[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CZC6A6F5E217B3EPSQZ75H":3,"skill-same:01M6CZC6A6F5E217B3EPSQZ75H":86},{"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":31,"publishedAt":52,"linkOnly":53,"markdownContent":54,"markdownBody":55,"frontMatter":56,"refName":63,"commitSha":64,"skillDirectory":65,"forksCount":66,"repositoryHtmlUrl":67,"repositoryHomepageUrl":68,"ownerHtmlUrl":69,"ownerBlogUrl":68,"ownerDescription":70,"updatedAt":71,"install":72,"resources":85},"01M6CZC6A6F5E217B3EPSQZ75H","skill-article",null,"Turn any skill in this instance into a publish-ready launch article - proof-stat headline, one contrarian thesis, mechanics, war stories from real run history, a mental-model reframe, and the full SKILL.md embedded verbatim so readers can steal it. Optional Higgsfield title banner with --banner.","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\u002Fskill-article\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"article","skill article","with","stories","can","banner","steal","title","reframe","full","run","publish","higgsfield","thesis","mechanics","Meta","basics","model","history","ready","2026-11-10 10:12:30",false,"---\nname: skill-article\ndescription: Turn any skill in this instance into a publish-ready launch article - proof-stat headline, one contrarian thesis, mechanics, war stories from real run history, a mental-model reframe, and the full SKILL.md embedded verbatim so readers can steal it. Optional Higgsfield title banner with --banner.\nmetadata:\n  title: Skill Article\n  category: basics\n  var: \"\"\n  tags:\n    - content\n    - meta\n---\n\n> **${var}** — Selector: `\u003Cskill-name> [--brand \u003Chandle>] [--banner]`.\n>\n> - **`\u003Cskill-name>`** → announce that skill (must exist under `skills\u002F\u003Cskill-name>\u002F`).\n> - **empty** → pick the most article-worthy skill from the last 14 days of `memory\u002Flogs\u002F`: prefer a skill that shipped recently, produced verified output, or hit a milestone. If nothing qualifies, log `SKILL_ARTICLE_NO_TARGET`, send no notification, and exit clean.\n> - **`--brand \u003Chandle>`** anywhere → byline\u002Fhandle for the outreach footer (default: this instance's public identity from `soul\u002F`, else the repo's org).\n> - **`--banner`** anywhere → also generate one 16:9 title banner through the Higgsfield MCP (spends credits; see Step 5). Off by default - a blank run never spends.\n>\n> Examples: `\"aeon-update\"`, `\"rug-scan --brand @myproject --banner\"`.\n\nToday is ${today}. Write a launch article for one skill, modeled on the security-industry \"skill announcement\" format: the article sells the *insight* the skill encodes, not the file - and then gives the file away.\n\n## Shared preamble\n\n1. Read `memory\u002FMEMORY.md` and the last 14 days of `memory\u002Flogs\u002F` - know what this skill has actually done.\n2. If a `soul\u002F` directory exists, read `soul\u002FSOUL.md` and `soul\u002FSTYLE.md` for voice. Default voice: terse, declarative, builder-wrote-this-fast.\n3. Read the target's full `skills\u002F\u003Cname>\u002FSKILL.md`. Every claim in the article must trace to a line in it.\n\n## Step 1 — Mine the track record (real numbers only)\n\nHunt for countable proof before writing a word:\n\n- `memory\u002Flogs\u002F` entries under the skill's `### \u003Cname>` headings: runs, OK\u002Ferror statuses, notable outcomes.\n- `output\u002F` files the skill produced; PRs or issues it opened (`gh pr list --search`).\n- `git log -- skills\u002F\u003Cname>\u002F` for ship date and iteration history.\n\nA real stat (\"84 verified findings\", \"31 runs, 0 false alarms\") becomes the headline. **If no real count exists, the headline uses the mechanism instead.** Never invent a number - a fabricated stat is the one thing that kills this format.\n\n## Step 2 — Find the thesis\n\nAnswer: **what does this skill see that the default workflow throws away?** That gap is the thesis.