[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CZDBP0ARPTTS0D3996EG3G":3,"skill-same:01M6CZDBP0ARPTTS0D3996EG3G":73},{"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":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":55,"ownerHtmlUrl":56,"ownerBlogUrl":55,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M6CZDBP0ARPTTS0D3996EG3G","token-pick",null,"One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak","aeonfun\u002Faeon","aeonfun","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F287715280?v=4","01M6CZ23C6MXGMF4N0V1DZ1247","aeon","01M6CZ23GMZP1BR424J8Y8K3DG",793,"MIT","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fskills\u002Ftoken-pick\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35],"pick","token pick","token","signals","prediction","when","read-only","with","coingecko","recommendation","notifications","crypto","Market","only","read","branch","api","2026-11-10 10:12:30",false,"---\nname: token-pick\ndescription: One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak\nmetadata:\n  title: Token Pick\n  mode: read-only\n  category: crypto\n  var: \"\"\n  tags:\n    - crypto\n  requires:\n    - COINGECKO_API_KEY?\n  capabilities:\n    - external_api\n    - sends_notifications\n---\n\u003C!-- autoresearch: variation B — sharper output via signal scoring, edge calculation, conviction tiers, and a skip-day branch -->\n\n> **${var}** — Focus area or thesis (e.g. \"AI tokens\", \"election markets\", \"contrarian bets\"). If empty, scans broadly.\n\nRead `memory\u002FMEMORY.md` for context.\nRead the last 7 days of `memory\u002Flogs\u002F` and grep for prior `Token Pick` entries — extract the symbols and market questions already picked. **Hard dedup gate**: do not re-pick the same token or the same prediction market unless there is a materially new catalyst that you can name in one sentence.\n\n## Goal\n\nProduce ONE token call and ONE prediction-market call per day, each with a numeric signal\u002Fedge score and a conviction tier. If neither qualifies for at least MEDIUM conviction, send a short \"no picks today\" message rather than forcing a weak pick.\n\n## Steps\n\n### 1. Fetch token data\n\nThe optional demo key rides .\u002Fsecretcurl's `{COINGECKO_API_KEY}` placeholder (never a bare secret on the line). Key check: read the \"Keys set for this run\" line in your run notes, never a shell test (those are refused and cost a turn). When `COINGECKO_API_KEY` is on that line keep the `-H \"x-cg-demo-api-key: {COINGECKO_API_KEY}\"` shown below; when it is not, drop that `-H` (the same public endpoint works keyless at a lower rate limit).\n\n```bash\n# Trending coins\n.\u002Fsecretcurl -s -H \"x-cg-demo-api-key: {COINGECKO_API_KEY}\" \"https:\u002F\u002Fapi.coingecko.com\u002Fapi\u002Fv3\u002Fsearch\u002Ftrending\"\n\n# Top 250 by market cap with 24h and 7d changes\n.\u002Fsecretcurl -s -H \"x-cg-demo-api-key: {COINGECKO_API_KEY}\" \"https:\u002F\u002Fapi.coingecko.com\u002Fapi\u002Fv3\u002Fcoins\u002Fmarkets?vs_currency=usd&order=market_cap_desc&per_page=250&page=1&sparkline=false&price_change_percentage=24h,7d\"\n\n# BTC + ETH 24h\u002F7d for relative-strength benchmark (extract from the markets call above; no extra request needed)\n\n# DEX-side cross-confirmation (no auth, optional but preferred)\ncurl -s \"https:\u002F\u002Fapi.dexscreener.com\u002Flatest\u002Fdex\u002Fsearch?q=trending\"\n```\n\nIf any curl returns empty or errors, retry once with **WebFetch** for the same URL. Track per-source status (`cg=ok|fail`, `dex=ok|fail`) — surfaced in the output footer.\n\n### 2. Fetch prediction markets\n\n```bash\n# Top events by 24h volume (events group multi-outcome questions)\ncurl -s \"https:\u002F\u002Fgamma-api.polymarket.com\u002Fevents?active=true&closed=false&order=volume_24hr&ascending=false&limit=30\"\n\n# Newer markets gaining traction\ncurl -s \"https:\u002F\u002Fgamma-api.polymarket.com\u002Fmarkets?closed=false&order=startDate&ascending=false&limit=20\"\n```\n\nWebFetch fallback on failure. Track `poly=ok|fail`.