[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CB8DWKBES8GFE1Z31MC003":3,"skill-same:01M7CB8DWKBES8GFE1Z31MC003":46},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M7CB8DWKBES8GFE1Z31MC003","vault-inbox",null,"Triage a .vault\u002Finbox\u002F drop zone into raw\u002F stubs or wiki\u002Fsummaries links, per that vault's own schema. Creates stubs only; never spawns deep-extraction subagents (that's \u002Fvault-summarize's job).","salomepoulain\u002Fmakery-stations","salomepoulain","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F136823771?v=4","01M7CB5VTPHHYMZVFGCT9YWMQW","Salomé Poulain","01M7CB5VVC773WAEPQM1HE1RTR",0,"MIT","https:\u002F\u002Fgithub.com\u002Fsalomepoulain\u002Fmakery-stations\u002Fblob\u002Fmain\u002Fstations\u002Fagent\u002Fworkbench\u002Fpantry\u002Fskills\u002Fvault-inbox\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: vault-inbox\ndescription: Triage a .vault\u002Finbox\u002F drop zone into raw\u002F stubs or wiki\u002Fsummaries links, per that vault's own schema. Creates stubs only; never spawns deep-extraction subagents (that's \u002Fvault-summarize's job).\nmetadata:\n  author: salomepoulain\n  source: makery-bakery\n---\n\n# \u002Fvault-inbox: triage the vault inbox\n\n## Preflight: confirm the vault (do this before anything else)\n\n1. Look for `.vault\u002F` at the repo root (it may be a symlink into a shadow dir, that's fine,\n   follow it). If the user names a specific vault\u002Fpath, use that instead.\n2. **If no `.vault\u002F` exists, stop here.** Don't create one, don't guess a structure, don't treat\n   some other folder as a vault; scaffolding a vault is a separate concern (the `vault`\n   makery station's job, not this skill's). Tell the user there's no vault and ask how they want\n   to proceed.\n3. Read `\u003Cvault>\u002F\u003CPREFIX>-schema.md`; every vault has exactly one, and it's the concrete source\n   of truth for that specific vault. The prefix is whatever that file uses (e.g. `sol-`); don't\n   assume it.\n4. From the schema, actually understand what the vault is composed of before touching anything:\n   its layers (`raw\u002F` ground-truth sources + stubs, `wiki\u002Fsummaries\u002F` AI-written extractions,\n   `wiki\u002Fatomic\u002F` human-only notes, `wiki\u002Fmaps\u002F` MOCs\u002Fmastery dashboards, `wiki\u002Flessons\u002F`\n   teaching transcripts where present, `inbox\u002F` the unsorted drop zone), which of those this\n   skill may touch, and its hard rules (no unconfident writeback, no AI writes to\n   `wiki\u002Fatomic\u002F`, etc.), not just enough to satisfy a frontmatter format.\n\nFor each item currently in `\u003Cvault>\u002Finbox\u002F` (skip `.keep`), decide where it belongs, per the\nschema's \"Processing the inbox\" section:\n\n1. **Genuinely a new source** (a document\u002Ftranscript\u002Fbook to treat as ground truth) →\n   - Move the file into `raw\u002F`, renamed to `\u003CPREFIX>-\u003Ckebab-case-title>.\u003Cext>` (strip junk like\n     download-site hashes\u002Fsuffixes from the original filename).\n   - Write a lightweight stub note `raw\u002F\u003CPREFIX>-\u003Cslug>.md`:\n     ```yaml\n     ---\n     type: source\n     title: \"Human-readable title\"\n     description: \"One-line description of what this source covers and why it's here\"\n     resource: \u003CPREFIX>-\u003Cslug>.\u003Cext>\n     tags: [\u003CPREFIX>, \u003Ca few topic tags>]\n     ---\n\n     Source: ![[\u003CPREFIX>-\u003Cslug>.