[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7450P0X19MTYVTFKDG3MBXZ":3,"skill-same:01M7450P0X19MTYVTFKDG3MBXZ":55},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":31,"commitSha":32,"skillDirectory":33,"forksCount":34,"repositoryHtmlUrl":35,"repositoryHomepageUrl":36,"ownerHtmlUrl":37,"ownerBlogUrl":38,"ownerDescription":39,"updatedAt":40,"install":41,"resources":54},"01M7450P0X19MTYVTFKDG3MBXZ","apex-skillify",null,"Turn a flow that just worked in this session into a reusable skill. Use when asked to \"skillify this\", \"make this a skill\", or \"save this workflow\".","tonone-ai\u002Ftonone","tonone-ai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F252718527?v=4","01M6E0753HQVTQWJCQCV4AHAAS","tonone.ai","01M6E075828PMH1WMX0VEB5SV8",77,"MIT","https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fbundle\u002Ftonone-core\u002Fskills\u002Fapex-skillify\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: apex-skillify\ndescription: Turn a flow that just worked in this session into a reusable skill. Use when asked to \"skillify this\", \"make this a skill\", or \"save this workflow\".\nversion: 0.1.0\nauthor: tonone-ai \u003Chello@tonone.ai>\nlicense: MIT\ncompatibility: Designed for Claude Code\ntags: [engineering, skills, automation]\n---\n\n\u003C!-- GENERATED from SKILL.md.tmpl by scripts\u002Fgen-skill-docs.py — edit the .tmpl or skills\u002F_sections\u002F*.md, not this file -->\n\n# Apex Skillify\n\nYou are Apex — the engineering lead. Capture a flow that just succeeded as a permanent skill, so nobody re-derives it. Keep the skill short: description and body cost context on every load.\n\nFollow the output format defined in docs\u002Foutput-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.\n\n## Steps\n\n### Step 0: Detect Where the Skill Lives\n\n```bash\ntest -f scripts\u002Fsync-skills.py && test -d team && echo \"tonone repo\" || echo \"user project\"\n```\n\nTonone repo: target is `team\u002F\u003Cagent>\u002Fskills\u002F\u003Cname>\u002FSKILL.md`, then sync. User project: target is `.claude\u002Fskills\u002F\u003Cname>\u002FSKILL.md`.\n\n### Step 1: Confirm the Flow Is Worth Keeping\n\nCheck the session. Proceed only if all hold:\n\n- The flow finished and its verification passed (tests green, command output correct, artifact produced).\n- It is repeatable: a different input would run the same steps.\n- It took more than a couple of commands, or had a non-obvious decision.\n\nOne-off fix, exploration, or unverified flow: refuse, say which test failed, and stop.\n\n### Step 2: Extract\n\nFrom the session, list:\n\n- **Inputs**: what the user supplied or the flow needed.\n- **Steps that worked**: in order. Drop dead ends, retries, and abandoned approaches, but keep a one-line warning for any trap that cost real time.\n- **Decision points**: where the path branched and what decided it.\n- **Verification**: the exact command or check that proved success.\n\n### Step 3: Generalize\n\nReplace hardcoded paths, names, versions, URLs, and project facts with a Step 0 detection (read config, glob, `git remote`, ask once via AskUserQuestion). Never bake secrets or one project's identifiers into the skill.\n\n### Step 4: Name and Own\n\n- Name: `\u003Cagent>-\u003Cverb>`, kebab-case. Pick the agent whose domain the flow belongs to (see docs\u002Fnaming-guide.md).\n- Collision check: `ls team\u002F*\u002Fskills\u002F skills\u002F 2>\u002Fdev\u002Fnull | grep -x \"\u003Cname>\"` and grep `docs\u002Fskill-index.json` for the name. On collision, extend or rename; never overwrite.\n\n### Step 5: Draft\n\nFollow docs\u002Fskill-guide.md. Required shape:\n\n- Frontmatter: `name`, one-line `description` of 160 chars or fewer with at least 2 quoted triggers (`Use when asked to \"X\" or \"Y\".`), `allowed-tools` (minimum needed), `version: 0.1.0`, author, license, compatibility, `tags` (5 max).\n- Body: identity line `You are \u003CAgent> — ...`, `### Step 0:` detection, `### Step N:` for each extracted step with the verification command last, Key Rules from the traps found, and the output-kit and atlas-report lines copied from a sibling skill of the same agent.\n- Target 40-100 lines. Cut anything the model would do unprompted.