\n\nWrite 3 candidate contrast pairs (two-sided sentences like \"production code shows what the system does; tests show what its developers thought it did\") and keep the sharpest. Everything in the article hangs on this one insight.\n\n## Step 3 — Collect war stories\n\n1-3 concrete moments where the skill caught or produced something a naive approach would miss - pulled from `memory\u002Flogs\u002F` and `output\u002F`, anonymized where needed, mechanism kept visible.\n\nIf the skill has no run history yet, write \"how it plays out\" scenarios and **label them as scenarios**. Never dress a hypothetical as a case study.\n\n## Step 4 — Write the article\n\nStructure, in order:\n\n1. **Headline**: `\u003CSkill Name>: \u003Cproof stat or mechanism claim>`. Bold claim, not a setup.\n2. **Provenance** (2 short paragraphs): what it is, where it runs, ship date, track record if real.\n3. **Thesis section** with a punchy heading (a claim, never a label): what everyone else's workflow misses.\n4. **Mechanics** (2-4 short paragraphs) built around the contrast pair.\n5. **War stories**: one mini-heading per story, 2-4 sentences each, ending with the generalized pattern (\"The same blind spot appears when...\").\n6. **Reframe section**: the mental-model shift the reader keeps even if they never run the skill.\n7. **Ship it**: where it lives + one-line CTA (star the upstream repo).\n8. **`CODENAME: \u003CSkill Name>`**: the target SKILL.md embedded verbatim in a fenced block (use a 4-backtick fence - skill files contain 3-backtick fences). Do not paraphrase or trim it.\n9. **Outreach footer**: 1-2 sentences, DMs-open style, pointing at the brand handle.\n\n## Voice rules (the anti-tells)\n\n- Short declarative sentences. Cut every sentence that only sets up the next one.\n- Banned: \"revolutionary\", \"game-changing\", \"unleash\", \"delve\", \"Let's dive in\".\n- No parallel-structure trios, no \"not X, but Y\" scaffolding.\n- Section headings are claims or scenes (\"There is an alpha in the test folder\"), never labels (\"Overview\").\n- Verify the repo\u002Flink in the CTA exists this run before naming it.\n- Never reference private forks or internal accounts - describe this instance generically and point at the upstream\u002Fpublic repo.\n\n## Step 5 — Title banner (only with `--banner`)\n\nSkip this step entirely unless `--banner` was passed. When it was:\n\n1. **Check the connection first.** If no `mcp__higgsfield__*` tool is callable, the banner is skipped, not the article: note `banner: HIGGS_NOT_CONNECTED` for the log, point the operator at the dashboard → MCP → Connect Higgsfield in the notify, and continue to Step 6. Same on 401\u002Fstale auth (`banner: HIGGS_AUTH_STALE`) or insufficient credits (`banner: HIGGS_NO_CREDITS`). The article never fails because the banner did.\n2. **Build the prompt from the thesis, not the feature list.** The banner is a visual metaphor for the Step 2 contrast pair - the scene that makes the insight visible. Image models garble long text, so the only text allowed in the prompt is the skill's short name (or none); the headline lives in the article, not the pixels. Match `soul\u002F` aesthetic if it defines one; otherwise: clean, high-contrast, one focal object, no collage.\n3. **Generate exactly one image**, `--ar 16:9`, following the `higgsfield` skill's spend rules: one generation per run, one retry at most on a transient error, never re-submit a job that already succeeded. Poll to completion with a bounded number of polls; on timeout record `banner: HIGGS_FAILED` and move on.\n4. **Capture the asset URL verbatim.** Never fabricate one. Banner asset URLs may be time-limited signed URLs - flag that in the notify so the operator saves it.\n\nEmbed the result at the top of the article file, next to the alts block:\n\n```markdown\n\u003C!-- banner: \u003Casset-url> · model: \u003Cmodel> · job: \u003Cid> -->\n```\n\n## Step 6 — Deliver\n\n1. Write the article to `output\u002Fskill-articles\u002F${today}-\u003Cskill-name>.md` (Write tool; shell redirects into files are refused). Include an `\u003C!-- alts -->` comment block at the top with 2 alternative headline + thesis-heading pairs so the operator can iterate without a rewrite.