\n\n### 3. Score every candidate token (0–10 scale)\n\nFor each token in the top 250 (and the trending list), compute a signal score:\n\n| Signal | Points |\n|---|---|\n| 24h price change > 0 | +1 |\n| 7d price change > 0 | +1 |\n| Both 24h and 7d > +5% | +2 (in addition to above) |\n| Appears on CoinGecko trending list | +2 |\n| Volume\u002FMarketCap ratio ≥ 0.10 | +2 |\n| Volume\u002FMarketCap ratio ≥ 0.20 (replaces above) | +3 |\n| Outperforming BOTH BTC and ETH on the 7d | +2 |\n| Confirmed on DexScreener trending\u002Fgainers (cross-source) | +1 |\n| Matches `${var}` thesis when set | +1 |\n\nDrop candidates with market cap \u003C $20M (too pumpable) unless `${var}` explicitly targets micro-caps. Drop any token already picked in the last 7 days (per dedup gate) unless you can name a fresh catalyst.\n\nPick the highest-scoring token. Use **WebSearch** to surface the most likely catalyst and at least one named risk (regulatory, unlock, narrative-faded, exchange listing, etc.).\n\n### 4. Score prediction markets — edge calculation\n\nFor the top ~10 markets by 24h volume that pass the dedup gate (and `${var}` filter when set), do this for each:\n\n1. Read the question and current YES price (`price`\u002F`outcomePrices`).\n2. Use **WebSearch** to gather 1–3 recent data points relevant to the resolution.\n3. Estimate a **fair YES probability** as a single number (your best calibrated guess, not a range). State the 1–3 inputs you used.\n4. Compute `edge = |fair − current_price|` as percentage points.\n5. Liquidity gate: require 24h volume ≥ $50k AND market not resolving in \u003C 24h (no last-minute mean-reversion roulette).\n\nPick the market with the largest edge that clears the gate. If you cannot defend a fair-value estimate within ±10% (insufficient public info), discard and try the next market.\n\n### 5. Conviction tiers\n\n| Tier | Token criterion | Market criterion |\n|---|---|---|\n| HIGH | signal score ≥ 7 | edge ≥ 10pp |\n| MEDIUM | signal score 4–6 | edge 5–10pp |\n| SKIP | signal score \u003C 4 | edge \u003C 5pp |\n\n**Skip-day branch**: if BOTH the chosen token and the chosen market land in SKIP, do not synthesize a pick. Send the skip message (step 6b) and log accordingly. This is a feature — forcing low-conviction picks degrades the signal of the whole feed.\n\n### 6a. Notification — normal day (under 4000 chars)\n\nSend via `.\u002Fnotify`:\n\n```\n*Daily Pick - ${today}*\n\n*Token: SYMBOL*  [HIGH | MEDIUM]  signal X\u002F10\nPrice: $X.XX (±X.X% 24h \u002F ±X.X% 7d) | mcap $XB | vol $XM (vol\u002Fmcap X.XX)\nScore breakdown: [trending+2, vol\u002Fmcap+3, RS vs BTC\u002FETH+2, narrative+1] = 8\u002F10\nCatalyst: [one sentence - what's driving this right now, named source\u002Fevent]\nRisk: [one sentence - concrete risk, not generic \"could go down\"]\nVs recent picks: [first time \u002F repeat with new catalyst: ...]\n\n*Market: \"Question?\"*  [HIGH | MEDIUM]  edge Xpp\nCurrent: YES X¢ \u002F NO Y¢ | 24h vol $Xm | resolves: DATE\nFair YES: ~Y% (inputs: [src1], [src2], [src3])\nThesis: [one sentence - why the market is wrong, action implied]\nRisk: [one sentence - what could make your fair-value estimate wrong]\n\nsources: cg=ok|fail, dex=ok|fail, poly=ok|fail\nnot financial advice - pattern-matching only\n```\n\nIf only one of the two pick types qualifies, send just that one section (omit the other entirely — do not include a HIGH and a SKIP in the same message).\n\n### 6b. Notification — skip day\n\n```\n*Daily Pick - ${today}* - no picks\n\nToken signals weak today (best: SYMBOL @ score 3\u002F10).\nMarkets either thin liquidity or no defensible edge ≥ 5pp (best: \"Question?