[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CZ2DXFAS2W5SY5CRYT6PZE":3,"skill-same:01M6CZ2DXFAS2W5SY5CRYT6PZE":54},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":26,"linkOnly":27,"markdownContent":28,"markdownBody":29,"frontMatter":30,"refName":31,"commitSha":32,"skillDirectory":33,"forksCount":34,"repositoryHtmlUrl":35,"repositoryHomepageUrl":36,"ownerHtmlUrl":37,"ownerBlogUrl":36,"ownerDescription":38,"updatedAt":39,"install":40,"resources":53},"01M6CZ2DXFAS2W5SY5CRYT6PZE","community-manager",null,"aeonfun\u002Faeon","aeonfun","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F287715280?v=4","01M6CZ23C6MXGMF4N0V1DZ1247","aeon","01M6CZ23GMZP1BR424J8Y8K3DG",792,"MIT","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fdocs\u002Fexamples\u002Fskill-templates\u002Fcommunity-manager\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25],"community","community manager","manager","2026-11-10 10:12:30",false,"---\nname: [REPLACE: SKILL_NAME]\ndescription: Summary of the [REPLACE: CHANNEL_PLATFORM] channel [REPLACE: CHANNEL_NAME] — top [REPLACE: TOP_N_THREADS] threads + open questions\nmetadata:\n  category: productivity\n  var: \"\"\n  tags:\n    - social\n  requires:\n    - DISCORD_BOT_TOKEN?\n    - DISCORD_CHANNEL_ID?\n    - TELEGRAM_BOT_TOKEN?\n    - TELEGRAM_CHAT_ID?\n    - SLACK_BOT_TOKEN?\n    - SLACK_CHANNEL_ID?\n---\n\n> **${var}** — Optional. Override the channel name. If empty, summarises `[REPLACE: CHANNEL_NAME]`.\n\nToday is ${today}. Read the last 24h of activity in **[REPLACE: CHANNEL_PLATFORM]** channel **[REPLACE: CHANNEL_NAME]** and produce a community digest.\n\n## Required secrets per platform\n\n| Platform | Secrets | Notes |\n|----------|---------|-------|\n| `discord` | `DISCORD_BOT_TOKEN`, `DISCORD_CHANNEL_ID` | Bot must be in the server with `View Channel` + `Read Message History`. |\n| `telegram` | `TELEGRAM_BOT_TOKEN`, `TELEGRAM_CHAT_ID` | Bot must have been added to the chat (private chats and groups both work). |\n| `slack` | `SLACK_BOT_TOKEN`, `SLACK_CHANNEL_ID` | Bot needs `channels:history` (public) or `groups:history` (private) scope. |\n\nRead the \"Keys set for this run\" line in your run notes, never a shell test (those are refused and cost a turn). If the secrets for `[REPLACE: CHANNEL_PLATFORM]` are not on it, log `COMMUNITY_NO_TOKEN` and exit cleanly.\n\n## Steps\n\n1. **Resolve channel** - the channel is `${var}` if set, else `[REPLACE: CHANNEL_NAME]`. A channel or chat ID is not a credential, so `.\u002Fsecretcurl` does not fill a `{DISCORD_CHANNEL_ID}` style placeholder: print the ID with its own call, `node -e 'console.log(process.env.DISCORD_CHANNEL_ID)'` (or `SLACK_CHANNEL_ID`), and write the printed value into the call literally (the `\u003CCHANNEL_ID>` below). The exact API call depends on `[REPLACE: CHANNEL_PLATFORM]`, one call each:\n\n   - **discord**:\n     ```bash\n     .\u002Fsecretcurl -s -o \u002Ftmp\u002Fcommunity-messages.json -w 'discord http=%{http_code}\\n' -H \"Authorization: Bot {DISCORD_BOT_TOKEN}\" \"https:\u002F\u002Fdiscord.com\u002Fapi\u002Fv10\u002Fchannels\u002F\u003CCHANNEL_ID>\u002Fmessages?limit=100\"\n     ```\n   - **telegram** - `getUpdates` polling has limits; better to read the bot's stored offset state from `memory\u002Ftopics\u002F[REPLACE: SKILL_NAME]-tg-offset.json` (Read it, then write the offset in literally):\n     ```bash\n     .\u002Fsecretcurl -s -o \u002Ftmp\u002Fcommunity-messages.json -w 'telegram http=%{http_code}\\n' \"https:\u002F\u002Fapi.telegram.org\u002Fbot{TELEGRAM_BOT_TOKEN}\u002FgetUpdates?offset=\u003COFFSET>&limit=100\"\n     ```\n   - **slack** - get the window start with its own call, `date -u -d '24 hours ago' +%s`, and write it in as `\u003COLDEST>`:\n     ```bash\n     .