[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CZ4FSBSAZ04QN4ERXXJXF7":3,"skill-same:01M6CZ4FSBSAZ04QN4ERXXJXF7":64},{"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":31,"linkOnly":32,"markdownContent":33,"markdownBody":34,"frontMatter":35,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":44,"repositoryHtmlUrl":45,"repositoryHomepageUrl":46,"ownerHtmlUrl":47,"ownerBlogUrl":46,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M6CZ4FSBSAZ04QN4ERXXJXF7","action-converter",null,"5 concrete real-life actions, leverage-scored against open loops with specificity and anti-fluff gates","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\u002Faction-converter\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30],"converter","action converter","action","actions","Meta","open","basics","life","gates","leverage","loops","with","2026-11-10 10:12:30",false,"---\nname: action-converter\ndescription: 5 concrete real-life actions, leverage-scored against open loops with specificity and anti-fluff gates\nmetadata:\n  title: Action Converter\n  category: basics\n  var: \"\"\n  tags:\n    - meta\n---\n\u003C!-- autoresearch: variation B — sharper output via specificity gates, leverage scoring, banned-phrase lint, open-loop anchoring, empty-state taxonomy -->\n\n> **${var}** — Optional focus area (e.g. `health`, `networking`, `learning`, `shipping`, `crypto`, `repo`). If empty, covers all areas. Treated as a tiebreaker, not a hard filter.\n\nRead `memory\u002FMEMORY.md` for stated goals, \"Next Priorities\", tracked items, and current topics.\nRead the last 7 days of `memory\u002Flogs\u002F` for recent activity, patterns, and what's already been suggested or done.\nRead `memory\u002Ftopics\u002F` (every file) for active threads.\nRead `memory\u002Fcron-state.json` for failing or stuck skills.\nRead `memory\u002Fwatched-repos.md` for repos under attention.\nRead `output\u002Farticles\u002F` (last 7 days, filenames only — peek at the 2 most recent for theme).\nIf `soul\u002FSOUL.md` exists, read it for identity, voice, focus areas.\nRun `gh pr list --state open --limit 20 --json number,title,createdAt,isDraft,reviewDecision,headRefName 2>\u002Fdev\u002Fnull` to get open PRs (used to anchor \"ship\" \u002F \"review\" \u002F \"merge\" loops).\n\n**Graceful bootstrap** — each of the reads above may be missing on cold starts. For every source, if the file\u002Fdirectory is missing or empty (including `memory\u002Ftopics\u002F*.md`, `memory\u002Fcron-state.json`, and `gh pr list` returning empty or erroring), skip it and record `BOOTSTRAP: \u003Cresource> not yet populated` in the run's working notes. Continue with whatever signals are available — the skill must degrade gracefully, never fail. If every single source is empty, fall through to the `ACTION_CONVERTER_NO_CONTEXT` mode below.\n\n## Steps\n\n### 1. Detect mode\n\nDecide which exit mode this run will produce based on context volume:\n\n- **ACTION_CONVERTER_NO_CONTEXT** — if BOTH `memory\u002Flogs\u002F` has 0 entries AND `memory\u002FMEMORY.md` is the unmodified template (matches \"*Last consolidated: never*\" AND \"Configure notification channels\"). Notify the operator and stop — do not invent actions out of thin air.\n- **ACTION_CONVERTER_BOOTSTRAP** — if `memory\u002Flogs\u002F` has \u003C3 distinct dates in the last 14 days OR `memory\u002FMEMORY.md` \"Next Priorities\" still contains template entries (\"Configure notification channels\", \"Run first digest\"). Switch the action pool to setup-completion actions: enable specific skills in `aeon.yml`, configure missing notification secrets, run the first digest, populate `memory\u002Ftopics\u002F` for the first tracked thread, etc. These are still real, named, completable actions — not generic onboarding advice.\n- **ACTION_CONVERTER_OK** — otherwise. Use the full leverage-scored loop pipeline below.