{ "schemaVersion": "1.0", "item": { "slug": "defi-sniper", "name": "Defi Sniper", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/h4gen/defi-sniper", "canonicalUrl": "https://clawhub.ai/h4gen/defi-sniper", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/defi-sniper", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=defi-sniper", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "references/inspected-skills.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/defi-sniper" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/defi-sniper", "agentPageUrl": "https://openagent3.xyz/skills/defi-sniper/agent", "manifestUrl": "https://openagent3.xyz/skills/defi-sniper/agent.json", "briefUrl": "https://openagent3.xyz/skills/defi-sniper/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Purpose", "body": "Run a high-speed token opportunity workflow:\n\ndetect very early pool/token activity,\ntriage contract/market risk,\nverify social signal quality,\nexecute small, bounded entries when rules pass.\n\nThis is an orchestration skill. It coordinates upstream skills and explicit risk policy. It does not guarantee profit." }, { "title": "Required Installed Skills", "body": "minara (inspected latest: 1.1.9)\ntorchmarket (inspected latest: 4.2.7)\ntorchliquidationbot (inspected latest: 3.0.2)\n\nInstall/update:\n\nnpx -y clawhub@latest install minara\nnpx -y clawhub@latest install torchmarket\nnpx -y clawhub@latest install torchliquidationbot\nnpx -y clawhub@latest update --all" }, { "title": "Required Configuration and Credentials", "body": "Minimum:\n\nMINARA_API_KEY\nSOLANA_RPC_URL\n\nDepending on execution route:\n\nMinara signer path: Circle Wallet preferred, or chain private-key fallback per Minara docs.\nTorch vault path: VAULT_CREATOR and linked agent wallet for vault-routed operations.\n\nPreflight checks before any live execution:\n\nchain (solana or base) explicitly selected\nfunding source identified (vault or signer account)\nmax-risk limits loaded\ndry-run path available" }, { "title": "Solana path (full stack)", "body": "Use:\n\nMinara for detection/intent parsing,\nTorch Market for deep token + quote + treasury/lending state,\noptional Torch execution patterns (vault-routed),\nexternal web search for social confirmation." }, { "title": "Base path (constrained path)", "body": "Use:\n\nMinara for detection/intent/transaction assembly,\nexternal web search for social confirmation.\n\nImportant boundary:\n\nTorch Market and Torch Liquidation Bot are Solana-focused and should not be assumed to provide Base-native token risk primitives." }, { "title": "Inputs the LM Must Collect First", "body": "target_chain: solana or base\ntoken_symbol_or_mint\nmax_entry_size (example: 1 SOL or base-chain equivalent)\nmax_slippage_bps (example: 300)\nrisk_mode: observe, paper, live\nsentiment_min_accounts (minimum credible, non-bot mentions)\nexecution_policy: manual-confirm or auto-with-guardrails\n\nIf missing, do not run live execution." }, { "title": "Minara (minara)", "body": "Primary detection/intelligence and swap-intent layer:\n\nmarket chat/intel,\nintent-to-swap transaction generation,\nchain-aware execution pathways,\nstrategy support across Solana and EVM (including Base).\n\nUse Minara when rapid parsing and transaction assembly are required." }, { "title": "Torch Market (torchmarket)", "body": "Solana-native deep state layer:\n\ntoken discovery (getTokens) and token details (getToken),\nbuy/sell quote simulation (getBuyQuote, getSellQuote),\ntreasury/lending/position context (getLendingInfo, getLoanPosition),\nvault-routed transaction builders.\n\nUse Torch Market for on-chain structural checks and quote sanity before Solana entries." }, { "title": "Torch Liquidation Bot (torchliquidationbot)", "body": "Execution engine specialized for liquidation keepers:\n\ncontinuous scan loop,\nhigh-speed vault-routed transaction execution patterns,\nstrict vault safety boundary.