup':258 'big':95 'block':127 'brief':36 'bug':159 'cannot':248 'caus':156 'causal':113 'caveman':1,26,30,32,44,76,203,228,255 'check':165 'clarifi':223 'clariti':200 'clear':230 'code':126 'common':105 'communic':5 'compon':172 'compress':4 'confirm':210 'conjunct':109 'conn':192 'connect':187 'course/happy':88 'cut':7 'd':141 'databas':186 'db':191 'db/auth/config/req/res/fn/impl':107 'delet':240 'destruct':234 'die':51 'done':232 'drift':65 'drop':12,81,202,252 'enough':121 'error':129 'everi':54 'exact':125,131 'exampl':169,233 'except':201 'exist':259 'experienc':153 'expiri':164 'explain':185 'extens':97 'fast':195 'filler':13,64,84 'first':260 'fix':98,168 'fluff':50 'fragment':91,216 'full':19 'handshak':194 'happi':143 'hedg':90 'help':145 'implement':100 'inlin':176 'invok':38 'irrevers':208 'issu':150 'just/really/basically/actually/simply':85 'keep':18 'less':33 'like':29,42,155 'load':197 'mani':61 'middlewar':162 'misread':219 'mode':6,27,79 'multi':212 'multi-step':211 'new':179 'next':136 'normal':78 'obj':177 'ok':92 'one':116,119 'op':235 'order':217 'part':231 'pattern':132 'perman':239 'persist':52 'pleasantri':16,86 'pool':188,189 'prop':178 'question':226 'quot':130 're':152,174,182 're-rend':173,181 'react':171 'reason':135 'ref':180 'render':175,183 'repeat':225 'respond':40 'respons':55 'resum':227,256 'reus':190 'revert':59 'risk':218 'row':242 'rule':80 'say':25,74 'secur':206 'sequenc':214 'short':93 'skill' 'skill-caveman' 'skip':193 'smart':43 'solut':102 'source-helderberto' 'sql':251 'stay':48,124 'step':137,213 'still':66 'stop':75 'strip':108 'substanc':47 'sure':139 'sure/certainly/of':87 'synonym':94 'tabl':246,253 'talk':28 'technic':20,46,122 'temporarili':204 'term':106,123 'ters':41 'thing':133 'token':8,34,163 'topic-agent-skills' 'topic-ai-tools' 'topic-antigravity' 'topic-claude-code' 'topic-cursor' 'topic-developer-tools' 'topic-gemini-cli' 'topic-markdown' 'topic-plugin' 'topic-sdlc' 'topic-skills' 'topic-tracer-bullet' 'trigger':57 'turn':62 'ultra':3 'ultra-compress':2 'unchang':128 'undon':250 'unsur':69 'usag':9 'use':22,31,110,166 'usememo':184 'user':24,73,220,245,254 'verifi':257 'warn':207,236 'word':117,120 'x':114 'y':115 'yes':158","prices":[{"id":"b0b0a927-7b5f-4693-a86b-3344dfb86ab7","listingId":"a18f33fe-43ad-4e16-8e3d-8c1214522479","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"helderberto","category":"agent-skills","install_from":"skills.sh"},"createdAt":"2026-05-18T13:14:51.726Z"}],"sources":[{"listingId":"a18f33fe-43ad-4e16-8e3d-8c1214522479","source":"github","sourceId":"helderberto/agent-skills/caveman","sourceUrl":"https://github.com/helderberto/agent-skills/tree/main/skills/caveman","isPrimary":false,"firstSeenAt":"2026-05-18T13:14:51.726Z","lastSeenAt":"2026-05-18T19:09:11.911Z"}],"details":{"listingId":"a18f33fe-43ad-4e16-8e3d-8c1214522479","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"helderberto","slug":"caveman","github":{"repo":"helderberto/agent-skills","stars":8,"topics":["agent-skills","ai","ai-tools","antigravity","claude-code","cursor","developer-tools","gemini-cli","markdown","plugin","sdlc","skills","tracer-bullet"],"license":"mit","html_url":"https://github.com/helderberto/agent-skills","pushed_at":"2026-05-14T11:37:47Z","description":"My personal SDLC toolbelt for AI coding agents — PRD to ship.","skill_md_sha":"85770a38992a7c74d2b3467b03fe5bd4b1287fe6","skill_md_path":"skills/caveman/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/helderberto/agent-skills/tree/main/skills/caveman"},"layout":"multi","source":"github","category":"agent-skills","frontmatter":{"name":"caveman","description":"Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says \"caveman mode\", \"talk like caveman\", \"use caveman\", \"less tokens\", \"be brief\", or invokes /caveman."},"skills_sh_url":"https://skills.sh/helderberto/agent-skills/caveman"},"updatedAt":"2026-05-18T19:09:11.911Z"}}