\u002Fsecretcurl -s -o \u002Ftmp\u002Fcommunity-messages.json -w 'slack http=%{http_code}\\n' -H \"Authorization: Bearer {SLACK_BOT_TOKEN}\" -G \"https:\u002F\u002Fslack.com\u002Fapi\u002Fconversations.history\" -d channel=\u003CCHANNEL_ID> -d oldest=\u003COLDEST> -d limit=200\n     ```\n\n2. **Filter to the last 24h** — drop messages older than `now - 24h`. Drop bot messages (most platforms expose `is_bot` \u002F `bot_id`). Keep replies.\n\n3. **Cluster into threads** — Discord and Slack expose explicit thread\u002Fparent IDs; Telegram doesn't. For Telegram, cluster by reply-chain hops.\n\n4. **Score threads** — for each thread:\n   - **Reach** — unique participants × log(message count).\n   - **Question pressure** — does the parent message end with `?` or contain words like \"how\", \"why\", \"anyone\", \"stuck\"? +5.\n   - **Recency** — within the last 12h gets full marks.\n\n   Pick the top **[REPLACE: TOP_N_THREADS]** threads.\n\n5. **Detect open questions** — scan all parent-level messages. If a message ends with `?` and has zero replies after 6 hours, mark it as `OPEN_QUESTION`. List them separately so the operator can chase.\n\n6. **Write `output\u002Farticles\u002F[REPLACE: SKILL_NAME]-${today}.md`**:\n   ```markdown\n   # [REPLACE: CHANNEL_NAME] — ${today}\n\n   **Volume**: N messages from M participants (vs 7d avg of K).\n\n   ## Top [REPLACE: TOP_N_THREADS] threads\n   1. [Author · timestamp] \"Parent message excerpt...\"\n      → N replies, M reactions\n      → Permalink\n\n   ...\n\n   ## Open questions (no reply > 6h)\n   - [Author] \"Question text...\" → permalink\n\n   ## Volume sparkline (last 7 days)\n   ▁▂▃▅▇▆▄\n   ```\n\n7. **Notify** via `.\u002Fnotify` with a 3-line summary:\n   ```\n   *[REPLACE: CHANNEL_NAME] — ${today}*\n   N messages · M participants · K open questions · top thread: \u003Cone-line>\n   Full digest: \u003Curl>\n   ```\n   Skip the notification on quiet days (volume \u003C 25% of 7d avg AND zero `OPEN_QUESTION`s).\n\n8. **Log** — append to `memory\u002Flogs\u002F${today}.md`:\n   ```\n   ## [REPLACE: SKILL_NAME]\n   - **Channel**: [REPLACE: CHANNEL_PLATFORM]\u002F[REPLACE: CHANNEL_NAME]\n   - **Volume**: messages=N, participants=M, vs_7d_avg=Δ%\n   - **Threads picked**: [REPLACE: TOP_N_THREADS] (of K candidates)\n   - **Open questions**: N\n   - **Status**: COMMUNITY_OK | COMMUNITY_QUIET | COMMUNITY_DEGRADED (api errors)\n   ```\n\n## Network note\n\nDiscord and Slack need their bot token in the `Authorization` header; Telegram puts it in the URL path (`\u002Fbot{TELEGRAM_BOT_TOKEN}\u002F`). A bare `$TOKEN` on a `curl` line is refused by the Bash permission analyzer - so call `.\u002Fsecretcurl` with a `{ENV_NAME}` placeholder instead. The token (injected via the skill's `requires:`) is substituted inside the helper and never appears on the command line, as in the step 1 calls.\n\n**Shell shape.** Each Bash call is one allowed command (pipes are fine). The run refuses a call that sets a variable (`CHANNEL=...`), uses `if` \u002F `for`, tests a key, joins commands with `;`, `&&` or `||`, redirects into a file, or puts a shell variable on a `.\u002Fsecretcurl` line (`$DISCORD_CHANNEL_ID`), and each refusal costs a model turn. So write IDs, offsets and dates into each call literally, save replies with `-o \u002Ftmp\u002F\u003Cfile>`, and write the offset file, the article and the log with Write\u002FEdit.\n\n## Constraints\n\n- **Privacy**. Don't quote DMs or anything from a private channel verbatim into a public notification — paraphrase, attribute by display name only, never include user IDs.\n- **The \"open questions\" section is the most useful output**. Even on a quiet day, if there's an unanswered question, surface it. That's the operator-action signal.\n- **Avoid bot-on-bot loops**. If this skill notifies into the same channel it reads from, filter your own bot's messages out before scoring.\n","> **${var}** — Optional. Override the channel name. If empty, summarises `[REPLACE: CHANNEL_NAME]`.