\u003Cext>]]\n     ```\n   - Also add a `## Contents` section (see the schema's \"Table of contents\" section for the\n     exact format); read enough of the source's front matter to get its real chapter\u002Fsection\n     structure with page numbers. This is cheap (a handful of pages) and doesn't require the\n     full deep read that `\u002Fvault-summarize` does, so do it inline yourself, no subagent.\n   - If the source is clearly **assessment material** (a past exam, problem set, homework, quiz)\n     rather than expository\u002Fconceptual reading, tag it distinctly (add an `exam` tag alongside\n     the topic tags). It's still filed in `raw\u002F` like any other source; the tag is just so\n     `vault-teach` can find and calibrate lessons against it specifically.\n   - Do NOT read the rest of the source and do NOT write anything into `wiki\u002Fsummaries\u002F`;\n     that's `\u002Fvault-summarize`'s job, on purpose, so a big inbox drop doesn't silently trigger a\n     huge background read.\n\n2. **An extraction\u002Fsummary of something already in `raw\u002F`** → write it into `wiki\u002Fsummaries\u002F`\n   directly (it's already synthesized, no need to defer), following the schema's frontmatter and\n   hub-linking rules.\n\n3. **Too thin to confidently place** (a stray thought, ambiguous screenshot, not enough context)\n   → leave it in `inbox\u002F`, don't guess, and ask the user about it in your final report.\n\n4. **Never `wiki\u002Fatomic\u002F`**: human-written only. Surface it back instead.\n\nOnce an item is triaged (moved, or explicitly discarded as noise with the user's OK), remove it\nfrom `inbox\u002F`.\n\n## Bookkeeping (do this yourself, no subagents needed for triage)\n\n- Update `\u003CPREFIX>-index.md`: add one line per new `raw\u002F` and `wiki\u002Fsummaries\u002F` entry under the\n  right heading.\n- Append one entry to `\u003CPREFIX>-log.md`: `## [YYYY-MM-DD] ingest | inbox batch (N items)` with a\n  short list of what got filed where.\n\n## Folder guardrail\n\nIf any of this triage work is ever delegated to a subagent, it must be scoped to ONLY\n`inbox\u002F`, the one raw file\u002Fstub it's placing, and `wiki\u002Fsummaries\u002F` for direct-summary items;\nnever allowed to browse Downloads, other drives, the web, or other vault folders looking for\n\"better\" material on its own initiative. See `\u002Fvault-summarize`'s guardrail for why this is a\nhard rule, not a suggestion.\n\n## Report back\n\nList what got filed where (new raw sources with their tags, any direct-summary items), and flag\nanything left in `inbox\u002F` because it was too thin; ask the user about those explicitly. Mention\nthat `wiki\u002Fsummaries\u002F` deep-extraction hasn't run yet and point at `\u002Fvault-summarize` for that.\n","# \u002Fvault-inbox: triage the vault inbox\n\n## Preflight: confirm the vault (do this before anything else)\n\n1. Look for `.vault\u002F` at the repo root (it may be a symlink into a shadow dir, that's fine,\n   follow it). If the user names a specific vault\u002Fpath, use that instead.\n2. **If no `.vault\u002F` exists, stop here.** Don't create one, don't guess a structure, don't treat\n   some other folder as a vault; scaffolding a vault is a separate concern (the `vault`\n   makery station's job, not this skill's). Tell the user there's no vault and ask how they want\n   to proceed.\n3. Read `\u003Cvault>\u002F\u003CPREFIX>-schema.md`; every vault has exactly one, and it's the concrete source\n   of truth for that specific vault. The prefix is whatever that file uses (e.g. `sol-`); don't\n   assume it.