{"id":"3cf31291-3ec5-4bae-9a08-93763f249416","shortId":"VFtwWG","kind":"skill","title":"audit-context-building","tagline":"Enables ultra-granular, line-by-line code analysis to build deep architectural context before vulnerability or bug finding.","description":"# Deep Context Builder Skill (Ultra-Granular Pure Context Mode)\n\n## 1. Purpose\n\nThis skill governs **how Claude thinks** during the context-building phase of an audit.\n\nWhen active, Claude will:\n- Perform **line-by-line / block-by-block** code analysis by default.\n- Apply **First Principles**, **5 Whys**, and **5 Hows** at micro scale.\n- Continuously link insights → functions → modules → entire system.\n- Maintain a stable, explicit mental model that evolves with new evidence.\n- Identify invariants, assumptions, flows, and reasoning hazards.\n\nThis skill defines a structured analysis format (see Example: Function Micro-Analysis below) and runs **before** the vulnerability-hunting phase.\n\n---\n\n## When to Use\nUse when:\n- Deep comprehension is needed before bug or vulnerability discovery.\n- You want bottom-up understanding instead of high-level guessing.\n- Reducing hallucinations, contradictions, and context loss is critical.\n- Preparing for security auditing, architecture review, or threat modeling.\n\nDo **not** use for:\n- Vulnerability findings\n- Fix recommendations\n- Exploit reasoning\n- Severity/impact rating\n\n---\n\n## 3. How This Skill Behaves\n\nWhen active, Claude will:\n- Default to **ultra-granular analysis** of each block and line.\n- Apply micro-level First Principles, 5 Whys, and 5 Hows.\n- Build and refine a persistent global mental model.\n- Update earlier assumptions when contradicted (\"Earlier I thought X; now Y.\").\n- Periodically anchor summaries to maintain stable context.\n- Avoid speculation; express uncertainty explicitly when needed.\n\nGoal: **deep, accurate understanding**, not conclusions.\n\n---\n\n## Rationalizations (Do Not Skip)\n\n| Rationalization | Why It's Wrong | Required Action |\n|-----------------|----------------|-----------------|\n| \"I get the gist\" | Gist-level understanding misses edge cases | Line-by-line analysis required |\n| \"This function is simple\" | Simple functions compose into complex bugs | Apply 5 Whys anyway |\n| \"I'll remember this invariant\" | You won't. Context degrades. | Write it down explicitly |\n| \"External call is probably fine\" | External = adversarial until proven otherwise | Jump into code or model as hostile |\n| \"I can skip this helper\" | Helpers contain assumptions that propagate | Trace the full call chain |\n| \"This is taking too long\" | Rushed context = hallucinated vulnerabilities later | Slow is fast |\n\n---\n\n## 4. Phase 1 — Initial Orientation (Bottom-Up Scan)\n\nBefore deep analysis, Claude performs a minimal mapping:\n\n1. Identify major modules/files/contracts.\n2. Note obvious public/external entrypoints.\n3. Identify likely actors (users, owners, relayers, oracles, other contracts).\n4. Identify important storage variables, dicts, state structs, or cells.\n5. Build a preliminary structure without assuming behavior.\n\nThis establishes anchors for detailed analysis.\n\n---\n\n## 5. Phase 2 — Ultra-Granular Function Analysis (Default Mode)\n\nEvery non-trivial function receives full micro analysis.\n\n### 5.1 Per-Function Microstructure Checklist\n\nFor each function:\n\n1. **Purpose**\n   - Why the function exists and its role in the system.\n\n2. **Inputs & Assumptions**\n   - Parameters and implicit inputs (state, sender, env).\n   - Preconditions and constraints.\n\n3. **Outputs & Effects**\n   - Return values.\n   - State/storage writes.\n   - Events/messages.\n   - External interactions.\n\n4. **Block-by-Block / Line-by-Line Analysis**\n   For each logical block:\n   - What it does.\n   - Why it appears here (ordering logic).\n   - What assumptions it relies on.\n   - What invariants it establishes or maintains.\n   - What later logic depends on it.