\n2. Notify with `.\u002Fnotify -f \u002Ftmp\u002Fskill-article-notify.md` (write the body under `\u002Ftmp\u002F`): the headline, the thesis in one line, whether the stats are real or the headline fell back to mechanism, the banner URL when one was generated (with a save-it note if the URL is signed\u002Fexpiring), and a **clickable** link built from the run's environment:\n\n   ```bash\n   git remote get-url origin\n   ```\n\n   Take `owner\u002Frepo` from the printed URL and write it in literally: `https:\u002F\u002Fgithub.com\u002F\u003Cowner\u002Frepo>\u002Fblob\u002Fmain\u002Foutput\u002Fskill-articles\u002F\u003Cfile>.md`.\n\n3. Log to `memory\u002Flogs\u002F${today}.md` under a `### skill-article` heading: target skill, headline, thesis pair, stats-real-or-mechanism, output path, and - when `--banner` was passed - a `banner:` line (`HIGGS_OK \u003Curl>` | `HIGGS_NOT_CONNECTED` | `HIGGS_AUTH_STALE` | `HIGGS_NO_CREDITS` | `HIGGS_FAILED` | `skipped`). Status codes: `SKILL_ARTICLE_OK` on success, `SKILL_ARTICLE_NO_TARGET` when `${var}` was empty and nothing article-worthy exists, `SKILL_ARTICLE_NOT_FOUND` when the named skill has no `SKILL.md`.\n\n## Limits\n\n- This writes the article; it does not post it. Publishing is the operator's call (or a posting skill's, explicitly chained).\n- The banner is opt-in and spends real Higgsfield credits - one image per run, hard cap, and its failure never blocks the article.\n- Track-record mining is only as good as `memory\u002Flogs\u002F` - a skill that runs but never logs will read as unproven, and the article will say so rather than guess.\n- One skill per run. Announcing a pack is a different article; run once per skill instead.\n","> **${var}** — Selector: `\u003Cskill-name> [--brand \u003Chandle>] [--banner]`.\n>\n> - **`\u003Cskill-name>`** → announce that skill (must exist under `skills\u002F\u003Cskill-name>\u002F`).\n> - **empty** → pick the most article-worthy skill from the last 14 days of `memory\u002Flogs\u002F`: prefer a skill that shipped recently, produced verified output, or hit a milestone. If nothing qualifies, log `SKILL_ARTICLE_NO_TARGET`, send no notification, and exit clean.\n> - **`--brand \u003Chandle>`** anywhere → byline\u002Fhandle for the outreach footer (default: this instance's public identity from `soul\u002F`, else the repo's org).\n> - **`--banner`** anywhere → also generate one 16:9 title banner through the Higgsfield MCP (spends credits; see Step 5). Off by default - a blank run never spends.\n>\n> Examples: `\"aeon-update\"`, `\"rug-scan --brand @myproject --banner\"`.\n\nToday is ${today}. Write a launch article for one skill, modeled on the security-industry \"skill announcement\" format: the article sells the *insight* the skill encodes, not the file - and then gives the file away.\n\n## Shared preamble\n\n1. Read `memory\u002FMEMORY.md` and the last 14 days of `memory\u002Flogs\u002F` - know what this skill has actually done.\n2. If a `soul\u002F` directory exists, read `soul\u002FSOUL.md` and `soul\u002FSTYLE.md` for voice. Default voice: terse, declarative, builder-wrote-this-fast.\n3. Read the target's full `skills\u002F\u003Cname>\u002FSKILL.md`. Every claim in the article must trace to a line in it.\n\n## Step 1 — Mine the track record (real numbers only)\n\nHunt for countable proof before writing a word:\n\n- `memory\u002Flogs\u002F` entries under the skill's `### \u003Cname>` headings: runs, OK\u002Ferror statuses, notable outcomes.\n- `output\u002F` files the skill produced; PRs or issues it opened (`gh pr list --search`).\n- `git log -- skills\u002F\u003Cname>\u002F` for ship date and iteration history.\n\nA real stat (\"84 verified findings\", \"31 runs, 0 false alarms\") becomes the headline. **If no real count exists, the headline uses the mechanism instead.** Never invent a number - a fabricated stat is the one thing that kills this format.\n\n## Step 2 — Find the thesis\n\nAnswer: **what does this skill see that the default workflow throws away?