\" edge 2pp).\n\nTomorrow.\nsources: cg=ok|fail, dex=ok|fail, poly=ok|fail\n```\n\nIf all sources failed, send `TOKEN_PICK_NO_DATA` with the source-status line — do not invent picks from cached intuition.\n\n### 6c. Offer a deep-dive (force-reply — normal-day only)\n\nOnly after a **normal-day** send (6a) — never on the skip-day (6b) or the no-data path (weak signals → no pick, so no offer). This skill is `read-only`, so it can't run the deep report itself; instead it offers to hand off to **token-movers** (write mode), which owns the single-token deep report and the `deep-dive:` handler. Because `force_reply` and inline buttons can't share one message, send this as a SEPARATE `.\u002Fnotify` AFTER the 6a pick:\n\n```bash\n.\u002Fnotify \"Want a deeper report on a token? Reply with a ticker or contract.\" \\\n  --force-reply --placeholder \"e.g. WIF\" \\\n  --context \"token-movers::deep-dive\"\n```\n\nThe `token-movers::deep-dive` marker routes the operator's reply to **token-movers** as `var=\"deep-dive:\u003Ctheir text>\"`; token-movers strips the `deep-dive:` prefix and produces the single-token deep report.\n\n**Dedup.** token-pick runs once daily, so one offer per run is already once-per-day. Being `read-only`, it can't write a `FORCE_REPLY_OFFERED` marker — but it already reads recent logs, so if today's log already carries a `FORCE_REPLY_OFFERED: deep-dive` line (e.g. token-movers offered earlier today), SKIP this offer to avoid double-nagging.\n\n### 7. Log record\n\nThis skill is `read-only`, so the workflow's read-only guard writes its `### token-pick` log entry from your captured output; a self-written entry would be a duplicate. Don't append to `memory\u002Flogs\u002F` yourself - put this record in your **final output**:\n\n```\n### token-pick\n- **Token:** SYMBOL - $price (±X% 24h) - tier HIGH\u002FMEDIUM\u002FSKIP - score X\u002F10\n- **Token thesis:** [one line, including catalyst]\n- **Market:** \"Question?\" - YES X¢ - tier HIGH\u002FMEDIUM\u002FSKIP - edge Xpp\n- **Market thesis:** [one line, including fair-value estimate]\n- **Sources:** cg=ok|fail, dex=ok|fail, poly=ok|fail\n- **Notification sent:** yes (normal | skip | no-data)\n```\n\nAlso include symbol + market question on a single line for easy grep next-day dedup, e.g.:\n```\nTOKEN_PICK_DEDUP: SYMBOL | \"Will X happen by Y?\"\n```\n\n## Network note\n\nThere is no network sandbox — `curl` works, with **WebFetch** as the fallback for any URL fetch (CoinGecko, DexScreener, Polymarket all work without auth). For an auth'd API, call `.\u002Fsecretcurl` with a `{ENV_NAME}` placeholder (the key is injected via `requires:`). On total source failure, send the no-data notification rather than silent fail.\n\n## Environment Variables\n- `COINGECKO_API_KEY` — CoinGecko API key (optional, increases rate limits)\n\n## Constraints\n\n- **Never force a pick.** If signals are weak, the skip message IS the output.\n- **Never re-pick** the same token or market within 7 days unless you can state a new catalyst in one sentence.\n- **Show your work**: every score must show the breakdown; every edge must show the inputs.\n- Liquidity gates (mcap ≥ $20M for tokens, 24h vol ≥ $50k for markets) are hard floors — ignoring them turns the feed into a degen casino.\n- One token + one market max. Never bundle \"honorable mentions\" — that defeats the discipline.\n","\u003C!-- autoresearch: variation B — sharper output via signal scoring, edge calculation, conviction tiers, and a skip-day branch -->\n\n> **${var}** — Focus area or thesis (e.g. \"AI tokens\", \"election markets\", \"contrarian bets\"). If empty, scans broadly.\n\nRead `memory\u002FMEMORY.md` for context.\nRead the last 7 days of `memory\u002Flogs\u002F` and grep for prior `Token Pick` entries — extract the symbols and market questions already picked. **Hard dedup gate**: do not re-pick the same token or the same prediction market unless there is a materially new catalyst that you can name in one sentence.