\n\n   Apply per-block:\n   - **First Principles**\n   - **5 Whys**\n   - **5 Hows**\n\n---\n\n### 5.2 Cross-Function & External Flow Analysis\n*(Full Integration of Jump-Into-External-Code Rule)*\n\nWhen encountering calls, **continue the same micro-first analysis across boundaries.**\n\n#### Internal Calls\n- Jump into the callee immediately.\n- Perform block-by-block analysis of relevant code.\n- Track flow of data, assumptions, and invariants:\n  caller → callee → return → caller.\n- Note if callee logic behaves differently in this specific call context.\n\n#### External Calls — Two Cases\n\n**Case A — External Call to a Contract Whose Code Exists in the Codebase**\nTreat as an internal call:\n- Jump into the target contract/function.\n- Continue block-by-block micro-analysis.\n- Propagate invariants and assumptions seamlessly.\n- Consider edge cases based on the *actual* code, not a black-box guess.\n\n**Case B — External Call Without Available Code (True External / Black Box)**\nAnalyze as adversarial:\n- Describe payload/value/gas or parameters sent.\n- Identify assumptions about the target.\n- Consider all outcomes:\n  - revert\n  - incorrect/strange return values\n  - unexpected state changes\n  - misbehavior\n  - reentrancy (if applicable)\n\n#### Continuity Rule\nTreat the entire call chain as **one continuous execution flow**.\nNever reset context.\nAll invariants, assumptions, and data dependencies must propagate across calls.\n\n---\n\n### 5.3 Complete Analysis Example\n\nSee FUNCTION_MICRO_ANALYSIS_EXAMPLE.md for a complete walkthrough demonstrating:\n- Full micro-analysis of a DEX swap function\n- Application of First Principles, 5 Whys, and 5 Hows\n- Block-by-block analysis with invariants and assumptions\n- Cross-function dependency mapping\n- Risk analysis for external interactions\n\nThis example demonstrates the level of depth and structure required for all analyzed functions.\n\n---\n\n### 5.4 Output Requirements\n\nWhen performing ultra-granular analysis, Claude MUST structure output following the format defined in OUTPUT_REQUIREMENTS.md.\n\nKey requirements:\n- **Purpose** (2-3 sentences minimum)\n- **Inputs & Assumptions** (all parameters, preconditions, trust assumptions)\n- **Outputs & Effects** (returns, state writes, external calls, events, postconditions)\n- **Block-by-Block Analysis** (What, Why here, Assumptions, First Principles/5 Whys/5 Hows)\n- **Cross-Function Dependencies** (internal calls, external calls with risk analysis, shared state)\n\nQuality thresholds:\n- Minimum 3 invariants per function\n- Minimum 5 assumptions documented\n- Minimum 3 risk considerations for external interactions\n- At least 1 First Principles application\n- At least 3 combined 5 Whys/5 Hows applications\n\n---\n\n### 5.5 Completeness Checklist\n\nBefore concluding micro-analysis of a function, verify against the COMPLETENESS_CHECKLIST.md:\n\n- **Structural Completeness**: All required sections present (Purpose, Inputs, Outputs, Block-by-Block, Dependencies)\n- **Content Depth**: Minimum thresholds met (invariants, assumptions, risk analysis, First Principles)\n- **Continuity & Integration**: Cross-references, propagated assumptions, invariant couplings\n- **Anti-Hallucination**: Line number citations, no vague statements, evidence-based claims\n\nAnalysis is complete when all checklist items are satisfied and no unresolved \"unclear\" items remain.\n\n---\n\n## 6. Phase 3 — Global System Understanding\n\nAfter sufficient micro-analysis:\n\n1. **State & Invariant Reconstruction**\n   - Map reads/writes of each state variable.\n   - Derive multi-function and multi-module invariants.\n\n2. **Workflow Reconstruction**\n   - Identify end-to-end flows (deposit, withdraw, lifecycle, upgrades).\n   - Track how state transforms across these flows.\n   - Record assumptions that persist across steps.\n\n3. **Trust Boundary Mapping**\n   - Actor → entrypoint → behavior.\n   - Identify untrusted input paths.\n   - Privilege changes and implicit role expectations.\n\n4. **Complexity & Fragility Clustering**\n   - Functions with many assumptions.\n   - High branching logic.\n   - Multi-step dependencies.\n   - Coupled state changes across modules.