[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M764EY2J858TC7ARDJHMQ937":3,"skill-same:01M764EY2J858TC7ARDJHMQ937":67},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":36,"ownerDescription":37,"updatedAt":38,"install":39,"resources":52},"01M764EY2J858TC7ARDJHMQ937","ctf-web-devtools",null,"Browser-native reconnaissance with chrome-devtools-mcp for CTF web targets. Use when the challenge is a JS-heavy page or SPA and you need the exact API requests the page makes, POST bodies, console errors with stack traces, computed CSS, localStorage\u002Fsecrets, or screenshots — before moving to wire replay with curl\u002Fffuf. Pairs with ctf-web (ops loop) and feeds har_map.py.","jiayaoqijia\u002Fcryptoskill","jiayaoqijia","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1453879?v=4","01M6GMYTX7Q7S504VC6E756ENR","YQ","01M6GMYV1QKJ1CC75MTTGT9PR0",81,"MIT","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fdev-tools\u002Fabhay2008-ctf-web-devtools\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fdev-tools\u002Fabhay2008-ctf-web-devtools\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: ctf-web-devtools\ndescription: Browser-native reconnaissance with chrome-devtools-mcp for CTF web targets. Use when the challenge is a JS-heavy page or SPA and you need the exact API requests the page makes, POST bodies, console errors with stack traces, computed CSS, localStorage\u002Fsecrets, or screenshots — before moving to wire replay with curl\u002Fffuf. Pairs with ctf-web (ops loop) and feeds har_map.py.\nlicense: MIT\ncompatibility: Requires the chrome-devtools MCP server (chrome-devtools-mcp 1.12.0, Node + Chrome) configured in .agents\u002Fmcp.json.\nallowed-tools: Bash Read Write Edit Glob Grep Task WebFetch WebSearch Skill\nmetadata:\n  user-invocable: \"true\"\n  argument-hint: \"[challenge URL]\"\n---\n\n# CTF Web DevTools — browser-native recon\n\nTalk to the page with `chrome-devtools-mcp` first. The page *shows* you which API requests matter; `har_map.py` *ranks* them; the wire lane (curl\u002Fffuf\u002F`api_fuzz.sh` from `ctf-web`) *exploits* them. Never fuzz blind when the browser will tell you the endpoints.\n\n## 0. Preconditions and cost control\n\n- Server: `chrome-devtools` in `.agents\u002Fmcp.json` (`--headless --isolated`, workspace=scoped, memory\u002Fperf categories off by default).\n- `--isolated` gives a throwaway profile: CTF cookies never touch your real browser.\n- Tool-call budget: each `get_network_request` returns full bodies — call it only on write\u002Finteresting requests, not on every static asset.\n- If the server fails to launch Chrome, check `Google Chrome.app` exists and retry with `--channel=stable` (default). Do NOT attach to your real profile (`--browser-url`) with non-CTF tabs open.\n\n## 1. The loop (in order)\n\n```\n1. navigate_page \u003CURL>                 # land on the challenge\n2. take_snapshot                        # accessibility tree: forms, buttons, inputs\n3. list_network_requests                # filter mentally: fetch\u002FXHR first, ignore static\n4. get_network_request \u003Cid>             # bodies of the 3-5 most interesting requests\n5. list_console_messages                 # leaked secrets, paths, stack traces, TODOs\n6. evaluate_script \u003Cread storage>       # localStorage \u002F sessionStorage \u002F window.__config\n7. export HAR -> scripts\u002Fhar_map.py     # rank endpoints, see ctf-web §HAR mapper\n8. move to wire: curl\u002Fffuf\u002Fapi_fuzz.sh  # clone cookies, mutate, fuzz (ctf-web lane)\n```\n\n### Step 2 — snapshot, not screenshot\n\n`take_snapshot` (accessibility tree) is cheaper and more actionable than `take_screenshot`. Use the screenshot only for canvas\u002FCAPTCHA\u002Fvisual-puzzle challenges, or to confirm a UI state after an action.\n\n### Step 3 — which requests matter\n\nPriority: `POST\u002FPUT\u002FPATCH\u002FDELETE` > `GET` with query strings > `GET` JSON > static assets (ignore `.js\u002F.css\u002F.png\u002F.woff2` unless you suspect a secret in JS — then fetch the JS body; source maps `*.js.map` are gold).\n\nWrite requests that return **4xx with a detailed JSON error** are the best leads: they prove the parser reads your input and tell you the expected shape.\n\n### Step 4 — bodies, the thing Playwright does not give you\n\n`get_network_request` returns request + response headers and bodies. Capture for each interesting request:\n\n- exact URL, method, headers (`Content-Type`, `Authorization`, custom `X-*`)\n- request body bytes (replay these exactly with curl before mutating)\n- response body and status — a `200` with `{\"ok\": false}` is a rendered-page lead, not a wire lead\n\n### Step 5 — console is a secret scanner\n\n`list_console_messages` then `get_console_message` on errors. Look for: API keys, internal hostnames, stack traces with file paths, `TODO`\u002F`FIXME` with endpoints, React\u002FVue dev-mode warnings that name components, failed `fetch()` URLs the UI never shows.