\n\n## Goal\n\nProduce ONE token call and ONE prediction-market call per day, each with a numeric signal\u002Fedge score and a conviction tier. If neither qualifies for at least MEDIUM conviction, send a short \"no picks today\" message rather than forcing a weak pick.\n\n## Steps\n\n### 1. Fetch token data\n\nThe optional demo key rides .\u002Fsecretcurl's `{COINGECKO_API_KEY}` placeholder (never a bare secret on the line). Key check: read the \"Keys set for this run\" line in your run notes, never a shell test (those are refused and cost a turn). When `COINGECKO_API_KEY` is on that line keep the `-H \"x-cg-demo-api-key: {COINGECKO_API_KEY}\"` shown below; when it is not, drop that `-H` (the same public endpoint works keyless at a lower rate limit).\n\n```bash\n# Trending coins\n.\u002Fsecretcurl -s -H \"x-cg-demo-api-key: {COINGECKO_API_KEY}\" \"https:\u002F\u002Fapi.coingecko.com\u002Fapi\u002Fv3\u002Fsearch\u002Ftrending\"\n\n# Top 250 by market cap with 24h and 7d changes\n.\u002Fsecretcurl -s -H \"x-cg-demo-api-key: {COINGECKO_API_KEY}\" \"https:\u002F\u002Fapi.coingecko.com\u002Fapi\u002Fv3\u002Fcoins\u002Fmarkets?vs_currency=usd&order=market_cap_desc&per_page=250&page=1&sparkline=false&price_change_percentage=24h,7d\"\n\n# BTC + ETH 24h\u002F7d for relative-strength benchmark (extract from the markets call above; no extra request needed)\n\n# DEX-side cross-confirmation (no auth, optional but preferred)\ncurl -s \"https:\u002F\u002Fapi.dexscreener.com\u002Flatest\u002Fdex\u002Fsearch?q=trending\"\n```\n\nIf any curl returns empty or errors, retry once with **WebFetch** for the same URL. Track per-source status (`cg=ok|fail`, `dex=ok|fail`) — surfaced in the output footer.\n\n### 2. Fetch prediction markets\n\n```bash\n# Top events by 24h volume (events group multi-outcome questions)\ncurl -s \"https:\u002F\u002Fgamma-api.polymarket.com\u002Fevents?active=true&closed=false&order=volume_24hr&ascending=false&limit=30\"\n\n# Newer markets gaining traction\ncurl -s \"https:\u002F\u002Fgamma-api.polymarket.com\u002Fmarkets?closed=false&order=startDate&ascending=false&limit=20\"\n```\n\nWebFetch fallback on failure. Track `poly=ok|fail`.\n\n### 3. Score every candidate token (0–10 scale)\n\nFor each token in the top 250 (and the trending list), compute a signal score:\n\n| Signal | Points |\n|---|---|\n| 24h price change > 0 | +1 |\n| 7d price change > 0 | +1 |\n| Both 24h and 7d > +5% | +2 (in addition to above) |\n| Appears on CoinGecko trending list | +2 |\n| Volume\u002FMarketCap ratio ≥ 0.10 | +2 |\n| Volume\u002FMarketCap ratio ≥ 0.20 (replaces above) | +3 |\n| Outperforming BOTH BTC and ETH on the 7d | +2 |\n| Confirmed on DexScreener trending\u002Fgainers (cross-source) | +1 |\n| Matches `${var}` thesis when set | +1 |\n\nDrop candidates with market cap \u003C $20M (too pumpable) unless `${var}` explicitly targets micro-caps. Drop any token already picked in the last 7 days (per dedup gate) unless you can name a fresh catalyst.\n\nPick the highest-scoring token. Use **WebSearch** to surface the most likely catalyst and at least one named risk (regulatory, unlock, narrative-faded, exchange listing, etc.).\n\n### 4. Score prediction markets — edge calculation\n\nFor the top ~10 markets by 24h volume that pass the dedup gate (and `${var}` filter when set), do this for each:\n\n1. Read the question and current YES price (`price`\u002F`outcomePrices`).\n2. Use **WebSearch** to gather 1–3 recent data points relevant to the resolution.\n3. Estimate a **fair YES probability** as a single number (your best calibrated guess, not a range). State the 1–3 inputs you used.\n4. Compute `edge = |fair − current_price|` as percentage points.