\n\n### 2. Extract open loops\n\nBuild a single deduped list of named open loops from every source above. A loop is a specific in-flight thing, not an area. Each loop captures at minimum: `id` (short slug), `text` (one phrase), `source` (where it came from), `age_days`, `urgency_signal` (deadline \u002F blocker \u002F stalled \u002F fresh).\n\nSources to mine:\n- **Open PRs** — every entry from `gh pr list`. Loop text: `PR #N: \u003Ctitle>` with urgency = `stalled` if >3 days old or review_decision is REQUEST_CHANGES.\n- **MEMORY.md \"Next Priorities\"** — each bullet becomes a loop. Skip template lines.\n- **`memory\u002Ftopics\u002F*.md`** — for each topic file, scan for headings or bullets that look like ongoing work (TODO, WIP, \"In progress\", \"Tracking\", trailing question marks, dated items in the last 30 days).\n- **`memory\u002Fcron-state.json`** — every skill with `consecutive_failures > 0` OR `last_status != success` becomes a loop: `fix \u003Cskill>`. Urgency = `blocker` if consecutive_failures ≥ 3.\n- **Recent logs (last 7 days)** — any line ending in `?`, containing \"blocked\", \"next:\", \"todo\", \"follow-up\", \"unfinished\", or naming a deferred decision.\n- **Recent articles (last 7 days)** — each new article opens a distribution\u002Fsyndication loop (\"syndicate \u003Cslug>\") if `syndicate-article` is enabled, and a feedback loop (\"respond to comments on \u003Cslug>\") if traffic is plausible.\n- **${var}** — if set, add a synthetic loop \"advance ${var}\" so at least one action ties to the requested focus area.\n\nDeduplicate by similarity in `text`. Cap the loop list at 25.\n\n### 3. Score loops\n\nScore every loop on three 1–5 axes. Total = leverage × urgency × concreteness.\n\n| Axis | 1 | 3 | 5 |\n|---|---|---|---|\n| **leverage** | personal hygiene | useful but local | unblocks others, shippable artifact, or compounds |\n| **urgency** | nice-to-have | this week | today (deadline \u002F blocker \u002F >5 day stall on hot loop) |\n| **concreteness** | \"think about X\" | known shape, no draft | next step is one named action |\n\nDrop any loop scoring \u003C8 from the candidate pool. If `${var}` is set, give a +0.5 leverage bump to loops touching that area.\n\n### 4. Convert loops to actions\n\nConvert the top loops into actions until you have 5 distinct ones. Constraints on every action:\n\n1. **Specificity gate** — must name at least one of: a file path, a PR number, a person\u002Fhandle, a project\u002Frepo, a tool\u002FCLI command, a URL, a tracked entity from MEMORY.md. Generic \"reach out to people\" \u002F \"review your goals\" \u002F \"explore opportunities\" fails this gate.\n2. **Banned-phrase lint** — reject any action whose `action` text contains: `go for a walk`, `drink water`, `take a break`, `reflect`, `journal`, `meditate`, `brainstorm`, `review your`, `think about`, `consider`, `look into`, `explore opportunities`, `reach out to people`, `network with`, `clean up your inbox`, `organize your`, `plan tomorrow`, `do some reading`, `check social media`. These are filler, not actions.\n3. **Time estimate** — must fit in ≤2 hours; bias toward 30–60 min slots.\n4. **Definition of done** — one observable check. \"PR opened\" \u002F \"commit pushed\" \u002F \"message sent to \u003Chandle>\" \u002F \"doc has section X with ≥3 items\". Not \"feel better\" or \"have more clarity\".\n5. **Anti-template (14-day novelty check)** — for each candidate action, extract the verb + main noun. Reject if the same verb+noun appears in any `memory\u002Flogs\u002F*.md` from the last 14 days. (Different verb+same noun is fine — only the bigram blocks.)\n6. **Score ≥4 on the 1–5 quality scale** below. Anything \u003C4 is dropped and replaced from the next loop in the queue.\n\nQuality 1–5: 1 = filler, 2 = vague, 3 = specific but low-leverage, 4 = specific + tied to a real loop, 5 = specific + high-leverage + would visibly move the project today.