\n\nThese clusters help guide the vulnerability-hunting phase.\n\n---\n\n## 7. Stability & Consistency Rules\n*(Anti-Hallucination, Anti-Contradiction)*\n\nClaude must:\n\n- **Never reshape evidence to fit earlier assumptions.**\n  When contradicted:\n  - Update the model.\n  - State the correction explicitly.\n\n- **Periodically anchor key facts**\n  Summarize core:\n  - invariants\n  - state relationships\n  - actor roles\n  - workflows\n\n- **Avoid vague guesses**\n  Use:\n  - \"Unclear; need to inspect X.\"\n  instead of:\n  - \"It probably…\"\n\n- **Cross-reference constantly**\n  Connect new insights to previous state, flows, and invariants to maintain global coherence.\n\n---\n\n## 8. Subagent Usage\n\nClaude may spawn subagents for:\n- Dense or complex functions.\n- Long data-flow or control-flow chains.\n- Cryptographic / mathematical logic.\n- Complex state machines.\n- Multi-module workflow reconstruction.\n\nUse the **`function-analyzer`** agent for per-function deep analysis.\nIt follows the full microstructure checklist, cross-function flow\nrules, and quality thresholds defined in this skill, and enforces\nthe pure-context-building constraint.\n\nSubagents must:\n- Follow the same micro-first rules.\n- Return summaries that Claude integrates into its global model.\n\n---\n\n## 9. Relationship to Other Phases\n\nThis skill runs **before**:\n- Vulnerability discovery\n- Classification / triage\n- Report writing\n- Impact modeling\n- Exploit reasoning\n\nIt exists solely to build:\n- Deep understanding\n- Stable context\n- System-level clarity\n\n---\n\n## 10. Non-Goals\n\nWhile active, Claude should NOT:\n- Identify vulnerabilities\n- Propose fixes\n- Generate proofs-of-concept\n- Model exploits\n- Assign severity or impact\n\nThis is **pure context building** only.\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":["audit","context","building","antigravity","awesome","skills","sickn33","agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding"],"capabilities":["skill","source-sickn33","skill-audit-context-building","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/audit-context-building","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 · 34964 github stars · SKILL.md body (9,779 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":"2026-04-25T00:50:28.941Z","embedding":null,"createdAt":"2026-04-18T21:31:34.265Z","updatedAt":"2026-04-25T00:50:28.941Z","lastSeenAt":"2026-04-25T00:50:28.941Z","tsv":"'-3':794 '1':35,355,370,441,859,959 '10':1240 '2':374,415,453,793,978 '3':182,379,466,842,851,865,950,1004 '4':353,389,476,1021 '5':72,75,208,211,291,399,413,522,524,733,736,847,867 '5.1':432 '5.2':526 '5.3':709 '5.4':771 '5.5':871 '6':948 '7':1050 '8':1120 '9':1208 'accur':248 'across':552,707,995,1002,1039 'action':262 'activ':53,188,1245 'actor':382,1008,1087 'actual':638 'adversari':314,659 'agent':1157 'analysi':14,66,110,117,196,278,364,412,420,431,485,532,551,566,626,711,723,742,753,779,817,836,878,908,933,958,1163 'analyz':657,769,1156 'anchor':233,409,1079 'anti':921,1055,1058 'anti-contradict':1057 'anti-hallucin':920,1054 'anyway':293 'appear':495 'appli':69,202,290,516 'applic':683,729,862,870 'architectur':18,165 'ask':1303 'assign':1260 'assum':405 'assumpt':100,223,332,455,500,574,630,666,701,746,798,803,821,848,906,917,999,1028,1068 'audit':2,51,164 'audit-context-build':1 'avail':651 'avoid':239,1090 'b':647 'base':635,931 'behav':186,585 'behavior':406,1010 'black':643,655 'black-box':642 'block':62,64,199,478,480,489,519,563,565,621,623,739,741,814,816,896,898 'block-by-block':61,477,562,620,738,813,895 'bottom':144,359 'bottom-up':143,358 'boundari':553,1006,1311 'box':644,656 'branch':1030 'bug':23,137,289 'build':4,16,47,213,400,1188,1231,1268 'builder':27 'call':309,338,544,555,590,593,599,613,649,689,708,810,831,833 'calle':559,578,583 'caller':577,580 'case':273,595,596,634,646 'cell':398 'chain':339,690,1140 'chang':679,1016,1038 'checklist':437,873,938,1169 'citat':925 'claim':932 'clarif':1305 'clariti':1239 'classif':1219 'claud':41,54,189,365,780,1060,1123,1202,1246 