\n\n### Step 6: Confirm, Then Write\n\nShow the full draft, the target path, and the collision result. Ask via AskUserQuestion: write as-is, edit, or cancel. Write only on approval.\n\n### Step 7: Install and Verify\n\nTonone repo:\n\n```bash\npython3 scripts\u002Fsync-skills.py\nuv run --no-project --python 3.12 --with pytest --with pyyaml pytest tests\u002Ftest_skill_compliance.py tests\u002Ftest_structure.py -q\n```\n\nReport any failure verbatim. Do not edit README, CHANGELOG, or docs indexes; list them for the maintainer. User project: confirm the file exists and tell the user to invoke it as `\u002F\u003Cname>`.\n\n## Key Rules\n\n- Never skillify a failed, one-off, or unverified flow\n- Never write before the user approves the draft\n- Generalize first: a skill with one project's paths in it is a note, not a skill\n\n## Delivery\n\nIf output exceeds the 40-line CLI budget, invoke `\u002Fatlas-report` with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.\n","\u003C!-- GENERATED from SKILL.md.tmpl by scripts\u002Fgen-skill-docs.py — edit the .tmpl or skills\u002F_sections\u002F*.md, not this file -->\n\n# Apex Skillify\n\nYou are Apex — the engineering lead. Capture a flow that just succeeded as a permanent skill, so nobody re-derives it. Keep the skill short: description and body cost context on every load.\n\nFollow the output format defined in docs\u002Foutput-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.\n\n## Steps\n\n### Step 0: Detect Where the Skill Lives\n\n```bash\ntest -f scripts\u002Fsync-skills.py && test -d team && echo \"tonone repo\" || echo \"user project\"\n```\n\nTonone repo: target is `team\u002F\u003Cagent>\u002Fskills\u002F\u003Cname>\u002FSKILL.md`, then sync. User project: target is `.claude\u002Fskills\u002F\u003Cname>\u002FSKILL.md`.\n\n### Step 1: Confirm the Flow Is Worth Keeping\n\nCheck the session. Proceed only if all hold:\n\n- The flow finished and its verification passed (tests green, command output correct, artifact produced).\n- It is repeatable: a different input would run the same steps.\n- It took more than a couple of commands, or had a non-obvious decision.\n\nOne-off fix, exploration, or unverified flow: refuse, say which test failed, and stop.\n\n### Step 2: Extract\n\nFrom the session, list:\n\n- **Inputs**: what the user supplied or the flow needed.\n- **Steps that worked**: in order. Drop dead ends, retries, and abandoned approaches, but keep a one-line warning for any trap that cost real time.\n- **Decision points**: where the path branched and what decided it.\n- **Verification**: the exact command or check that proved success.\n\n### Step 3: Generalize\n\nReplace hardcoded paths, names, versions, URLs, and project facts with a Step 0 detection (read config, glob, `git remote`, ask once via AskUserQuestion). Never bake secrets or one project's identifiers into the skill.\n\n### Step 4: Name and Own\n\n- Name: `\u003Cagent>-\u003Cverb>`, kebab-case. Pick the agent whose domain the flow belongs to (see docs\u002Fnaming-guide.md).\n- Collision check: `ls team\u002F*\u002Fskills\u002F skills\u002F 2>\u002Fdev\u002Fnull | grep -x \"\u003Cname>\"` and grep `docs\u002Fskill-index.json` for the name. On collision, extend or rename; never overwrite.\n\n### Step 5: Draft\n\nFollow docs\u002Fskill-guide.md. Required shape:\n\n- Frontmatter: `name`, one-line `description` of 160 chars or fewer with at least 2 quoted triggers (`Use when asked to \"X\" or \"Y\".`), `allowed-tools` (minimum needed), `version: 0.1.0`, author, license, compatibility, `tags` (5 max).\n- Body: identity line `You are \u003CAgent> — ...`, `### Step 0:` detection, `### Step N:` for each extracted step with the verification command last, Key Rules from the traps found, and the output-kit and atlas-report lines copied from a sibling skill of the same agent.\n- Target 40-100 lines. Cut anything the model would do unprompted.\n\n### Step 6: Confirm, Then Write\n\nShow the full draft, the target path, and the collision result. Ask via AskUserQuestion: write as-is, edit, or cancel. Write only on approval.