\n\nImportant boundary:\n\nIt is purpose-built for liquidation flow (buildLiquidateTransaction path), not a generic buy/sell sniper by default.\nReuse only its operational/safety pattern unless a dedicated swap executor is explicitly available." }, { "title": "Canonical Signal Chain", "body": "Use this chain for launch-sniping decisions." }, { "title": "Stage 1: Early launch detection", "body": "Use Minara intelligence to detect candidate opportunities and parse swap intent context.\n\nRequired output:\n\ntoken/mint identifier\nchain\ninitial liquidity signal if available\ntimestamp of first detection" }, { "title": "Stage 2: On-chain risk triage", "body": "For Solana candidates, use Torch Market state:\n\ntoken status and reserves,\nquote simulation (buy/sell impact),\ntreasury and lending context where relevant,\nholder concentration snapshots (if available through token/holder queries).\n\nRisk interpretation policy:\n\nNo single field should be treated as a complete rug/honeypot verdict.\nRequire multiple independent indicators before green-lighting." }, { "title": "Stage 3: Social signal confirmation", "body": "Use external web search tools (not bundled in these three skills) to validate whether real accounts are discussing the token.\n\nMinimum checks:\n\naccount quality (non-trivial follower/history signals)\nmessage diversity (not duplicate bot spam)\ntemporal alignment with on-chain launch timing" }, { "title": "Stage 4: Decision matrix", "body": "Compute two gates:\n\nSecurityGate: pass/fail\nSentimentGate: pass/fail\n\nExecution rule:\n\nonly if both gates are pass\notherwise no_trade" }, { "title": "Stage 5: Execution", "body": "If execution allowed:\n\nenforce position cap (example: 1 SOL)\nenforce slippage cap\nrecord tx hash and rationale\nimmediately set post-entry monitoring conditions" }, { "title": "Scenario Mapping (PEPE2.0 on Solana)", "body": "For the scenario in this skill request:\n\nMinara flags a new Solana token/pool event with initial liquidity context.\nTorch Market fetches token-level state and quote/treasury context.\nSocial verification runs in parallel via external web search (X/Twitter signal quality).\nIf SecurityGate=pass and SentimentGate=pass, execute bounded entry (example 1 SOL) with fixed slippage tolerance.\nLog full decision trail: signals, checks, final action." }, { "title": "Output Contract", "body": "Always return:\n\nDetection\n\nchain, token ID, first-seen timestamp\n\n\n\nOnChainRisk\n\nindicators checked\npass/fail with reasons\n\n\n\nSocialSignal\n\nsource summary\npass/fail with reasons\n\n\n\nExecutionDecision\n\ntrade or no_trade\nsize, slippage, route\n\n\n\nAuditTrail\n\nexact checks performed\nunresolved uncertainties" }, { "title": "Risk Guardrails", "body": "Never deploy unbounded size; always cap first entry.\nNever trade without slippage limits.\nNever treat hype alone as trade permission.\nNever claim \"safe\" based on one heuristic.\nPrefer no_trade on ambiguous or conflicting evidence.\nIn auto-with-guardrails mode, require preconfigured hard limits and fail-closed defaults." }, { "title": "observe", "body": "Detection and scoring only. No trade." }, { "title": "paper", "body": "Simulated entries/exits with recorded hypothetical PnL." }, { "title": "live", "body": "Real execution only after preflight and guardrail checks pass." }, { "title": "Failure Handling", "body": "Missing key/config/env: halt with explicit missing item list.\nDetection without sufficient risk data: downgrade to observe.\nSentiment source unavailable: require manual confirmation or no_trade.\nExecution route unavailable on selected chain: return explicit compatibility mismatch." }, { "title": "Known Limits from Inspected Upstream Skills", "body": "Minara inspected docs describe intent parsing and transaction assembly, but do not expose a dedicated \"mempool scanner\" endpoint in the inspected SKILL.md.