** That gap is the thesis.\n\nWrite 3 candidate contrast pairs (two-sided sentences like \"production code shows what the system does; tests show what its developers thought it did\") and keep the sharpest. Everything in the article hangs on this one insight.\n\n## Step 3 — Collect war stories\n\n1-3 concrete moments where the skill caught or produced something a naive approach would miss - pulled from `memory\u002Flogs\u002F` and `output\u002F`, anonymized where needed, mechanism kept visible.\n\nIf the skill has no run history yet, write \"how it plays out\" scenarios and **label them as scenarios**. Never dress a hypothetical as a case study.\n\n## Step 4 — Write the article\n\nStructure, in order:\n\n1. **Headline**: `\u003CSkill Name>: \u003Cproof stat or mechanism claim>`. Bold claim, not a setup.\n2. **Provenance** (2 short paragraphs): what it is, where it runs, ship date, track record if real.\n3. **Thesis section** with a punchy heading (a claim, never a label): what everyone else's workflow misses.\n4. **Mechanics** (2-4 short paragraphs) built around the contrast pair.\n5. **War stories**: one mini-heading per story, 2-4 sentences each, ending with the generalized pattern (\"The same blind spot appears when...\").\n6. **Reframe section**: the mental-model shift the reader keeps even if they never run the skill.\n7. **Ship it**: where it lives + one-line CTA (star the upstream repo).\n8. **`CODENAME: \u003CSkill Name>`**: the target SKILL.md embedded verbatim in a fenced block (use a 4-backtick fence - skill files contain 3-backtick fences). Do not paraphrase or trim it.\n9. **Outreach footer**: 1-2 sentences, DMs-open style, pointing at the brand handle.\n\n## Voice rules (the anti-tells)\n\n- Short declarative sentences. Cut every sentence that only sets up the next one.\n- Banned: \"revolutionary\", \"game-changing\", \"unleash\", \"delve\", \"Let's dive in\".\n- No parallel-structure trios, no \"not X, but Y\" scaffolding.\n- Section headings are claims or scenes (\"There is an alpha in the test folder\"), never labels (\"Overview\").\n- Verify the repo\u002Flink in the CTA exists this run before naming it.\n- Never reference private forks or internal accounts - describe this instance generically and point at the upstream\u002Fpublic repo.\n\n## Step 5 — Title banner (only with `--banner`)\n\nSkip this step entirely unless `--banner` was passed. When it was:\n\n1. **Check the connection first.** If no `mcp__higgsfield__*` tool is callable, the banner is skipped, not the article: note `banner: HIGGS_NOT_CONNECTED` for the log, point the operator at the dashboard → MCP → Connect Higgsfield in the notify, and continue to Step 6. Same on 401\u002Fstale auth (`banner: HIGGS_AUTH_STALE`) or insufficient credits (`banner: HIGGS_NO_CREDITS`). The article never fails because the banner did.\n2. **Build the prompt from the thesis, not the feature list.** The banner is a visual metaphor for the Step 2 contrast pair - the scene that makes the insight visible. Image models garble long text, so the only text allowed in the prompt is the skill's short name (or none); the headline lives in the article, not the pixels. Match `soul\u002F` aesthetic if it defines one; otherwise: clean, high-contrast, one focal object, no collage.\n3. **Generate exactly one image**, `--ar 16:9`, following the `higgsfield` skill's spend rules: one generation per run, one retry at most on a transient error, never re-submit a job that already succeeded. Poll to completion with a bounded number of polls; on timeout record `banner: HIGGS_FAILED` and move on.\n4. **Capture the asset URL verbatim.** Never fabricate one. Banner asset URLs may be time-limited signed URLs - flag that in the notify so the operator saves it.\n\nEmbed the result at the top of the article file, next to the alts block:\n\n```markdown\n\u003C!-- banner: \u003Casset-url> · model: \u003Cmodel> · job: \u003Cid> -->\n```\n\n## Step 6 — Deliver\n\n1. Write the article to `output\u002Fskill-articles\u002F${today}-\u003Cskill-name>.md` (Write tool; shell redirects into files are refused). Include an `\u003C!