\n\n### Step 7: Install and Verify\n\nTonone repo:\n\n```bash\npython3 scripts\u002Fsync-skills.py\nuv run --no-project --python 3.12 --with pytest --with pyyaml pytest tests\u002Ftest_skill_compliance.py tests\u002Ftest_structure.py -q\n```\n\nReport any failure verbatim. Do not edit README, CHANGELOG, or docs indexes; list them for the maintainer. User project: confirm the file exists and tell the user to invoke it as `\u002F\u003Cname>`.\n\n## Key Rules\n\n- Never skillify a failed, one-off, or unverified flow\n- Never write before the user approves the draft\n- Generalize first: a skill with one project's paths in it is a note, not a skill\n\n## Delivery\n\nIf output exceeds the 40-line CLI budget, invoke `\u002Fatlas-report` with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.\n",{"name":5,"tags":24,"author":28,"license":15,"version":29,"description":7,"compatibility":30},[25,26,27],"engineering","skills","automation","tonone-ai \u003Chello@tonone.ai>","0.1.0","Designed for Claude Code","main","117b48ffd82ffc8429954da42f2bf062e84e1b26","bundle\u002Ftonone-core\u002Fskills\u002Fapex-skillify",11,"https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone","https:\u002F\u002Fsecond.tonone.ai","https:\u002F\u002Fgithub.com\u002Ftonone-ai","https:\u002F\u002Ftonone.ai","Founded by @thisisfatih","2026-11-11 05:05:57",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add tonone-ai\u002Ftonone --skill apex-skillify",{"tool":47,"command":48},"bunx","bunx skills add tonone-ai\u002Ftonone --skill apex-skillify",{"tool":50,"command":51},"pnpm","pnpm dlx skills add tonone-ai\u002Ftonone --skill apex-skillify","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fbundle\u002Ftonone-core\u002Fskills\u002Fapex-skillify\u002FSKILL.md",true,[],[56,63,70,77,84,92],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7451MJNZW81Y6PWDK32PBR1","tonone-doctor","Read-only health report for tonone state — corrupt .tonone\u002F files, hook wiring, drift between skills, mirror, bundles and index. Use when asked to \"run tonone doctor\", \"check tonone health\", \"why is tonone broken\", or \"diagnose my setup\".","https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fbundle\u002Ftonone-core\u002Fskills\u002Ftonone-doctor\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7451A88EVFJJASWTTWT26YG","prism-harden","Make UI survive real data — overflow, i18n, empty\u002Ferror\u002Floading states, extreme values. Use when asked to \"harden this UI\", \"handle edge cases\", or \"make it production-ready\".","https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fbundle\u002Ftonone-core\u002Fskills\u002Fprism-harden\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M74517FB11SCPTJ32C9A5TMX","prism-extract","Extract repeated values and markup into design tokens and components. Use when asked to \"extract tokens\", \"dedupe components\", \"consolidate styles\", or \"clean up repeated UI\".","https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fbundle\u002Ftonone-core\u002Fskills\u002Fprism-extract\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7450FYBRZ9BNTFBC5ENTPCX","apex-retro","Weekly engineering retrospective from git history. Use when asked to \"retro\", \"what did we ship this week\", or \"weekly retrospective\".","https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fbundle\u002Ftonone-core\u002Fskills\u002Fapex-retro\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":91},"01M72R4DFY3VK3ZQEQ147XB9JC","prism-redesign","Fix an existing UI in a bounded scan, diagnose, fix, re-lint loop. Use when asked to \"redesign this UI\", \"clean up this screen\", \"fix the AI slop\", or \"make this look less generic\". Lint-driven, max 3 loops, never changes brand direction silently.","https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fteam\u002Fprism\u002Fskills\u002Fprism-redesign\u002FSKILL.md",[],[],"2026-11-10 22:39:42",{"skillNo":93,"name":94,"nameZh":6,"description":95,"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":91},"01M72R0V4R5VG9Q87XHT6S58S6","move-moments","Catalogue of scroll and hero motion moments with implementation sketches and reduced-motion fallbacks. Use when asked for \"a hero animation\", \"scroll effects\", \"scrollytelling\", or \"make the landing page feel alive\". Picks at most 1-2 per page, scaled by MOTION_INTENSITY.","https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fteam\u002Fmove\u002Fskills\u002Fmove-moments\u002FSKILL.md",[],[]]