\n4. From the schema, actually understand what the vault is composed of before touching anything:\n   its layers (`raw\u002F` ground-truth sources + stubs, `wiki\u002Fsummaries\u002F` AI-written extractions,\n   `wiki\u002Fatomic\u002F` human-only notes, `wiki\u002Fmaps\u002F` MOCs\u002Fmastery dashboards, `wiki\u002Flessons\u002F`\n   teaching transcripts where present, `inbox\u002F` the unsorted drop zone), which of those this\n   skill may touch, and its hard rules (no unconfident writeback, no AI writes to\n   `wiki\u002Fatomic\u002F`, etc.), not just enough to satisfy a frontmatter format.\n\nFor each item currently in `\u003Cvault>\u002Finbox\u002F` (skip `.keep`), decide where it belongs, per the\nschema's \"Processing the inbox\" section:\n\n1. **Genuinely a new source** (a document\u002Ftranscript\u002Fbook to treat as ground truth) →\n   - Move the file into `raw\u002F`, renamed to `\u003CPREFIX>-\u003Ckebab-case-title>.\u003Cext>` (strip junk like\n     download-site hashes\u002Fsuffixes from the original filename).\n   - Write a lightweight stub note `raw\u002F\u003CPREFIX>-\u003Cslug>.md`:\n     ```yaml\n     ---\n     type: source\n     title: \"Human-readable title\"\n     description: \"One-line description of what this source covers and why it's here\"\n     resource: \u003CPREFIX>-\u003Cslug>.\u003Cext>\n     tags: [\u003CPREFIX>, \u003Ca few topic tags>]\n     ---\n\n     Source: ![[\u003CPREFIX>-\u003Cslug>.\u003Cext>]]\n     ```\n   - Also add a `## Contents` section (see the schema's \"Table of contents\" section for the\n     exact format); read enough of the source's front matter to get its real chapter\u002Fsection\n     structure with page numbers. This is cheap (a handful of pages) and doesn't require the\n     full deep read that `\u002Fvault-summarize` does, so do it inline yourself, no subagent.\n   - If the source is clearly **assessment material** (a past exam, problem set, homework, quiz)\n     rather than expository\u002Fconceptual reading, tag it distinctly (add an `exam` tag alongside\n     the topic tags). It's still filed in `raw\u002F` like any other source; the tag is just so\n     `vault-teach` can find and calibrate lessons against it specifically.\n   - Do NOT read the rest of the source and do NOT write anything into `wiki\u002Fsummaries\u002F`;\n     that's `\u002Fvault-summarize`'s job, on purpose, so a big inbox drop doesn't silently trigger a\n     huge background read.\n\n2. **An extraction\u002Fsummary of something already in `raw\u002F`** → write it into `wiki\u002Fsummaries\u002F`\n   directly (it's already synthesized, no need to defer), following the schema's frontmatter and\n   hub-linking rules.\n\n3. **Too thin to confidently place** (a stray thought, ambiguous screenshot, not enough context)\n   → leave it in `inbox\u002F`, don't guess, and ask the user about it in your final report.\n\n4. **Never `wiki\u002Fatomic\u002F`**: human-written only. Surface it back instead.\n\nOnce an item is triaged (moved, or explicitly discarded as noise with the user's OK), remove it\nfrom `inbox\u002F`.\n\n## Bookkeeping (do this yourself, no subagents needed for triage)\n\n- Update `\u003CPREFIX>-index.md`: add one line per new `raw\u002F` and `wiki\u002Fsummaries\u002F` entry under the\n  right heading.\n- Append one entry to `\u003CPREFIX>-log.md`: `## [YYYY-MM-DD] ingest | inbox batch (N items)` with a\n  short list of what got filed where.\n\n## Folder guardrail\n\nIf any of this triage work is ever delegated to a subagent, it must be scoped to ONLY\n`inbox\u002F`, the one raw file\u002Fstub it's placing, and `wiki\u002Fsummaries\u002F` for direct-summary items;\nnever allowed to browse Downloads, other drives, the web, or other vault folders looking for\n\"better\" material on its own initiative. See `\u002Fvault-summarize`'s guardrail for why this is a\nhard rule, not a suggestion.