{"id":"a170d9d3-35fb-4df3-92bb-d4503edccf75","shortId":"zgj4tn","kind":"skill","title":"bdistill-behavioral-xray","tagline":"X-ray any AI model's behavioral patterns — refusal boundaries, hallucination tendencies, reasoning style, formatting defaults. No API key needed.","description":"# Behavioral X-Ray\n\nSystematically probe an AI model's behavioral patterns and generate a visual report. The AI agent probes *itself* — no API key or external setup needed.\n\n## Overview\n\nbdistill's Behavioral X-Ray runs 30 carefully designed probe questions across 6 dimensions, auto-tags each response with behavioral metadata, and compiles results into a styled HTML report with radar charts and actionable insights.\n\nUse it to understand your model before building with it, compare models for task selection, or track behavioral drift over time.\n\n## When to Use This Skill\n\n- Use when you want to understand how your AI model actually behaves (not how it claims to)\n- Use when choosing between models for a specific task\n- Use when debugging unexpected refusals, hallucinations, or formatting issues\n- Use for compliance auditing — documenting model behavior at deployment boundaries\n- Use for red team assessments — systematic boundary mapping across safety dimensions\n\n## How It Works\n\n### Step 1: Install\n\n```bash\npip install bdistill\nclaude mcp add bdistill -- bdistill-mcp   # Claude Code\n```\n\nFor other tools, add bdistill-mcp as an MCP server in your project config.\n\n### Step 2: Run the probe\n\nIn Claude Code:\n```\n/xray                          # Full behavioral probe (30 questions)\n/xray --dimensions refusal     # Probe just one dimension\n/xray-report                   # Generate report from completed probe\n```\n\nIn any tool with MCP:\n```\n\"X-ray your behavioral patterns\"\n\"Test your refusal boundaries\"\n\"Generate a behavioral report\"\n```\n\n## Probe Dimensions\n\n| Dimension | What it measures |\n|-----------|-----------------|\n| **tool_use** | When does it call tools vs. answer from knowledge? |\n| **refusal** | Where does it draw safety boundaries? Does it over-refuse? |\n| **formatting** | Lists vs. prose? Code blocks? Length calibration? |\n| **reasoning** | Does it show chain-of-thought? Handle trick questions? |\n| **persona** | Identity, tone matching, composure under hostility |\n| **grounding** | Hallucination resistance, fabrication traps, knowledge limits |\n\n## Output\n\nA styled HTML report showing:\n- Refusal rate, hedge rate, chain-of-thought usage\n- Per-dimension breakdown with bar charts\n- Notable response examples with behavioral tags\n- Actionable insights (e.g., \"you already show CoT 85% of the time, no need to prompt for it\")\n\n## Best Practices\n\n- Answer probe questions honestly — the value is in authentic behavioral data\n- Run probes on the same model periodically to track behavioral drift\n- Compare reports across models to make informed selection decisions\n- Use adversarial knowledge extraction (`/distill --adversarial`) alongside behavioral probes for complete model profiling\n\n## Related Skills\n\n- `@bdistill-knowledge-extraction` - Extract structured domain knowledge from any AI model\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":["bdistill","behavioral","xray","antigravity","awesome","skills","sickn33","agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding"],"capabilities":["skill","source-sickn33","skill-bdistill-behavioral-xray","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/bdistill-behavioral-xray","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 · 34928 github stars · SKILL.md body (3,152 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":"2026-04-24T18:50:35.899Z","embedding":null,"createdAt":"2026-04-18T21:33:29.382Z","updatedAt":"2026-04-24T18:50:35.899Z","lastSeenAt":"2026-04-24T18:50:35.899Z","tsv":"'/distill':399 '/xray':217,223 '/xray-report':230 '1':179 '2':210 '30':63,221 '6':69 '85':352 'across':68,172,388 'action':91,345 'actual':129 'add':187,197 'adversari':396,400 'agent':45 'ai':9,33,44,127,420 'alongsid':401 'alreadi':349 'answer':269,364 'api':23,49 'ask':455 