'clear':1278 'cluster':1024,1042 'code':13,65,320,540,569,604,639,652 'codebas':608 'coher':1119 'combin':866 'complet':710,717,872,887,935 'completeness_checklist.md':885 'complex':288,1022,1130,1144 'compos':286 'comprehens':133 'concept':1257 'conclud':875 'conclus':251 'connect':1107 'consid':632,670 'consider':853 'consist':1052 'constant':1106 'constraint':465,1189 'contain':331 'content':900 'context':3,19,26,33,46,157,238,302,346,591,698,1187,1235,1267 'context-build':45 'continu':80,545,619,684,693,911 'contract':388,602 'contract/function':618 'contradict':155,225,1059,1070 'control':1138 'control-flow':1137 'core':1083 'correct':1076 'coupl':919,1036 'criteria':1314 'critic':160 'cross':528,748,827,914,1104,1171 'cross-funct':527,747,826,1170 'cross-refer':913,1103 'cryptograph':1141 'data':573,703,1134 'data-flow':1133 'deep':17,25,132,247,363,1162,1232 'default':68,191,421 'defin':107,787,1178 'degrad':303 'demonstr':719,759 'dens':1128 'depend':513,704,750,829,899,1035 'deposit':987 'depth':763,901 'deriv':969 'describ':660,1282 'detail':411 'dex':726 'dict':394 'differ':586 'discoveri':140,1218 'document':849 'earlier':222,226,1067 'edg':272,633 'effect':468,805 'enabl':5 'encount':543 'end':983,985 'end-to-end':982 'enforc':1183 'entir':85,688 'entrypoint':378,1009 'env':462 'environ':1294 'environment-specif':1293 'establish':408,507 'event':811 'events/messages':473 'everi':423 'evid':97,930,1064 'evidence-bas':929 'evolv':94 'exampl':113,712,758 'execut':694 'exist':446,605,1228 'expect':1020 'expert':1299 'explicit':90,243,307,1077 'exploit':178,1225,1259 'express':241 'extern':308,313,474,530,539,592,598,648,654,755,809,832,855 'fact':1081 'fast':352 'find':24,175 'fine':312 'first':70,206,520,550,731,822,860,909,1197 'fit':1066 'fix':176,1252 'flow':101,531,571,695,986,997,1113,1135,1139,1173 'follow':784,1165,1192 'format':111,786 'fragil':1023 'full':337,429,533,720,1167 'function':83,114,281,285,419,427,435,440,445,529,728,749,770,828,845,881,972,1025,1131,1155,1161,1172 'function-analyz':1154 'function_micro_analysis_example.md':714 'generat':1253 'get':264 'gist':266,268 'gist-level':267 'global':218,951,1118,1206 'goal':246,1243 'govern':39 'granular':8,31,195,418,778 'guess':152,645,1092 'guid':1044 'hallucin':154,347,922,1056 'hazard':104 'help':1043 'helper':329,330 'high':150,1029 'high-level':149 'hostil':324 'how':76,212,525,737,825,869 'hunt':125,1048 'identifi':98,371,380,390,665,981,1011,1249 'immedi':560 'impact':1223,1263 'implicit':458,1018 'import':391 'incorrect/strange':674 'initi':356 'input':454,459,797,893,1013,1308 'insight':82,1109 'inspect':1097 'instead':147,1099 'integr':534,912,1203 'interact':475,756,856 'intern':554,612,830 'invari':99,298,505,576,628,700,744,843,905,918,961,977,1084,1115 'item':939,946 'jump':318,537,556,614 'jump-into-external-cod':536 'key':790,1080 'later':349,511 'least':858,864 'level':151,205,269,761,1238 'lifecycl':989 'like':381 'limit':1270 'line':10,12,58,60,201,275,277,482,484,923 'line-by-lin':9,57,274,481 'link':81 'll':295 'logic':488,498,512,584,1031,1143 'long':344,1132 'loss':158 'machin':1146 'maintain':87,236,509,1117 'major':372 'mani':1027 'map':369,751,963,1007 'match':1279 'mathemat':1142 'may':1124 'mental':91,219 'met':904 'micro':78,116,204,430,549,625,722,877,957,1196 'micro-analysi':115,624,721,876,956 'micro-first':548,1195 'micro-level':203 'microstructur':436,1168 'minim':368 'minimum':796,841,846,850,902 'misbehavior':680 'miss':271,1316 'mode':34,422 'model':92,169,220,322,1073,1207,1224,1258 'modul':84,976,1040,1149 'modules/files/contracts':373 'multi':971,975,1033,1148 'multi-funct':970 'multi-modul':974,1147 'multi-step':1032 'must':705,781,1061,1191 'need':135,245,1095 'never':696,1062 'new':96,1108 'non':425,1242 'non-goal':1241 'non-trivi':424 'note':375,581 'number':924 'obvious':376 'one':692 'oracl':386 'order':497 'orient':357 'otherwis':317 'outcom':672 'output':467,772,783,804,894,1288 'output_requirements.md':789 'owner':384 'paramet':456,663,800 'path':1014 'payload/value/gas':661 'per':434,518,844,1160 'per-block':517 