\n\nIf after exhausting the loop list you have \u003C5 surviving actions, fill the rest from the **category pool below** but only with category-specific candidates that pass all gates above. Categories exist as a fallback, not a checklist:\n- **Build** — ship, write, create, deploy, fix, prototype, refactor against a named file\u002FPR\n- **Connect** — DM\u002Freply\u002Fquote a *named* handle about a *named* topic; comment on a *named* PR\u002Fissue\n- **Learn** — read a *named* paper\u002Fdoc\u002Frepo and write a 5-bullet takeaway to `memory\u002Ftopics\u002F`\n- **Health\u002FEnergy** — only if tied to a named, novel, non-banned action (rare; usually skipped)\n- **Money** — concrete revenue\u002Ffunding\u002Fdeal step naming a counterparty\n- **Position** — write a *named* tweet\u002Fcast\u002Fpost on a *named* claim\n- **Explore** — lateral move tied to a named external signal from this week's logs\n\nIf even with the category pool you can't reach 5, output fewer (3 or 4) and flag `ACTION_CONVERTER_THIN` in the notify — don't pad.\n\n### 5. Compose the output\n\nBuild one **today's shape** line: ≤14 words capturing the dominant theme of the 5 actions (\"Ship 2 PRs, unblock failing skill, syndicate yesterday's article\" — not \"be productive today\"). This becomes the lede.\n\nOrder the 5 actions by descending quality score, then by descending urgency.\n\n### 6. Send via `.\u002Fnotify`\n\nUse this exact format (`.\u002Fnotify` renders the Markdown per-channel — just write it cleanly):\n\n```\n*5 Actions - ${today}*\nShape: \u003Ctoday's shape line>\n\n1. \u003Caction - one imperative sentence, names a specific entity>\nwhy: \u003C≤18 words, what makes this leverage today, names a specific signal>\ndone: \u003Cone observable check>\nloop: \u003Cloop id or \"category:\u003Cname>\" if filled from pool>\n\n2. \u003Caction>\nwhy: \u003C…>\ndone: \u003C…>\nloop: \u003C…>\n\n3. \u003Caction>\nwhy: \u003C…>\ndone: \u003C…>\nloop: \u003C…>\n\n4. \u003Caction>\nwhy: \u003C…>\ndone: \u003C…>\nloop: \u003C…>\n\n5. \u003Caction>\nwhy: \u003C…>\ndone: \u003C…>\nloop: \u003C…>\n\nsources: memory=\u003Clines> logs=\u003Cdays> topics=\u003Cfiles> prs=\u003Copen> cron_failing=\u003Cn> mode=\u003COK|BOOTSTRAP|THIN>\n```\n\nNotification rules:\n- Drop any action whose `done:` line couldn't be written without hand-waving.\n- If mode is `ACTION_CONVERTER_NO_CONTEXT`, skip the action list entirely and notify: `*Action Converter — no context yet*` plus a one-line pointer (\"Populate memory\u002FMEMORY.md or run a skill to seed memory\u002Flogs\u002F\").\n- If mode is `ACTION_CONVERTER_BOOTSTRAP`, prefix the shape line with `Bootstrap mode: ` and pull all actions from the setup-completion pool.\n\n### 7. Log to `memory\u002Flogs\u002F${today}.md`\n\nAppend:\n```\n### action-converter\n- **Mode:** OK | BOOTSTRAP | THIN | NO_CONTEXT\n- **Focus:** \u003Cvar or \"general\">\n- **Shape:** \u003Ctoday's shape line>\n- **Actions:** N (quality avg \u003Cx.x>\u002F5)\n- **Loops anchored:** \u003Clist of loop ids surfaced>\n- **Loops carried over:** \u003Clist of high-score loops not chosen, for tomorrow>\n- **Notification sent:** yes\n```\n\nCarrying loops forward in the log is what powers the 14-day novelty check and lets the next run see what's been deferred.\n\n## Network note\n\n`gh pr list` works in a GitHub Actions run via the `gh` CLI (handles auth internally, so no token touches the command line). If `gh` is unavailable or returns empty, treat the open-PR loop source as `prs=0` and continue — do not block the whole run.\n\nNo outbound HTTP is required. All inputs are local files and `gh`. No new env vars.\n","\u003C!-- autoresearch: variation B — sharper output via specificity gates, leverage scoring, banned-phrase lint, open-loop anchoring, empty-state taxonomy -->\n\n> **${var}** — Optional focus area (e.g. `health`, `networking`, `learning`, `shipping`, `crypto`, `repo`). If empty, covers all areas. Treated as a tiebreaker, not a hard filter.\n\nRead `memory\u002FMEMORY.md` for stated goals, \"Next Priorities\", tracked items, and current topics.\nRead the last 7 days of `memory\u002Flogs\u002F` for recent activity, patterns, and what's already been suggested or done.