\n\n### Step 6 — client-side storage\n\n```js\n\u002F\u002F evaluate_script payloads (read-only; never write during recon)\nObject.entries(localStorage)\nObject.entries(sessionStorage)\ndocument.cookie\nObject.keys(window).filter(k => \u002Fconfig|flag|api|token|secret\u002Fi.test(k))\n```\n\nSPAs park JWTs, feature flags, and admin booleans here. If you find a token, jump to the wire lane immediately — do not keep clicking.\n\n## 2. Manipulation (only after recon)\n\nInput tools in cheapest-first order: `fill` (single field) → `fill_form` (whole form) → `click` → `press_key` (Enter\u002FEscape) → `handle_dialog` (alert\u002Fconfirm\u002Fprompt block automation — handle them or the page stalls). `upload_file` for file-upload challenges; pair with the `ctf-web` upload notes. `drag` for slider\u002Fdrag-drop CAPTCHAs.\n\n## 3. Emulation for environment-gated challenges\n\n`emulate` (UA, geolocation, timezone, locale) then `resize_page` (mobile viewport) when the challenge branches on device, locale, or \"mobile-only\" features. Re-run `list_network_requests` after emulation — mobile builds often call *different* endpoints.\n\n## 4. When to leave this skill\n\n| Signal | Go to |\n|---|---|\n| You have ranked endpoints + cloned cookies | `ctf-web` API lane (replay\u002Fmutate\u002Ffuzz) |\n| Login wall you cannot pass in-browser | `ctf-web` auth notes (JWT\u002FOAuth sections) |\n| Need request interception\u002Fmodification in flight | mitmproxy\u002FCaido\u002FBurp (see reports\u002Fskills-plugins-research-2026-11.md §4.2) |\n| No network tools available (server down) | `agent-browser` HAR capture, then `har_map.py` manually |\n| Page is a game\u002Fcanvas with no API | `take_screenshot` + manual play; this skill is done |\n\n## 5. Failure branches\n\n- **Empty network list:** the page may use WebSockets (`list_network_requests` may not show frames — check console + snapshot for `ws:\u002F\u002F`), or requests fired before you attached. `navigate_page` again (fresh load) and re-list.\n- **Auth-gated API returns 401 in replay:** your cloned cookie jar is stale — re-export from the browser, do not hand-edit tokens.\n- **`evaluate_script` blocked by CSP:** read storage via `take_snapshot` exposed values, or move to the wire lane; do not fight CSP during recon.\n- **Memory category needed** (prototype-pollution\u002Fclosure hunt): restart the server with `--categoryMemory` (14 heap tools) — off by default for context cost.\n\n## 6. Verify the stack\n\n```\nnpx -y chrome-devtools-mcp@1.12.0 --help | head -3\n# smoke: navigate to a harmless page, list_network_requests returns ≥1 entry\n```\n","# CTF Web DevTools — browser-native recon\n\nTalk to the page with `chrome-devtools-mcp` first. The page *shows* you which API requests matter; `har_map.py` *ranks* them; the wire lane (curl\u002Fffuf\u002F`api_fuzz.sh` from `ctf-web`) *exploits* them. Never fuzz blind when the browser will tell you the endpoints.\n\n## 0. Preconditions and cost control\n\n- Server: `chrome-devtools` in `.agents\u002Fmcp.json` (`--headless --isolated`, workspace=scoped, memory\u002Fperf categories off by default).\n- `--isolated` gives a throwaway profile: CTF cookies never touch your real browser.\n- Tool-call budget: each `get_network_request` returns full bodies — call it only on write\u002Finteresting requests, not on every static asset.\n- If the server fails to launch Chrome, check `Google Chrome.app` exists and retry with `--channel=stable` (default). Do NOT attach to your real profile (`--browser-url`) with non-CTF tabs open.\n\n## 1. The loop (in order)\n\n```\n1. navigate_page \u003CURL>                 # land on the challenge\n2. take_snapshot                        # accessibility tree: forms, buttons, inputs\n3. list_network_requests                # filter mentally: fetch\u002FXHR first, ignore static\n4. get_network_request \u003Cid>             # bodies of the 3-5 most interesting requests\n5. list_console_messages                 # leaked secrets, paths, stack traces, TODOs\n6. evaluate_script \u003Cread storage>       # localStorage \u002F sessionStorage \u002F window.__config\n7. export HAR -> scripts\u002Fhar_map.py     # rank endpoints, see ctf-web §HAR mapper\n8. move to wire: curl\u002Fffuf\u002Fapi_fuzz.sh  # clone cookies, mutate, fuzz (ctf-web lane)\n```\n\n### Step 2 — snapshot, not screenshot\n\n`take_snapshot` (accessibility tree) is cheaper and more actionable than `take_screenshot`. Use the screenshot only for canvas\u002FCAPTCHA\u002Fvisual-puzzle challenges, or to confirm a UI state after an action.\n\n### Step 3 — which requests matter\n\nPriority: `POST\u002FPUT\u002FPATCH\u002FDELETE` > `GET` with query strings > `GET` JSON > static assets (ignore `.js\u002F.css\u002F.png\u002F.woff2` unless you suspect a secret in JS — then fetch the JS body; source maps `*.js.map` are gold).