'per-funct':433,1159 'perform':56,366,561,775 'period':232,1078 'permiss':1309 'persist':217,1001 'phase':48,126,354,414,949,1049,1212 'postcondit':812 'precondit':463,801 'preliminari':402 'prepar':161 'present':891 'previous':1111 'principl':71,207,521,732,861,910 'principles/5':823 'privileg':1015 'probabl':311,1102 'proof':1255 'proofs-of-concept':1254 'propag':334,627,706,916 'propos':1251 'proven':316 'public/external':377 'pure':32,1186,1266 'pure-context-build':1185 'purpos':36,442,792,892 'qualiti':839,1176 'rate':181 'ration':252,256 'reads/writes':964 'reason':103,179,1226 'receiv':428 'recommend':177 'reconstruct':962,980,1151 'record':998 'reduc':153 'reentranc':681 'refer':915,1105 'refin':215 'relationship':1086,1209 'relay':385 'relev':568 'reli':502 'remain':947 'rememb':296 'report':1221 'requir':261,279,766,773,791,889,1307 'reset':697 'reshap':1063 'return':469,579,675,806,1199 'revert':673 'review':166,1300 'risk':752,835,852,907 'role':449,1019,1088 'rule':541,685,1053,1174,1198 'run':120,1215 'rush':345 'safeti':1310 'satisfi':941 'scale':79 'scan':361 'scope':1281 'seamless':631 'section':890 'secur':163 'see':112,713 'sender':461 'sent':664 'sentenc':795 'sever':1261 'severity/impact':180 'share':837 'simpl':283,284 'skill':28,38,106,185,1181,1214,1273 'skill-audit-context-building' 'skip':255,327 'slow':350 'sole':1229 'source-sickn33' 'spawn':1125 'specif':589,1295 'specul':240 'stabil':1051 'stabl':89,237,1234 'state':395,460,678,807,838,960,967,993,1037,1074,1085,1112,1145 'state/storage':471 'statement':928 'step':1003,1034 'stop':1301 'storag':392 'struct':396 'structur':109,403,765,782,886 'subag':1121,1126,1190 'substitut':1291 'success':1313 'suffici':955 'summar':1082 'summari':234,1200 'swap':727 'system':86,452,952,1237 'system-level':1236 'take':342 'target':617,669 'task':1277 'test':1297 'think':42 'thought':228 'threat':168 'threshold':840,903,1177 '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' 'trace':335 'track':570,991 'transform':994 'treat':609,686,1286 'triag':1220 'trivial':426 'true':653 'trust':802,1005 'two':594 'ultra':7,30,194,417,777 'ultra-granular':6,29,193,416,776 'uncertainti':242 'unclear':945,1094 'understand':146,249,270,953,1233 'unexpect':677 'unresolv':944 'untrust':1012 'updat':221,1071 'upgrad':990 'usag':1122 'use':129,130,172,1093,1152,1271 'user':383 'vagu':927,1091 'valid':1296 'valu':470,676 'variabl':393,968 'verifi':882 'vulner':21,124,139,174,348,1047,1217,1250 'vulnerability-hunt':123,1046 'walkthrough':718 'want':142 'whose':603 'whys':73,209,292,523,734 'whys/5':824,868 'withdraw':988 'without':404,650 'won':300 'workflow':979,1089,1150 'write':304,472,808,1222 'wrong':260 'x':229,1098 'y':231","prices":[{"id":"5db4963e-ce37-4ee8-bd09-16fa47859d75","listingId":"3cf31291-3ec5-4bae-9a08-93763f249416","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":"2026-04-18T21:31:34.265Z"}],"sources":[{"listingId":"3cf31291-3ec5-4bae-9a08-93763f249416","source":"github","sourceId":"sickn33/antigravity-awesome-skills/audit-context-building","sourceUrl":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/audit-context-building","isPrimary":false,"firstSeenAt":"2026-04-18T21:31:34.265Z","lastSeenAt":"2026-04-25T00:50:28.941Z"}],"details":{"listingId":"3cf31291-3ec5-4bae-9a08-93763f249416","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"sickn33","slug":"audit-context-building","github":{"repo":"sickn33/antigravity-awesome-skills","stars":34964,"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":"0f955090e254309a169ed833dba6afea042c62a9","skill_md_path":"skills/audit-context-building/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/audit-context-building"},"layout":"multi","source":"github","category":"antigravity-awesome-skills","frontmatter":{"name":"audit-context-building","description":"Enables ultra-granular, line-by-line code analysis to build deep architectural context before vulnerability or bug finding."},"skills_sh_url":"https://skills.sh/sickn33/antigravity-awesome-skills/audit-context-building"},"updatedAt":"2026-04-25T00:50:28.941Z"}}