\nTorch Market exposes rich Solana token/treasury/lending state and quotes, but no single built-in \"honeypot/rug score\" flag.\nTorch Liquidation Bot is liquidation-specialized; using it as a generic swap executor is a repurposing pattern, not its native primary workflow.\nSocial signal checks require external web/search skills outside this three-skill stack.\n\nTreat these limits as mandatory disclosures in final operator output." } ], "body": "Purpose\n\nRun a high-speed token opportunity workflow:\n\ndetect very early pool/token activity,\ntriage contract/market risk,\nverify social signal quality,\nexecute small, bounded entries when rules pass.\n\nThis is an orchestration skill. It coordinates upstream skills and explicit risk policy. It does not guarantee profit.\n\nRequired Installed Skills\nminara (inspected latest: 1.1.9)\ntorchmarket (inspected latest: 4.2.7)\ntorchliquidationbot (inspected latest: 3.0.2)\n\nInstall/update:\n\nnpx -y clawhub@latest install minara\nnpx -y clawhub@latest install torchmarket\nnpx -y clawhub@latest install torchliquidationbot\nnpx -y clawhub@latest update --all\n\nRequired Configuration and Credentials\n\nMinimum:\n\nMINARA_API_KEY\nSOLANA_RPC_URL\n\nDepending on execution route:\n\nMinara signer path: Circle Wallet preferred, or chain private-key fallback per Minara docs.\nTorch vault path: VAULT_CREATOR and linked agent wallet for vault-routed operations.\n\nPreflight checks before any live execution:\n\nchain (solana or base) explicitly selected\nfunding source identified (vault or signer account)\nmax-risk limits loaded\ndry-run path available\nChain-Aware Architecture\nSolana path (full stack)\n\nUse:\n\nMinara for detection/intent parsing,\nTorch Market for deep token + quote + treasury/lending state,\noptional Torch execution patterns (vault-routed),\nexternal web search for social confirmation.\nBase path (constrained path)\n\nUse:\n\nMinara for detection/intent/transaction assembly,\nexternal web search for social confirmation.\n\nImportant boundary:\n\nTorch Market and Torch Liquidation Bot are Solana-focused and should not be assumed to provide Base-native token risk primitives.\nInputs the LM Must Collect First\ntarget_chain: solana or base\ntoken_symbol_or_mint\nmax_entry_size (example: 1 SOL or base-chain equivalent)\nmax_slippage_bps (example: 300)\nrisk_mode: observe, paper, live\nsentiment_min_accounts (minimum credible, non-bot mentions)\nexecution_policy: manual-confirm or auto-with-guardrails\n\nIf missing, do not run live execution.\n\nTool Responsibilities\nMinara (minara)\n\nPrimary detection/intelligence and swap-intent layer:\n\nmarket chat/intel,\nintent-to-swap transaction generation,\nchain-aware execution pathways,\nstrategy support across Solana and EVM (including Base).\n\nUse Minara when rapid parsing and transaction assembly are required.\n\nTorch Market (torchmarket)\n\nSolana-native deep state layer:\n\ntoken discovery (getTokens) and token details (getToken),\nbuy/sell quote simulation (getBuyQuote, getSellQuote),\ntreasury/lending/position context (getLendingInfo, getLoanPosition),\nvault-routed transaction builders.\n\nUse Torch Market for on-chain structural checks and quote sanity before Solana entries.\n\nTorch Liquidation Bot (torchliquidationbot)\n\nExecution engine specialized for liquidation keepers:\n\ncontinuous scan loop,\nhigh-speed vault-routed transaction execution patterns,\nstrict vault safety boundary.\n\nImportant boundary:\n\nIt is purpose-built for liquidation flow (buildLiquidateTransaction path), not a generic buy/sell sniper by default.\nReuse only its operational/safety pattern unless a dedicated swap executor is explicitly available.\nCanonical Signal Chain\n\nUse this chain for launch-sniping decisions.\n\nStage 1: Early launch detection\n\nUse Minara intelligence to detect candidate opportunities and parse swap intent context.