\n\nWrite requests that return **4xx with a detailed JSON error** are the best leads: they prove the parser reads your input and tell you the expected shape.\n\n### Step 4 — bodies, the thing Playwright does not give you\n\n`get_network_request` returns request + response headers and bodies. Capture for each interesting request:\n\n- exact URL, method, headers (`Content-Type`, `Authorization`, custom `X-*`)\n- request body bytes (replay these exactly with curl before mutating)\n- response body and status — a `200` with `{\"ok\": false}` is a rendered-page lead, not a wire lead\n\n### Step 5 — console is a secret scanner\n\n`list_console_messages` then `get_console_message` on errors. Look for: API keys, internal hostnames, stack traces with file paths, `TODO`\u002F`FIXME` with endpoints, React\u002FVue dev-mode warnings that name components, failed `fetch()` URLs the UI never shows.\n\n### Step 6 — client-side storage\n\n```js\n\u002F\u002F evaluate_script payloads (read-only; never write during recon)\nObject.entries(localStorage)\nObject.entries(sessionStorage)\ndocument.cookie\nObject.keys(window).filter(k => \u002Fconfig|flag|api|token|secret\u002Fi.test(k))\n```\n\nSPAs park JWTs, feature flags, and admin booleans here. If you find a token, jump to the wire lane immediately — do not keep clicking.\n\n## 2. Manipulation (only after recon)\n\nInput tools in cheapest-first order: `fill` (single field) → `fill_form` (whole form) → `click` → `press_key` (Enter\u002FEscape) → `handle_dialog` (alert\u002Fconfirm\u002Fprompt block automation — handle them or the page stalls). `upload_file` for file-upload challenges; pair with the `ctf-web` upload notes. `drag` for slider\u002Fdrag-drop CAPTCHAs.\n\n## 3. Emulation for environment-gated challenges\n\n`emulate` (UA, geolocation, timezone, locale) then `resize_page` (mobile viewport) when the challenge branches on device, locale, or \"mobile-only\" features. Re-run `list_network_requests` after emulation — mobile builds often call *different* endpoints.\n\n## 4. When to leave this skill\n\n| Signal | Go to |\n|---|---|\n| You have ranked endpoints + cloned cookies | `ctf-web` API lane (replay\u002Fmutate\u002Ffuzz) |\n| Login wall you cannot pass in-browser | `ctf-web` auth notes (JWT\u002FOAuth sections) |\n| Need request interception\u002Fmodification in flight | mitmproxy\u002FCaido\u002FBurp (see reports\u002Fskills-plugins-research-2026-11.md §4.2) |\n| No network tools available (server down) | `agent-browser` HAR capture, then `har_map.py` manually |\n| Page is a game\u002Fcanvas with no API | `take_screenshot` + manual play; this skill is done |\n\n## 5. Failure branches\n\n- **Empty network list:** the page may use WebSockets (`list_network_requests` may not show frames — check console + snapshot for `ws:\u002F\u002F`), or requests fired before you attached. `navigate_page` again (fresh load) and re-list.\n- **Auth-gated API returns 401 in replay:** your cloned cookie jar is stale — re-export from the browser, do not hand-edit tokens.\n- **`evaluate_script` blocked by CSP:** read storage via `take_snapshot` exposed values, or move to the wire lane; do not fight CSP during recon.\n- **Memory category needed** (prototype-pollution\u002Fclosure hunt): restart the server with `--categoryMemory` (14 heap tools) — off by default for context cost.\n\n## 6. Verify the stack\n\n```\nnpx -y chrome-devtools-mcp@1.12.0 --help | head -3\n# smoke: navigate to a harmless page, list_network_requests returns ≥1 entry\n```\n",{"name":5,"license":15,"metadata":25,"description":7,"allowed-tools":28,"compatibility":29},{"argument-hint":26,"user-invocable":27},"[challenge URL]","true","Bash Read Write Edit Glob Grep Task WebFetch WebSearch Skill","Requires the chrome-devtools MCP server (chrome-devtools-mcp 1.12.0, Node + Chrome) configured in .agents\u002Fmcp.json.","main","fa749116cef035d5ee7c7e7deb1aa875e30afc91","skills\u002Fdev-tools\u002Fabhay2008-ctf-web-devtools",17,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia","https:\u002F\u002Feth2030.com","Hardcore infra. Building @alt-research and applied cryptography.","2026-11-15 02:28:10",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add jiayaoqijia\u002Fcryptoskill --skill ctf-web-devtools",{"tool":45,"command":46},"bunx","bunx skills add jiayaoqijia\u002Fcryptoskill --skill ctf-web-devtools",{"tool":48,"command":49},"pnpm","pnpm dlx skills add jiayaoqijia\u002Fcryptoskill --skill