\n5. Liquidity gate: require 24h volume ≥ $50k AND market not resolving in \u003C 24h (no last-minute mean-reversion roulette).\n\nPick the market with the largest edge that clears the gate. If you cannot defend a fair-value estimate within ±10% (insufficient public info), discard and try the next market.\n\n### 5. Conviction tiers\n\n| Tier | Token criterion | Market criterion |\n|---|---|---|\n| HIGH | signal score ≥ 7 | edge ≥ 10pp |\n| MEDIUM | signal score 4–6 | edge 5–10pp |\n| SKIP | signal score \u003C 4 | edge \u003C 5pp |\n\n**Skip-day branch**: if BOTH the chosen token and the chosen market land in SKIP, do not synthesize a pick. Send the skip message (step 6b) and log accordingly. This is a feature — forcing low-conviction picks degrades the signal of the whole feed.\n\n### 6a. Notification — normal day (under 4000 chars)\n\nSend via `.\u002Fnotify`:\n\n```\n*Daily Pick - ${today}*\n\n*Token: SYMBOL*  [HIGH | MEDIUM]  signal X\u002F10\nPrice: $X.XX (±X.X% 24h \u002F ±X.X% 7d) | mcap $XB | vol $XM (vol\u002Fmcap X.XX)\nScore breakdown: [trending+2, vol\u002Fmcap+3, RS vs BTC\u002FETH+2, narrative+1] = 8\u002F10\nCatalyst: [one sentence - what's driving this right now, named source\u002Fevent]\nRisk: [one sentence - concrete risk, not generic \"could go down\"]\nVs recent picks: [first time \u002F repeat with new catalyst: ...]\n\n*Market: \"Question?\"*  [HIGH | MEDIUM]  edge Xpp\nCurrent: YES X¢ \u002F NO Y¢ | 24h vol $Xm | resolves: DATE\nFair YES: ~Y% (inputs: [src1], [src2], [src3])\nThesis: [one sentence - why the market is wrong, action implied]\nRisk: [one sentence - what could make your fair-value estimate wrong]\n\nsources: cg=ok|fail, dex=ok|fail, poly=ok|fail\nnot financial advice - pattern-matching only\n```\n\nIf only one of the two pick types qualifies, send just that one section (omit the other entirely — do not include a HIGH and a SKIP in the same message).\n\n### 6b. Notification — skip day\n\n```\n*Daily Pick - ${today}* - no picks\n\nToken signals weak today (best: SYMBOL @ score 3\u002F10).\nMarkets either thin liquidity or no defensible edge ≥ 5pp (best: \"Question?\" edge 2pp).\n\nTomorrow.\nsources: cg=ok|fail, dex=ok|fail, poly=ok|fail\n```\n\nIf all sources failed, send `TOKEN_PICK_NO_DATA` with the source-status line — do not invent picks from cached intuition.\n\n### 6c. Offer a deep-dive (force-reply — normal-day only)\n\nOnly after a **normal-day** send (6a) — never on the skip-day (6b) or the no-data path (weak signals → no pick, so no offer). This skill is `read-only`, so it can't run the deep report itself; instead it offers to hand off to **token-movers** (write mode), which owns the single-token deep report and the `deep-dive:` handler. Because `force_reply` and inline buttons can't share one message, send this as a SEPARATE `.\u002Fnotify` AFTER the 6a pick:\n\n```bash\n.\u002Fnotify \"Want a deeper report on a token? Reply with a ticker or contract.\" \\\n  --force-reply --placeholder \"e.g. WIF\" \\\n  --context \"token-movers::deep-dive\"\n```\n\nThe `token-movers::deep-dive` marker routes the operator's reply to **token-movers** as `var=\"deep-dive:\u003Ctheir text>\"`; token-movers strips the `deep-dive:` prefix and produces the single-token deep report.\n\n**Dedup.** token-pick runs once daily, so one offer per run is already once-per-day. Being `read-only`, it can't write a `FORCE_REPLY_OFFERED` marker — but it already reads recent logs, so if today's log already carries a `FORCE_REPLY_OFFERED: deep-dive` line (e.g. token-movers offered earlier today), SKIP this offer to avoid double-nagging.