'assess':168 'audit':157 'authent':372 'auto':72 'auto-tag':71 'bar':337 'bash':181 'bdistil':2,56,184,188,190,199,411 'bdistill-behavioral-xray':1 'bdistill-knowledge-extract':410 'bdistill-mcp':189,198 'behav':130 'behavior':3,12,26,36,58,77,110,160,219,245,253,343,373,384,402 'best':362 'block':289 'boundari':15,163,170,250,278,463 'breakdown':335 'build':100 'calibr':291 'call':266 'care':64 'chain':297,328 'chain-of-thought':296,327 'chart':89,338 'choos':138 'claim':134 'clarif':457 'claud':185,192,215 'clear':430 'code':193,216,288 'compar':103,386 'compil':80 'complet':234,405 'complianc':156 'composur':307 'config':208 'cot':351 'criteria':466 'data':374 'debug':147 'decis':394 'default':21 'deploy':162 'describ':434 'design':65 'dimens':70,174,224,229,256,257,334 'document':158 'domain':416 'draw':276 'drift':111,385 'e.g':347 'environ':446 'environment-specif':445 'exampl':341 'expert':451 'extern':52 'extract':398,413,414 'fabric':313 'format':20,152,284 'full':218 'generat':39,231,251 'ground':310 'hallucin':16,150,311 'handl':300 'hedg':325 'honest':367 'hostil':309 'html':85,320 'ident':304 'inform':392 'input':460 'insight':92,346 'instal':180,183 'issu':153 'key':24,50 'knowledg':271,315,397,412,417 'length':290 'limit':316,422 'list':285 'make':391 'map':171 'match':306,431 'mcp':186,191,200,203,240 'measur':260 'metadata':78 'miss':468 'model':10,34,98,104,128,140,159,380,389,406,421 'need':25,54,357 'notabl':339 'one':228 'output':317,440 'over-refus':281 'overview':55 'pattern':13,37,246 'per':333 'per-dimens':332 'period':381 'permiss':461 'persona':303 'pip':182 'practic':363 'probe':31,46,66,213,220,226,235,255,365,376,403 'profil':407 'project':207 'prompt':359 'prose':287 'question':67,222,302,366 'radar':88 'rate':324,326 'ray':7,29,61,243 'reason':18,292 'red':166 'refus':14,149,225,249,272,283,323 'relat':408 'report':42,86,232,254,321,387 'requir':459 'resist':312 'respons':75,340 'result':81 'review':452 'run':62,211,375 'safeti':173,277,462 'scope':433 'select':107,393 'server':204 'setup':53 'show':295,322,350 'skill':118,409,425 'skill-bdistill-behavioral-xray' 'source-sickn33' 'specif':143,447 'step':178,209 'stop':453 'structur':415 'style':19,84,319 'substitut':443 'success':465 'systemat':30,169 'tag':73,344 'task':106,144,429 'team':167 'tendenc':17 'test':247,449 'thought':299,330 'time':113,355 'tone':305 'tool':196,238,261,267 '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' 'track':109,383 'trap':314 'treat':438 'trick':301 'understand':96,124 'unexpect':148 'usag':331 'use':93,116,119,136,145,154,164,262,395,423 'valid':448 'valu':369 'visual':41 'vs':268,286 'want':122 'work':177 'x':6,28,60,242 'x-ray':5,27,59,241 'xray':4","prices":[{"id":"87159b3c-21be-44e0-959c-3715762d1f41","listingId":"a170d9d3-35fb-4df3-92bb-d4503edccf75","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":"2026-04-18T21:33:29.382Z"}],"sources":[{"listingId":"a170d9d3-35fb-4df3-92bb-d4503edccf75","source":"github","sourceId":"sickn33/antigravity-awesome-skills/bdistill-behavioral-xray","sourceUrl":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/bdistill-behavioral-xray","isPrimary":false,"firstSeenAt":"2026-04-18T21:33:29.382Z","lastSeenAt":"2026-04-24T18:50:35.899Z"}],"details":{"listingId":"a170d9d3-35fb-4df3-92bb-d4503edccf75","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"sickn33","slug":"bdistill-behavioral-xray","github":{"repo":"sickn33/antigravity-awesome-skills","stars":34928,"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":"c4fa9227749f9306f1c89b0eda8789798156cb02","skill_md_path":"skills/bdistill-behavioral-xray/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/bdistill-behavioral-xray"},"layout":"multi","source":"github","category":"antigravity-awesome-skills","frontmatter":{"name":"bdistill-behavioral-xray","description":"X-ray any AI model's behavioral patterns — refusal boundaries, hallucination tendencies, reasoning style, formatting defaults. No API key needed."},"skills_sh_url":"https://skills.sh/sickn33/antigravity-awesome-skills/bdistill-behavioral-xray"},"updatedAt":"2026-04-24T18:50:35.899Z"}}