\n\nToday is ${today}. Read the last 24h of activity in **[REPLACE: CHANNEL_PLATFORM]** channel **[REPLACE: CHANNEL_NAME]** and produce a community digest.\n\n## Required secrets per platform\n\n| Platform | Secrets | Notes |\n|----------|---------|-------|\n| `discord` | `DISCORD_BOT_TOKEN`, `DISCORD_CHANNEL_ID` | Bot must be in the server with `View Channel` + `Read Message History`. |\n| `telegram` | `TELEGRAM_BOT_TOKEN`, `TELEGRAM_CHAT_ID` | Bot must have been added to the chat (private chats and groups both work). |\n| `slack` | `SLACK_BOT_TOKEN`, `SLACK_CHANNEL_ID` | Bot needs `channels:history` (public) or `groups:history` (private) scope. |\n\nRead the \"Keys set for this run\" line in your run notes, never a shell test (those are refused and cost a turn). If the secrets for `[REPLACE: CHANNEL_PLATFORM]` are not on it, log `COMMUNITY_NO_TOKEN` and exit cleanly.\n\n## Steps\n\n1. **Resolve channel** - the channel is `${var}` if set, else `[REPLACE: CHANNEL_NAME]`. A channel or chat ID is not a credential, so `.\u002Fsecretcurl` does not fill a `{DISCORD_CHANNEL_ID}` style placeholder: print the ID with its own call, `node -e 'console.log(process.env.DISCORD_CHANNEL_ID)'` (or `SLACK_CHANNEL_ID`), and write the printed value into the call literally (the `\u003CCHANNEL_ID>` below). The exact API call depends on `[REPLACE: CHANNEL_PLATFORM]`, one call each:\n\n   - **discord**:\n     ```bash\n     .\u002Fsecretcurl -s -o \u002Ftmp\u002Fcommunity-messages.json -w 'discord http=%{http_code}\\n' -H \"Authorization: Bot {DISCORD_BOT_TOKEN}\" \"https:\u002F\u002Fdiscord.com\u002Fapi\u002Fv10\u002Fchannels\u002F\u003CCHANNEL_ID>\u002Fmessages?limit=100\"\n     ```\n   - **telegram** - `getUpdates` polling has limits; better to read the bot's stored offset state from `memory\u002Ftopics\u002F[REPLACE: SKILL_NAME]-tg-offset.json` (Read it, then write the offset in literally):\n     ```bash\n     .\u002Fsecretcurl -s -o \u002Ftmp\u002Fcommunity-messages.json -w 'telegram http=%{http_code}\\n' \"https:\u002F\u002Fapi.telegram.org\u002Fbot{TELEGRAM_BOT_TOKEN}\u002FgetUpdates?offset=\u003COFFSET>&limit=100\"\n     ```\n   - **slack** - get the window start with its own call, `date -u -d '24 hours ago' +%s`, and write it in as `\u003COLDEST>`:\n     ```bash\n     .\u002Fsecretcurl -s -o \u002Ftmp\u002Fcommunity-messages.json -w 'slack http=%{http_code}\\n' -H \"Authorization: Bearer {SLACK_BOT_TOKEN}\" -G \"https:\u002F\u002Fslack.com\u002Fapi\u002Fconversations.history\" -d channel=\u003CCHANNEL_ID> -d oldest=\u003COLDEST> -d limit=200\n     ```\n\n2. **Filter to the last 24h** — drop messages older than `now - 24h`. Drop bot messages (most platforms expose `is_bot` \u002F `bot_id`). Keep replies.\n\n3. **Cluster into threads** — Discord and Slack expose explicit thread\u002Fparent IDs; Telegram doesn't. For Telegram, cluster by reply-chain hops.\n\n4. **Score threads** — for each thread:\n   - **Reach** — unique participants × log(message count).\n   - **Question pressure** — does the parent message end with `?` or contain words like \"how\", \"why\", \"anyone\", \"stuck\"? +5.\n   - **Recency** — within the last 12h gets full marks.\n\n   Pick the top **[REPLACE: TOP_N_THREADS]** threads.\n\n5. **Detect open questions** — scan all parent-level messages. If a message ends with `?` and has zero replies after 6 hours, mark it as `OPEN_QUESTION`. List them separately so the operator can chase.\n\n6. **Write `output\u002Farticles\u002F[REPLACE: SKILL_NAME]-${today}.md`**:\n   ```markdown\n   # [REPLACE: CHANNEL_NAME] — ${today}\n\n   **Volume**: N messages from M participants (vs 7d avg of K).\n\n   ## Top [REPLACE: TOP_N_THREADS] threads\n   1. [Author · timestamp] \"Parent message excerpt...\"\n      → N replies, M reactions\n      → Permalink\n\n   ...