\nRead `memory\u002Ftopics\u002F` (every file) for active threads.\nRead `memory\u002Fcron-state.json` for failing or stuck skills.\nRead `memory\u002Fwatched-repos.md` for repos under attention.\nRead `output\u002Farticles\u002F` (last 7 days, filenames only — peek at the 2 most recent for theme).\nIf `soul\u002FSOUL.md` exists, read it for identity, voice, focus areas.\nRun `gh pr list --state open --limit 20 --json number,title,createdAt,isDraft,reviewDecision,headRefName 2>\u002Fdev\u002Fnull` to get open PRs (used to anchor \"ship\" \u002F \"review\" \u002F \"merge\" loops).\n\n**Graceful bootstrap** — each of the reads above may be missing on cold starts. For every source, if the file\u002Fdirectory is missing or empty (including `memory\u002Ftopics\u002F*.md`, `memory\u002Fcron-state.json`, and `gh pr list` returning empty or erroring), skip it and record `BOOTSTRAP: \u003Cresource> not yet populated` in the run's working notes. Continue with whatever signals are available — the skill must degrade gracefully, never fail. If every single source is empty, fall through to the `ACTION_CONVERTER_NO_CONTEXT` mode below.\n\n## Steps\n\n### 1. Detect mode\n\nDecide which exit mode this run will produce based on context volume:\n\n- **ACTION_CONVERTER_NO_CONTEXT** — if BOTH `memory\u002Flogs\u002F` has 0 entries AND `memory\u002FMEMORY.md` is the unmodified template (matches \"*Last consolidated: never*\" AND \"Configure notification channels\"). Notify the operator and stop — do not invent actions out of thin air.\n- **ACTION_CONVERTER_BOOTSTRAP** — if `memory\u002Flogs\u002F` has \u003C3 distinct dates in the last 14 days OR `memory\u002FMEMORY.md` \"Next Priorities\" still contains template entries (\"Configure notification channels\", \"Run first digest\"). Switch the action pool to setup-completion actions: enable specific skills in `aeon.yml`, configure missing notification secrets, run the first digest, populate `memory\u002Ftopics\u002F` for the first tracked thread, etc. These are still real, named, completable actions — not generic onboarding advice.\n- **ACTION_CONVERTER_OK** — otherwise. Use the full leverage-scored loop pipeline below.\n\n### 2. Extract open loops\n\nBuild a single deduped list of named open loops from every source above. A loop is a specific in-flight thing, not an area. Each loop captures at minimum: `id` (short slug), `text` (one phrase), `source` (where it came from), `age_days`, `urgency_signal` (deadline \u002F blocker \u002F stalled \u002F fresh).\n\nSources to mine:\n- **Open PRs** — every entry from `gh pr list`. Loop text: `PR #N: \u003Ctitle>` with urgency = `stalled` if >3 days old or review_decision is REQUEST_CHANGES.\n- **MEMORY.md \"Next Priorities\"** — each bullet becomes a loop. Skip template lines.\n- **`memory\u002Ftopics\u002F*.md`** — for each topic file, scan for headings or bullets that look like ongoing work (TODO, WIP, \"In progress\", \"Tracking\", trailing question marks, dated items in the last 30 days).\n- **`memory\u002Fcron-state.json`** — every skill with `consecutive_failures > 0` OR `last_status != success` becomes a loop: `fix \u003Cskill>`. Urgency = `blocker` if consecutive_failures ≥ 3.\n- **Recent logs (last 7 days)** — any line ending in `?`, containing \"blocked\", \"next:\", \"todo\", \"follow-up\", \"unfinished\", or naming a deferred decision.\n- **Recent articles (last 7 days)** — each new article opens a distribution\u002Fsyndication loop (\"syndicate \u003Cslug>\") if `syndicate-article` is enabled, and a feedback loop (\"respond to comments on \u003Cslug>\") if traffic is plausible.\n- **${var}** — if set, add a synthetic loop \"advance ${var}\" so at least one action ties to the requested focus area.\n\nDeduplicate by similarity in `text`. Cap the loop list at 25.\n\n### 3. Score loops\n\nScore every loop on three 1–5 axes. Total = leverage × urgency × concreteness.