ctf-web-devtools","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fdev-tools\u002Fabhay2008-ctf-web-devtools\u002FSKILL.md",true,[53,57,63],{"path":54,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":16},"LICENSE","许可证",1072,{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"SOURCE.md","REFERENCE","参考文档",357,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fdev-tools\u002Fabhay2008-ctf-web-devtools\u002FSOURCE.md",{"path":64,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":65,"sourceHtmlUrl":66},"TRUST.auto.yaml",2065,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fdev-tools\u002Fabhay2008-ctf-web-devtools\u002FTRUST.auto.yaml",[68,77,85,93,101,109],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":72,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":76},"01M7DTKCERMV0RNX3HZJP4CZ26","troves","Deposit and withdraw from Troves DeFi yield vault strategies on Starknet. View available strategies, check positions, and manage vault deposits. Use this skill when the user mentions Troves, vault, yield vault, DeFi vault, strategy, yield farming, vault deposit, vault withdraw, earning yield through vaults, passive yield strategies, or wants to deposit into or withdraw from a yield strategy — even if they don't say \"Troves\" explicitly.","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-troves\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-troves\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":81,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":76},"01M7DTK6CJSMGC8KCQHGNYFZBD","trade","Swap tokens on Starknet via Fibrous DEX aggregator. Supports per-provider selection (avnu, ekubo, or auto to race all). Use this skill when the user wants to swap, exchange, trade, convert, buy, or sell one token for another on Starknet. Also use when the user asks about token prices, exchange rates, DEX routing, best swap route, or wants to check how much they would receive for a given amount — even if they don't explicitly say \"swap\".","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-trade\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-trade\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":89,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":76},"01M7DTJZ6A0X4PAW3Y8W4J9K64","staking","Stake, unstake, claim, and compound rewards for STRK, WBTC, tBTC, SolvBTC, and LBTC on Starknet. View validators, pools, and staking positions. Use this skill when the user mentions staking, delegating, validators, staking pools, rewards, compounding, unstaking, earning yield, passive income on crypto, or wants to earn on their STRK or BTC tokens — even if they don't say \"stake\" explicitly.","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-staking\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-staking\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":97,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":76},"01M7DTJSDZJKCDMW7GHRF4BRH5","send","Send STRK, ETH, or any ERC-20 token to a Starknet address. Supports simulation (dry-run) before execution. Use this skill when the user wants to send, transfer, pay, tip, or move tokens to another wallet address on Starknet. Also trigger when the user mentions sending funds to someone, making a payment, transferring assets, or moving crypto to a specific address — even if they just say \"pay 10 STRK to 0x...\".","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-send\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-send\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":105,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":76},"01M7DTJG1E480D51ZQ7WKDQ26K","portfolio","View a comprehensive DeFi portfolio dashboard and optimize portfolio allocation via automated rebalancing. Use this skill when the user wants an overview, summary, dashboard, total value, net worth, portfolio rebalancing, target allocation, or wants to see all their DeFi positions across Starknet at once. Also trigger when the user asks \"what do I have\", \"show me everything\", \"how much am I worth\", \"my positions\", \"my investments\", \"rebalance my portfolio\", \"I want 50% ETH\", \"optimize my holdings\", or any request for a holistic view of their Starknet holdings — even if they don't explicitly say \"portfolio\".","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-portfolio\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-portfolio\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":113,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":76},"01M7DTJ7M8TE9R2N36HFBZDGVD","multi-swap","Execute multiple token swaps in a single Starknet transaction via Fibrous (default). Supports per-provider selection (avnu, ekubo, or auto to race all). Supports 2-3 swap pairs bundled into one multicall. Use this skill when the user wants to swap multiple token pairs at once, do batch swaps, execute several trades simultaneously, perform parallel swaps, or do bulk trading in one transaction. Also trigger when the user mentions \"two swaps\", \"three swaps\", \"swap X and Y at the same time\", or wants to convert multiple tokens in a single call.","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-multi-swap\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-multi-swap\u002FSKILL.md",[],[]]