\n\n   ## Open questions (no reply > 6h)\n   - [Author] \"Question text...\" → permalink\n\n   ## Volume sparkline (last 7 days)\n   ▁▂▃▅▇▆▄\n   ```\n\n7. **Notify** via `.\u002Fnotify` with a 3-line summary:\n   ```\n   *[REPLACE: CHANNEL_NAME] — ${today}*\n   N messages · M participants · K open questions · top thread: \u003Cone-line>\n   Full digest: \u003Curl>\n   ```\n   Skip the notification on quiet days (volume \u003C 25% of 7d avg AND zero `OPEN_QUESTION`s).\n\n8. **Log** — append to `memory\u002Flogs\u002F${today}.md`:\n   ```\n   ## [REPLACE: SKILL_NAME]\n   - **Channel**: [REPLACE: CHANNEL_PLATFORM]\u002F[REPLACE: CHANNEL_NAME]\n   - **Volume**: messages=N, participants=M, vs_7d_avg=Δ%\n   - **Threads picked**: [REPLACE: TOP_N_THREADS] (of K candidates)\n   - **Open questions**: N\n   - **Status**: COMMUNITY_OK | COMMUNITY_QUIET | COMMUNITY_DEGRADED (api errors)\n   ```\n\n## Network note\n\nDiscord and Slack need their bot token in the `Authorization` header; Telegram puts it in the URL path (`\u002Fbot{TELEGRAM_BOT_TOKEN}\u002F`). A bare `$TOKEN` on a `curl` line is refused by the Bash permission analyzer - so call `.\u002Fsecretcurl` with a `{ENV_NAME}` placeholder instead. The token (injected via the skill's `requires:`) is substituted inside the helper and never appears on the command line, as in the step 1 calls.\n\n**Shell shape.** Each Bash call is one allowed command (pipes are fine). The run refuses a call that sets a variable (`CHANNEL=...`), uses `if` \u002F `for`, tests a key, joins commands with `;`, `&&` or `||`, redirects into a file, or puts a shell variable on a `.\u002Fsecretcurl` line (`$DISCORD_CHANNEL_ID`), and each refusal costs a model turn. So write IDs, offsets and dates into each call literally, save replies with `-o \u002Ftmp\u002F\u003Cfile>`, and write the offset file, the article and the log with Write\u002FEdit.\n\n## Constraints\n\n- **Privacy**. Don't quote DMs or anything from a private channel verbatim into a public notification — paraphrase, attribute by display name only, never include user IDs.\n- **The \"open questions\" section is the most useful output**. Even on a quiet day, if there's an unanswered question, surface it. That's the operator-action signal.\n- **Avoid bot-on-bot loops**. If this skill notifies into the same channel it reads from, filter your own bot's messages out before scoring.\n",{},"main","fddec052c66754287c08582d49ae5fe6a3657221","docs\u002Fexamples\u002Fskill-templates\u002Fcommunity-manager",308,"https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon","https:\u002F\u002Fwww.aeon.fun\u002F","https:\u002F\u002Fgithub.com\u002Faeonfun","The most autonomous agent framework.","2026-11-14 00:57:36",{"source":7,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add aeonfun\u002Faeon --skill community-manager",{"tool":46,"command":47},"bunx","bunx skills add aeonfun\u002Faeon --skill community-manager",{"tool":49,"command":50},"pnpm","pnpm dlx skills add aeonfun\u002Faeon --skill community-manager","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fdocs\u002Fexamples\u002Fskill-templates\u002Fcommunity-manager\u002FSKILL.md",true,[],[55,82,109,133,158,180],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":26},"01M70R8RA3SFXK2D1XP7XTJGAQ","sns-digest","Digest Internet Computer governance - new and open NNS proposals and SNS DAO proposals - so the operator sees what is up for a vote without watching the dashboard. Fully public, no secret; fires only when there is something new to report.","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fskills\u002Fsns-digest\u002FSKILL.md",[],[62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81],"sns","digest","sns digest","proposals","for","up","open","icp","only","new","internet","when","api","notifications","dao","crypto","dashboard","governance","report","write",{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":91,"publishedAt":26},"01M70R5BMYW94KZ3XQM3MSWPC0","icp-deploy-check","Pre-deploy