\n\n| Axis | 1 | 3 | 5 |\n|---|---|---|---|\n| **leverage** | personal hygiene | useful but local | unblocks others, shippable artifact, or compounds |\n| **urgency** | nice-to-have | this week | today (deadline \u002F blocker \u002F >5 day stall on hot loop) |\n| **concreteness** | \"think about X\" | known shape, no draft | next step is one named action |\n\nDrop any loop scoring \u003C8 from the candidate pool. If `${var}` is set, give a +0.5 leverage bump to loops touching that area.\n\n### 4. Convert loops to actions\n\nConvert the top loops into actions until you have 5 distinct ones. Constraints on every action:\n\n1. **Specificity gate** — must name at least one of: a file path, a PR number, a person\u002Fhandle, a project\u002Frepo, a tool\u002FCLI command, a URL, a tracked entity from MEMORY.md. Generic \"reach out to people\" \u002F \"review your goals\" \u002F \"explore opportunities\" fails this gate.\n2. **Banned-phrase lint** — reject any action whose `action` text contains: `go for a walk`, `drink water`, `take a break`, `reflect`, `journal`, `meditate`, `brainstorm`, `review your`, `think about`, `consider`, `look into`, `explore opportunities`, `reach out to people`, `network with`, `clean up your inbox`, `organize your`, `plan tomorrow`, `do some reading`, `check social media`. These are filler, not actions.\n3. **Time estimate** — must fit in ≤2 hours; bias toward 30–60 min slots.\n4. **Definition of done** — one observable check. \"PR opened\" \u002F \"commit pushed\" \u002F \"message sent to \u003Chandle>\" \u002F \"doc has section X with ≥3 items\". Not \"feel better\" or \"have more clarity\".\n5. **Anti-template (14-day novelty check)** — for each candidate action, extract the verb + main noun. Reject if the same verb+noun appears in any `memory\u002Flogs\u002F*.md` from the last 14 days. (Different verb+same noun is fine — only the bigram blocks.)\n6. **Score ≥4 on the 1–5 quality scale** below. Anything \u003C4 is dropped and replaced from the next loop in the queue.\n\nQuality 1–5: 1 = filler, 2 = vague, 3 = specific but low-leverage, 4 = specific + tied to a real loop, 5 = specific + high-leverage + would visibly move the project today.\n\nIf after exhausting the loop list you have \u003C5 surviving actions, fill the rest from the **category pool below** but only with category-specific candidates that pass all gates above. Categories exist as a fallback, not a checklist:\n- **Build** — ship, write, create, deploy, fix, prototype, refactor against a named file\u002FPR\n- **Connect** — DM\u002Freply\u002Fquote a *named* handle about a *named* topic; comment on a *named* PR\u002Fissue\n- **Learn** — read a *named* paper\u002Fdoc\u002Frepo and write a 5-bullet takeaway to `memory\u002Ftopics\u002F`\n- **Health\u002FEnergy** — only if tied to a named, novel, non-banned action (rare; usually skipped)\n- **Money** — concrete revenue\u002Ffunding\u002Fdeal step naming a counterparty\n- **Position** — write a *named* tweet\u002Fcast\u002Fpost on a *named* claim\n- **Explore** — lateral move tied to a named external signal from this week's logs\n\nIf even with the category pool you can't reach 5, output fewer (3 or 4) and flag `ACTION_CONVERTER_THIN` in the notify — don't pad.\n\n### 5. Compose the output\n\nBuild one **today's shape** line: ≤14 words capturing the dominant theme of the 5 actions (\"Ship 2 PRs, unblock failing skill, syndicate yesterday's article\" — not \"be productive today\"). This becomes the lede.\n\nOrder the 5 actions by descending quality score, then by descending urgency.\n\n### 6. Send via `.\u002Fnotify`\n\nUse this exact format (`.