{"id":"1db77a01-3ac2-4c49-ba6a-6f39544c9208","shortId":"ydWhXD","kind":"skill","title":"vibeguard","tagline":"Lightweight anti-hallucination workflow for task kickoff, review prioritization, and regression retrospectives. Use when the user asks for guardrails, task contracts, risk scoring, or review templates.","description":"# VibeGuard\n\nLightweight VibeGuard for everyday use inside Claude Arsenal.\n\nThis skill helps with three moments where AI-assisted work usually drifts:\n- before implementation starts\n- while review findings are being prioritized\n- after regressions or avoidable mistakes happen\n\n## What This Skill Includes\n\n- A task contract checklist for scoping work before coding\n- A scoring matrix for prioritizing findings with evidence\n- A weekly review template for regression and guardrail retrospectives\n\n## Hard Boundaries\n\nThis skill is intentionally lightweight.\n\nIt does:\n- guide task kickoff\n- structure review output\n- make risk tradeoffs explicit\n\nIt does not:\n- install hooks\n- run guard scripts automatically\n- patch global Claude or Codex configuration\n- claim that full VibeGuard enforcement is active\n\nIf the user asks for automated interception, repo-level rules, or environment setup, escalate to the full VibeGuard repository and tooling.\n\n## When To Use It\n\nTrigger this skill when the user asks for:\n- anti-hallucination guardrails\n- task startup checks\n- review scoring or triage\n- regression prevention\n- retrospective templates\n- \"vibeguard\" by name\n\n## Workflow\n\n### 1. Start With The Task Contract\n\nOpen [`references/task-contract.yaml`](./references/task-contract.yaml) and confirm:\n- goal\n- source of truth\n- acceptance criteria\n- scope\n\nDo not move into implementation until these are concrete.\n\n### 2. Score Findings Before Acting\n\nOpen [`references/scoring-matrix.md`](./references/scoring-matrix.md) and score each finding on:\n- impact\n- effort\n- risk\n- confidence\n\nUse the score to separate urgent fixes from weak guesses.\n\n### 3. Pick The Right Delivery Mode\n\n- 1-2 files: implement directly once the contract is clear\n- 3-5 files: write a short spec or step plan first\n- 6+ files: produce a full design/spec and staged execution plan\n\n### 4. Review The Failure, Not Just The Symptom\n\nIf something regressed, identify which defense failed:\n- scope control\n- source-of-truth validation\n- verification depth\n- review prioritization\n- missing guardrail\n\nThen capture the follow-up in [`references/review-template.md`](./references/review-template.md).\n\n## Expected Outputs\n\nDepending on the request, produce one of these:\n- a filled task contract\n- a scored findings table with priorities\n- a short regression review or weekly retrospective\n\n## Reference Files\n\n- [`references/task-contract.yaml`](./references/task-contract.yaml) - kickoff checklist\n- [`references/scoring-matrix.md`](./references/scoring-matrix.md) - prioritization model\n- [`references/review-template.md`](./references/review-template.md) - retrospective template","tags":["vibeguard","claude","arsenal","majiayu000","agent-skills","ai-agents","ai-coding-assistant","automation","claude-code","code-review","developer-tools","devops"],"capabilities":["skill","source-majiayu000","skill-vibeguard","topic-agent-skills","topic-ai-agents","topic-ai-coding-assistant","topic-automation","topic-claude","topic-claude-code","topic-code-review","topic-developer-tools","topic-devops","topic-productivity","topic-prompt-engineering","topic-python"],"categories":["claude-arsenal"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/majiayu000/claude-arsenal/vibeguard","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add majiayu000/claude-arsenal","source_repo":"https://github.com/majiayu000/claude-arsenal","install_from":"skills.sh"}},"qualityScore":"0.464","qualityRationale":"deterministic score 0.46 from registry signals: · indexed on github topic:agent-skills · 29 github stars · SKILL.md body (2,653 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":"2026-05-01T07:01:17.513Z","embedding":null,"createdAt":"2026-04-18T22:24:36.297Z","updatedAt":"2026-05-01T07:01:17.513Z","lastSeenAt":"2026-05-01T07:01:17.513Z","tsv":"'-2':251 '-5':261 '/references/review-template.md':317,356 '/references/scoring-matrix.md':224,352 '/references/task-contract.yaml':198,348 '1':190,250 '2':217 '3':244,260 '4':281 '6':271 'accept':205 'act':221 