safety checklist for an Internet Computer Rust canister - read a local\u002Fcloned canister repo and verify the deploy-time footguns from the canister-security checklist (controller backup, anonymous-principal rejection, no mainnet fetch_root_key, upgrade safety) before it ships. Static, read-only, no network and no mainnet action.","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fskills\u002Ficp-deploy-check\u002FSKILL.md",[88],{"categoryNo":89,"categoryName":90,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[69,92,93,94,95,96,97,98,99,100,101,70,72,102,103,104,105,106,107,108],"icp deploy check","deploy check","check","deploy","fetch","anonymous","static","time","rust","local","upgrade","controller","read","Safety","network","action","security",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":123,"publishedAt":26},"01M70R312QZ9T236SZHGX8A8CM","canister-status","Monitor Internet Computer canisters for control-plane changes - a new controller, a module-hash change (upgrade), or a canister going missing from the public index - and alert the moment one happens. Uses only the public IC dashboard API.","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fskills\u002Fcanister-status\u002FSKILL.md",[115,118],{"categoryNo":116,"categoryName":117,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":119,"categoryName":120,"taxonomyType":121,"taxonomyTypeDesc":122},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[124,125,66,126,127,69,128,70,71,72,102,129,130,74,75,103,77,131,78,132],"canister status","status","missing","monitor","module","alert","plane","change","changes",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":141,"publishedAt":26},"01M6FVEXRG77BT4VH94P0S1TDT","you-web-search","Web search using You.com Search API with high-quality, cited results — runs keyless out of the box; YDC_API_KEY unlocks higher limits and real-time web crawling","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fskills\u002Fyou-web-search\u002FSKILL.md",[139,140],{"categoryNo":116,"categoryName":117,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":119,"categoryName":120,"taxonomyType":121,"taxonomyTypeDesc":122},[142,143,144,145,146,99,70,74,147,104,148,149,150,151,152,153,154,155,156,157],"web search","search","you","you web search","web","web crawling","read-only","real-time","basics","keyless","with","research","results","quality","high","limits",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":164,"publishedAt":26},"01M6FVER8Y2B0H7H26G4GTYK6N","write-tweet","Multi-format tweet studio - standalone drafts (10 across 5 size tiers), a 5-10 tweet thread, or 10 remixes of past tweets, selected via ${var}","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fskills\u002Fwrite-tweet\u002FSKILL.md",[],[81,165,166,167,74,168,169,150,170,171,172,173,174,175,176,177,178,179],"write tweet","social","studio","across","xai","twitter","multi","via","format","content","standalone","past","drafts","thread","size",{"skillNo":181,"name":182,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":184,"categories":185,"keywords":189,"publishedAt":26},"01M6FVENCJ0HY2TEE6CNZN4F96","weekly-aeoncard","Build a weekly token-consumption recap image from memory\u002Ftoken-usage.csv - this week + all-time totals, top skills, rendered as a shareable SVG card.","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fskills\u002Fweekly-aeoncard\u002FSKILL.md",[186],{"categoryNo":187,"categoryName":188,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",[190,191,192,193,194,195,196,99,197,198,199,200,201,75,202,203,81,204,11,205],"weekly aeoncard","weekly","as","usage","SVG","memory","card","Meta","image","recap","csv","monitoring","productivity","build","token","top"]