\u002Fnotify` renders the Markdown per-channel — just write it cleanly):\n\n```\n*5 Actions - ${today}*\nShape: \u003Ctoday's shape line>\n\n1. \u003Caction - one imperative sentence, names a specific entity>\nwhy: \u003C≤18 words, what makes this leverage today, names a specific signal>\ndone: \u003Cone observable check>\nloop: \u003Cloop id or \"category:\u003Cname>\" if filled from pool>\n\n2. \u003Caction>\nwhy: \u003C…>\ndone: \u003C…>\nloop: \u003C…>\n\n3. \u003Caction>\nwhy: \u003C…>\ndone: \u003C…>\nloop: \u003C…>\n\n4. \u003Caction>\nwhy: \u003C…>\ndone: \u003C…>\nloop: \u003C…>\n\n5. \u003Caction>\nwhy: \u003C…>\ndone: \u003C…>\nloop: \u003C…>\n\nsources: memory=\u003Clines> logs=\u003Cdays> topics=\u003Cfiles> prs=\u003Copen> cron_failing=\u003Cn> mode=\u003COK|BOOTSTRAP|THIN>\n```\n\nNotification rules:\n- Drop any action whose `done:` line couldn't be written without hand-waving.\n- If mode is `ACTION_CONVERTER_NO_CONTEXT`, skip the action list entirely and notify: `*Action Converter — no context yet*` plus a one-line pointer (\"Populate memory\u002FMEMORY.md or run a skill to seed memory\u002Flogs\u002F\").\n- If mode is `ACTION_CONVERTER_BOOTSTRAP`, prefix the shape line with `Bootstrap mode: ` and pull all actions from the setup-completion pool.\n\n### 7. Log to `memory\u002Flogs\u002F${today}.md`\n\nAppend:\n```\n### action-converter\n- **Mode:** OK | BOOTSTRAP | THIN | NO_CONTEXT\n- **Focus:** \u003Cvar or \"general\">\n- **Shape:** \u003Ctoday's shape line>\n- **Actions:** N (quality avg \u003Cx.x>\u002F5)\n- **Loops anchored:** \u003Clist of loop ids surfaced>\n- **Loops carried over:** \u003Clist of high-score loops not chosen, for tomorrow>\n- **Notification sent:** yes\n```\n\nCarrying loops forward in the log is what powers the 14-day novelty check and lets the next run see what's been deferred.\n\n## Network note\n\n`gh pr list` works in a GitHub Actions run via the `gh` CLI (handles auth internally, so no token touches the command line). If `gh` is unavailable or returns empty, treat the open-PR loop source as `prs=0` and continue — do not block the whole run.\n\nNo outbound HTTP is required. All inputs are local files and `gh`. No new env vars.\n",{"name":5,"metadata":36,"description":7},{"var":37,"tags":38,"title":40,"category":25},"",[39],"meta","Action Converter","main","504a21d53c0c9b485f6e90c43db83000825e1d3c","skills\u002Faction-converter",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":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add aeonfun\u002Faeon --skill action-converter",{"tool":56,"command":57},"bunx","bunx skills add aeonfun\u002Faeon --skill action-converter",{"tool":59,"command":60},"pnpm","pnpm dlx skills add aeonfun\u002Faeon --skill action-converter","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fskills\u002Faction-converter\u002FSKILL.md",true,[],[65,72,78,84,90,96],{"skillNo":66,"name":67,"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":68,"categories":69,"keywords":70,"publishedAt":71},"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":73,"name":74,"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":75,"categories":76,"keywords":77,"publishedAt":71},"01M7DSM0496DRYYW5A4NAAHZDX","Warn Hidden CSS","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fwarn-hidden-css\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"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":81,"categories":82,"keywords":83,"publishedAt":71},"01M7DSKWCGDVYZSDJM31YHS2JB","Malicious Injection Uppercase","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fmalicious-injection-uppercase\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"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":87,"categories":88,"keywords":89,"publishedAt":71},"01M7DSKRV2RRA1V0HK13KYWJXD","Malicious Injection Homoglyph","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fmalicious-injection-homoglyph\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"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":93,"categories":94,"keywords":95,"publishedAt":71},"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":97,"name":98,"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":99,"categories":100,"keywords":101,"publishedAt":71},"01M7DSKGFQ5V2VNSA4K97CVFMB","Benign Greek Math","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fbenign-greek-math\u002FSKILL.md",[],[]]