'activ':136 'ai':46 'ai-assist':45 'anti':4,172 'anti-hallucin':3,171 'arsenal':37 'ask':19,140,169 'assist':47 'autom':142 'automat':123 'avoid':63 'boundari':97 'captur':310 'check':177 'checklist':73,350 'claim':130 'claud':36,126 'clear':259 'code':78 'codex':128 'concret':216 'confid':233 'configur':129 'confirm':200 'contract':23,72,195,257,331 'control':297 'criteria':206 'defens':294 'deliveri':248 'depend':320 'depth':304 'design/spec':276 'direct':254 'drift':50 'effort':231 'enforc':134 'environ':149 'escal':151 'everyday':33 'evid':86 'execut':279 'expect':318 'explicit':114 'fail':295 'failur':284 'file':252,262,272,346 'fill':329 'find':56,84,219,228,334 'first':270 'fix':240 'follow':313 'follow-up':312 'full':132,154,275 'global':125 'goal':201 'guard':121 'guardrail':21,94,174,308 'guess':243 'guid':105 'hallucin':5,173 'happen':65 'hard':96 'help':40 'hook':119 'identifi':292 'impact':230 'implement':52,212,253 'includ':69 'insid':35 'instal':118 'intent':101 'intercept':143 'kickoff':9,107,349 'level':146 'lightweight':2,30,102 'make':111 'matrix':81 'miss':307 'mistak':64 'mode':249 'model':354 'moment':43 'move':210 'name':188 'one':325 'open':196,222 'output':110,319 'patch':124 'pick':245 'plan':269,280 'prevent':183 'priorit':11,59,83,306,353 'prioriti':337 'produc':273,324 'refer':345 'references/review-template.md':316,355 'references/scoring-matrix.md':223,351 'references/task-contract.yaml':197,347 'regress':13,61,92,182,291,340 'repo':145 'repo-level':144 'repositori':156 'request':323 'retrospect':14,95,184,344,357 'review':10,27,55,89,109,178,282,305,341 'right':247 'risk':24,112,232 'rule':147 'run':120 'scope':75,207,296 'score':25,80,179,218,226,236,333 'script':122 'separ':238 'setup':150 'short':265,339 'skill':39,68,99,165 'skill-vibeguard' 'someth':290 'sourc':202,299 'source-majiayu000' 'source-of-truth':298 'spec':266 'stage':278 'start':53,191 'startup':176 'step':268 'structur':108 'symptom':288 'tabl':335 'task':8,22,71,106,175,194,330 'templat':28,90,185,358 'three':42 'tool':158 'topic-agent-skills' 'topic-ai-agents' 'topic-ai-coding-assistant' 'topic-automation' 'topic-claude' 'topic-claude-code' 'topic-code-review' 'topic-developer-tools' 'topic-devops' 'topic-productivity' 'topic-prompt-engineering' 'topic-python' 'tradeoff':113 'triag':181 'trigger':163 'truth':204,301 'urgent':239 'use':15,34,161,234 'user':18,139,168 'usual':49 'valid':302 'verif':303 'vibeguard':1,29,31,133,155,186 'weak':242 'week':88,343 'work':48,76 'workflow':6,189 'write':263","prices":[{"id":"daeaeb0d-4fb1-48ce-b74c-f6de39bdcb19","listingId":"1db77a01-3ac2-4c49-ba6a-6f39544c9208","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"majiayu000","category":"claude-arsenal","install_from":"skills.sh"},"createdAt":"2026-04-18T22:24:36.297Z"}],"sources":[{"listingId":"1db77a01-3ac2-4c49-ba6a-6f39544c9208","source":"github","sourceId":"majiayu000/claude-arsenal/vibeguard","sourceUrl":"https://github.com/majiayu000/claude-arsenal/tree/main/skills/vibeguard","isPrimary":false,"firstSeenAt":"2026-04-18T22:24:36.297Z","lastSeenAt":"2026-05-01T07:01:17.513Z"}],"details":{"listingId":"1db77a01-3ac2-4c49-ba6a-6f39544c9208","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"majiayu000","slug":"vibeguard","github":{"repo":"majiayu000/claude-arsenal","stars":29,"topics":["agent-skills","ai-agents","ai-coding-assistant","automation","claude","claude-code","code-review","developer-tools","devops","productivity","prompt-engineering","python","software-development","typescript","workflows"],"license":"mit","html_url":"https://github.com/majiayu000/claude-arsenal","pushed_at":"2026-04-29T04:12:22Z","description":"52 production-ready Claude Code skills and 7 specialized agents for software development, DevOps, product workflows, and automation.","skill_md_sha":"3909f55fbaf8ebb670c9944905ceb87c76c8b320","skill_md_path":"skills/vibeguard/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/majiayu000/claude-arsenal/tree/main/skills/vibeguard"},"layout":"multi","source":"github","category":"claude-arsenal","frontmatter":{"name":"vibeguard","description":"Lightweight anti-hallucination workflow for task kickoff, review prioritization, and regression retrospectives. Use when the user asks for guardrails, task contracts, risk scoring, or review templates."},"skills_sh_url":"https://skills.sh/majiayu000/claude-arsenal/vibeguard"},"updatedAt":"2026-05-01T07:01:17.513Z"}}