\n\nRequired output:\n\ntoken/mint identifier\nchain\ninitial liquidity signal if available\ntimestamp of first detection\nStage 2: On-chain risk triage\n\nFor Solana candidates, use Torch Market state:\n\ntoken status and reserves,\nquote simulation (buy/sell impact),\ntreasury and lending context where relevant,\nholder concentration snapshots (if available through token/holder queries).\n\nRisk interpretation policy:\n\nNo single field should be treated as a complete rug/honeypot verdict.\nRequire multiple independent indicators before green-lighting.\nStage 3: Social signal confirmation\n\nUse external web search tools (not bundled in these three skills) to validate whether real accounts are discussing the token.\n\nMinimum checks:\n\naccount quality (non-trivial follower/history signals)\nmessage diversity (not duplicate bot spam)\ntemporal alignment with on-chain launch timing\nStage 4: Decision matrix\n\nCompute two gates:\n\nSecurityGate: pass/fail\nSentimentGate: pass/fail\n\nExecution rule:\n\nonly if both gates are pass\notherwise no_trade\nStage 5: Execution\n\nIf execution allowed:\n\nenforce position cap (example: 1 SOL)\nenforce slippage cap\nrecord tx hash and rationale\nimmediately set post-entry monitoring conditions\nScenario Mapping (PEPE2.0 on Solana)\n\nFor the scenario in this skill request:\n\nMinara flags a new Solana token/pool event with initial liquidity context.\nTorch Market fetches token-level state and quote/treasury context.\nSocial verification runs in parallel via external web search (X/Twitter signal quality).\nIf SecurityGate=pass and SentimentGate=pass, execute bounded entry (example 1 SOL) with fixed slippage tolerance.\nLog full decision trail: signals, checks, final action.\nOutput Contract\n\nAlways return:\n\nDetection\n\nchain, token ID, first-seen timestamp\n\nOnChainRisk\n\nindicators checked\npass/fail with reasons\n\nSocialSignal\n\nsource summary\npass/fail with reasons\n\nExecutionDecision\n\ntrade or no_trade\nsize, slippage, route\n\nAuditTrail\n\nexact checks performed\nunresolved uncertainties\nRisk Guardrails\nNever deploy unbounded size; always cap first entry.\nNever trade without slippage limits.\nNever treat hype alone as trade permission.\nNever claim \"safe\" based on one heuristic.\nPrefer no_trade on ambiguous or conflicting evidence.\nIn auto-with-guardrails mode, require preconfigured hard limits and fail-closed defaults.\nOperational Modes\nobserve\n\nDetection and scoring only. No trade.\n\npaper\n\nSimulated entries/exits with recorded hypothetical PnL.\n\nlive\n\nReal execution only after preflight and guardrail checks pass.\n\nFailure Handling\nMissing key/config/env: halt with explicit missing item list.\nDetection without sufficient risk data: downgrade to observe.\nSentiment source unavailable: require manual confirmation or no_trade.\nExecution route unavailable on selected chain: return explicit compatibility mismatch.\nKnown Limits from Inspected Upstream Skills\nMinara inspected docs describe intent parsing and transaction assembly, but do not expose a dedicated \"mempool scanner\" endpoint in the inspected SKILL.md.\nTorch Market exposes rich Solana token/treasury/lending state and quotes, but no single built-in \"honeypot/rug score\" flag.\nTorch Liquidation Bot is liquidation-specialized; using it as a generic swap executor is a repurposing pattern, not its native primary workflow.\nSocial signal checks require external web/search skills outside this three-skill stack.\n\nTreat these limits as mandatory disclosures in final operator output." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/h4gen/defi-sniper", "publisherUrl": "https://clawhub.ai/h4gen/defi-sniper", "owner": "h4gen", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/defi-sniper", "downloadUrl": "https://openagent3.xyz/downloads/defi-sniper", "agentUrl": "https://openagent3.xyz/skills/defi-sniper/agent", "manifestUrl": "https://openagent3.xyz/skills/defi-sniper/agent.json", "briefUrl": "https://openagent3.xyz/skills/defi-sniper/agent.md" } }