\n\n### 7. Log record\n\nThis skill is `read-only`, so the workflow's read-only guard writes its `### token-pick` log entry from your captured output; a self-written entry would be a duplicate. Don't append to `memory\u002Flogs\u002F` yourself - put this record in your **final output**:\n\n```\n### token-pick\n- **Token:** SYMBOL - $price (±X% 24h) - tier HIGH\u002FMEDIUM\u002FSKIP - score X\u002F10\n- **Token thesis:** [one line, including catalyst]\n- **Market:** \"Question?\" - YES X¢ - tier HIGH\u002FMEDIUM\u002FSKIP - edge Xpp\n- **Market thesis:** [one line, including fair-value estimate]\n- **Sources:** cg=ok|fail, dex=ok|fail, poly=ok|fail\n- **Notification sent:** yes (normal | skip | no-data)\n```\n\nAlso include symbol + market question on a single line for easy grep next-day dedup, e.g.:\n```\nTOKEN_PICK_DEDUP: SYMBOL | \"Will X happen by Y?\"\n```\n\n## Network note\n\nThere is no network sandbox — `curl` works, with **WebFetch** as the fallback for any URL fetch (CoinGecko, DexScreener, Polymarket all work without auth). For an auth'd API, call `.\u002Fsecretcurl` with a `{ENV_NAME}` placeholder (the key is injected via `requires:`). On total source failure, send the no-data notification rather than silent fail.\n\n## Environment Variables\n- `COINGECKO_API_KEY` — CoinGecko API key (optional, increases rate limits)\n\n## Constraints\n\n- **Never force a pick.** If signals are weak, the skip message IS the output.\n- **Never re-pick** the same token or market within 7 days unless you can state a new catalyst in one sentence.\n- **Show your work**: every score must show the breakdown; every edge must show the inputs.\n- Liquidity gates (mcap ≥ $20M for tokens, 24h vol ≥ $50k for markets) are hard floors — ignoring them turns the feed into a degen casino.\n- One token + one market max. Never bundle \"honorable mentions\" — that defeats the discipline.\n",{"name":5,"metadata":41,"description":7},{"var":42,"mode":25,"tags":43,"title":44,"category":30,"requires":45,"capabilities":47},"",[30],"Token Pick",[46],"COINGECKO_API_KEY?",[48,49],"external_api","sends_notifications","main","504a21d53c0c9b485f6e90c43db83000825e1d3c","skills\u002Ftoken-pick",308,"https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon","https:\u002F\u002Fwww.aeon.fun\u002F","https:\u002F\u002Fgithub.com\u002Faeonfun","The most autonomous agent framework.","2026-11-15 03:40:18",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add aeonfun\u002Faeon --skill token-pick",{"tool":65,"command":66},"bunx","bunx skills add aeonfun\u002Faeon --skill token-pick",{"tool":68,"command":69},"pnpm","pnpm dlx skills add aeonfun\u002Faeon --skill token-pick","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fskills\u002Ftoken-pick\u002FSKILL.md",true,[],[74,81,87,93,99,105],{"skillNo":75,"name":76,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":80},"01M7DSM3QWBJ44FKRMDDRAGNET","Warn Mixed Script","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fwarn-mixed-script\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":82,"name":83,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":80},"01M7DSM0496DRYYW5A4NAAHZDX","Warn Hidden CSS","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fwarn-hidden-css\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":80},"01M7DSKWCGDVYZSDJM31YHS2JB","Malicious Injection Uppercase","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fmalicious-injection-uppercase\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":80},"01M7DSKRV2RRA1V0HK13KYWJXD","Malicious Injection Homoglyph","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fmalicious-injection-homoglyph\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":80},"01M7DSKMXJKY0167YHVCKF7B49","Malicious Injection Disregard Prior","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fmalicious-injection-disregard-prior\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":80},"01M7DSKGFQ5V2VNSA4K97CVFMB","Benign Greek Math","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fbenign-greek-math\u002FSKILL.md",[],[]]