-- alts -->` comment block at the top with 2 alternative headline + thesis-heading pairs so the operator can iterate without a rewrite.\n2. Notify with `.\u002Fnotify -f \u002Ftmp\u002Fskill-article-notify.md` (write the body under `\u002Ftmp\u002F`): the headline, the thesis in one line, whether the stats are real or the headline fell back to mechanism, the banner URL when one was generated (with a save-it note if the URL is signed\u002Fexpiring), and a **clickable** link built from the run's environment:\n\n   ```bash\n   git remote get-url origin\n   ```\n\n   Take `owner\u002Frepo` from the printed URL and write it in literally: `https:\u002F\u002Fgithub.com\u002F\u003Cowner\u002Frepo>\u002Fblob\u002Fmain\u002Foutput\u002Fskill-articles\u002F\u003Cfile>.md`.\n\n3. Log to `memory\u002Flogs\u002F${today}.md` under a `### skill-article` heading: target skill, headline, thesis pair, stats-real-or-mechanism, output path, and - when `--banner` was passed - a `banner:` line (`HIGGS_OK \u003Curl>` | `HIGGS_NOT_CONNECTED` | `HIGGS_AUTH_STALE` | `HIGGS_NO_CREDITS` | `HIGGS_FAILED` | `skipped`). Status codes: `SKILL_ARTICLE_OK` on success, `SKILL_ARTICLE_NO_TARGET` when `${var}` was empty and nothing article-worthy exists, `SKILL_ARTICLE_NOT_FOUND` when the named skill has no `SKILL.md`.\n\n## Limits\n\n- This writes the article; it does not post it. Publishing is the operator's call (or a posting skill's, explicitly chained).\n- The banner is opt-in and spends real Higgsfield credits - one image per run, hard cap, and its failure never blocks the article.\n- Track-record mining is only as good as `memory\u002Flogs\u002F` - a skill that runs but never logs will read as unproven, and the article will say so rather than guess.\n- One skill per run. Announcing a pack is a different article; run once per skill instead.\n",{"name":5,"metadata":57,"description":7},{"var":58,"tags":59,"title":62,"category":48},"",[60,61],"content","meta","Skill Article","main","fddec052c66754287c08582d49ae5fe6a3657221","skills\u002Fskill-article",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":73,"prompt":83,"zipAvailable":84},[74,77,80],{"tool":75,"command":76},"npx","npx skills add aeonfun\u002Faeon --skill skill-article",{"tool":78,"command":79},"bunx","bunx skills add aeonfun\u002Faeon --skill skill-article",{"tool":81,"command":82},"pnpm","pnpm dlx skills add aeonfun\u002Faeon --skill skill-article","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fskills\u002Fskill-article\u002FSKILL.md",true,[],[87,94,100,106,112,118],{"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":93},"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":95,"name":96,"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":97,"categories":98,"keywords":99,"publishedAt":93},"01M7DSM0496DRYYW5A4NAAHZDX","Warn Hidden CSS","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fwarn-hidden-css\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"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":103,"categories":104,"keywords":105,"publishedAt":93},"01M7DSKWCGDVYZSDJM31YHS2JB","Malicious Injection Uppercase","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fmalicious-injection-uppercase\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"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":109,"categories":110,"keywords":111,"publishedAt":93},"01M7DSKRV2RRA1V0HK13KYWJXD","Malicious Injection Homoglyph","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fmalicious-injection-homoglyph\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"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":115,"categories":116,"keywords":117,"publishedAt":93},"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":119,"name":120,"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":121,"categories":122,"keywords":123,"publishedAt":93},"01M7DSKGFQ5V2VNSA4K97CVFMB","Benign Greek Math","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fbenign-greek-math\u002FSKILL.md",[],[]]