\n\n## Report back\n\nList what got filed where (new raw sources with their tags, any direct-summary items), and flag\nanything left in `inbox\u002F` because it was too thin; ask the user about those explicitly. Mention\nthat `wiki\u002Fsummaries\u002F` deep-extraction hasn't run yet and point at `\u002Fvault-summarize` for that.\n",{"name":5,"metadata":24,"description":7},{"author":9,"source":25},"makery-bakery","main","4b7c39d99102c3553e0154cf6cd9d355474d2d5e","stations\u002Fagent\u002Fworkbench\u002Fpantry\u002Fskills\u002Fvault-inbox","https:\u002F\u002Fgithub.com\u002Fsalomepoulain\u002Fmakery-stations","https:\u002F\u002Fgithub.com\u002Fsalomepoulain","2026-11-05 19:59:44",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add salomepoulain\u002Fmakery-stations --skill vault-inbox",{"tool":38,"command":39},"bunx","bunx skills add salomepoulain\u002Fmakery-stations --skill vault-inbox",{"tool":41,"command":42},"pnpm","pnpm dlx skills add salomepoulain\u002Fmakery-stations --skill vault-inbox","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsalomepoulain\u002Fmakery-stations\u002Fblob\u002Fmain\u002Fstations\u002Fagent\u002Fworkbench\u002Fpantry\u002Fskills\u002Fvault-inbox\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7CBGSD6SJZFDYW6S7RGZWDB","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fsalomepoulain\u002Fmakery-stations\u002Fblob\u002Fmain\u002Fstations\u002Fclaude\u002Fworkbench\u002Fpantry\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7CBGJQA0MGJF0BX2DC4KWB9","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Fsalomepoulain\u002Fmakery-stations\u002Fblob\u002Fmain\u002Fstations\u002Fclaude\u002Fworkbench\u002Fpantry\u002Fskills\u002Fwrite-skills\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7CBGBQB29Y6TZ0CVSCYYM6M","write-mastery-website","Turn a mastery chapter into a clickable website (one HTML page published as an artifact) that looks like the LaTeX PDF. Solutions sit behind a blue bar, hints open one at a time, every solution line has a \"why\" toggle, MC options can be checked, and each exercise has a finished circle and a flag. Use when the user asks for the website, HTML or clickable version of a chapter, or for \u002Fwrite-mastery-website. The chapter content itself is written with write-mastery-chapter.","https:\u002F\u002Fgithub.com\u002Fsalomepoulain\u002Fmakery-stations\u002Fblob\u002Fmain\u002Fstations\u002Fclaude\u002Fworkbench\u002Fpantry\u002Fskills\u002Fwrite-mastery-website\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7CBFVG8QJXK0EN7CCNW1XWT","write-mastery-chapter","Use when authoring a new theory-then-practice study chapter for any subject as a LaTeX PDF (with figures and predict-the-picture exercises), or when revising a chapter this skill previously produced because a specific section was confusing during study.","https:\u002F\u002Fgithub.com\u002Fsalomepoulain\u002Fmakery-stations\u002Fblob\u002Fmain\u002Fstations\u002Fclaude\u002Fworkbench\u002Fpantry\u002Fskills\u002Fwrite-mastery-chapter\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7CBF2Z75S3T4NDHM1KFCCE6","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002Fsalomepoulain\u002Fmakery-stations\u002Fblob\u002Fmain\u002Fstations\u002Fclaude\u002Fworkbench\u002Fpantry\u002Fskills\u002Fwizard\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7CBF0HFTPND5KRPT39BYZST","wayfinder","Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.","https:\u002F\u002Fgithub.com\u002Fsalomepoulain\u002Fmakery-stations\u002Fblob\u002Fmain\u002Fstations\u002Fclaude\u002Fworkbench\u002Fpantry\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[]]