[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EJNYBTHFHZ2VTQEABDP476":3,"skill-same:01M7EJNYBTHFHZ2VTQEABDP476":58},{"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":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7EJNYBTHFHZ2VTQEABDP476","brand-audit",null,"Reverse-engineer an imprint's target design image into the imprint's references\u002Fvisual-audit.md (palette with sampled hex and approximate ratios, typography roles, spacing, composition, navigation, image behavior, mark, line weights, texture, hierarchy, repeated motifs), classifying every observation as core identity, candidate motif, or hero-specific, each a numbered proposal for the owner to check at PR review. Also freezes the target image from Notion into references\u002Ftarget-homepage.png. Trigger on \"\u002Fbrand-audit\", \"audit the Valesor target\", \"what's intentional in the S9 homepage\", \"freeze the new target image\", \"re-audit after the new mockup\". Requires the visual-designer role. Not for writing tokens or brand docs from an approved audit (visual-designer, directly), the illustration system (art-direction), checking built pages (brand-qa), or a game's concept images (that game's concept-art role).","valesordev\u002Fautomate.valesordev.com","valesordev","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F16853473?v=4","01M7EJN3ZVF4JZK1XGDEN3R3AB","Valesor Development","01M7EJN40C3HFMB7A0VHKYM6MZ",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fvalesordev\u002Fautomate.valesordev.com\u002Fblob\u002Fmain\u002Fplugins\u002Fvalesor-dev\u002Fskills\u002Fbrand-audit\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: brand-audit\ndescription: Reverse-engineer an imprint's target design image into the imprint's references\u002Fvisual-audit.md (palette with sampled hex and approximate ratios, typography roles, spacing, composition, navigation, image behavior, mark, line weights, texture, hierarchy, repeated motifs), classifying every observation as core identity, candidate motif, or hero-specific, each a numbered proposal for the owner to check at PR review. Also freezes the target image from Notion into references\u002Ftarget-homepage.png. Trigger on \"\u002Fbrand-audit\", \"audit the Valesor target\", \"what's intentional in the S9 homepage\", \"freeze the new target image\", \"re-audit after the new mockup\". Requires the visual-designer role. Not for writing tokens or brand docs from an approved audit (visual-designer, directly), the illustration system (art-direction), checking built pages (brand-qa), or a game's concept images (that game's concept-art role).\nargument-hint: \"\u003Cslug> [freeze \u003Cnotion-url> | revise]\"\nallowed-tools: Bash(.claude\u002Fbin\u002Frole:*) Bash(git log:*) Bash(git fetch:*) Bash(python3 -c:*) Bash(magick:*) Bash(identify:*)\n---\n\n# Brand audit\n\nRequest: `$ARGUMENTS`\n\nThe target is evidence, not a spec. This audit turns what it shows into\ndecisions the owner makes, one observation at a time. Nothing downstream (tokens,\nbrand docs, components) may cite the target directly: it cites the approved\naudit.\n\n## Preflight\n0. Run `.claude\u002Fbin\u002Frole require visual-designer ${CLAUDE_SESSION_ID}`. If it\n   fails, stop and tell the owner to run `\u002Frole visual-designer`.\n1. `git fetch origin`. Resolve the slug (`brands\u002F\u003Cslug>\u002F`). Read the imprint's\n   Notion \"Brand Kit Project Direction\" page (the role file or `brand\u002FREADME.md`\n   links it), any existing `brand\u002F` docs, and a previous `visual-audit.md`.\n\n## Freeze the target (`freeze`, or when `references\u002Ftarget-homepage.png` is missing)\n1. Fetch the image from the Notion page (the file block's download URL), and\n   save it as `references\u002Ftarget-homepage.png`. Never re-encode or resize it.\n2. Record its provenance in `references\u002FREADME.md`: the Notion page URL, file\n   name, pixel size, date fetched, and `sha256`.\n3. A target that changes later is a new freeze in its own commit, and the\n   audit gets a revision against it. Never overwrite silently.\n\n## Audit\nOpen the image and look at it, at full size and zoomed into each region.\nNever describe it from the Notion text alone. Fill `references\u002Faudit-template.md`:\n\n1. **Palette:** sample every distinct colour (`python3 -c` with Pillow, or\n   `magick … -unique-colors`, on regions you name), with hex values and\n   approximate area ratios. Note anything that looks like a generator\n   artefact (off-by-a-few greys, noise) rather than a colour decision.\n2. **Typography:** each text role (wordmark, display, body, mono metadata,\n   links, nav), with a likely typeface family or class, size ratio to body,\n   weight, case, and tracking. Name candidates for open-source, self-hostable\n   fonts, but choosing one is the owner's call.\n3. **Layout:** grid and columns, max width, gutters, vertical rhythm, rule\n   weights and where rules carry the layout.\n4. **Composition and image behavior:** how the hero sits (bleed, mask, empty\n   zone for type), crop behavior implied for mobile.\n5. **Navigation, mark, components:** header, nav, CTAs, cards and rows,\n   metadata blocks, footer. Each repeated pattern is a component candidate.\n6. **Line, texture, hierarchy, motifs:** line weights, texture layers, the\n   read order, and anything repeated.\n7. **Copy:** headlines, CTA wording, and voice signals visible in the image.\n8. **Tells:** pseudo-text, broken letterforms, impossible geometry, misspelt\n   names, wrong URLs. These are never core.\n\n## Classify\nEvery observation gets one class, marked `[PROPOSED P\u003Cn>]` (the next IDs\nunused in `brands\u002F\u003Cslug>\u002F`, per the role's Proposals section), with one line\nof reasoning:\n\n- **core identity:** persists across every application of the brand\n- **candidate motif:** worth testing in other applications before adopting\n- **hero-specific:** belongs to this composition only (it goes to a slot brief,\n  never to the brand docs)\n\nTest each proposed core item against the Notion page's direction (its\n\"character\", \"not\", and anti-pattern lists) and against the sibling\nimprints' approved audits. A core item that matches a sibling's core is a\ndistinctness flag: say so.\n\n## Ship\nThe audit goes in its own PR on a `design\u002F` branch, labeled\n`role:visual-designer`, after `\u002Fpre-pr`. The PR body has one checkbox per\nproposal, core items first, each at the start of a line:\n`- [ ] P\u003Cn>: \u003Cclass> — \u003Cobservation> (references\u002Fvisual-audit.md#\u003Csection>)`.\nThe owner decides at PR review: a checked box approves that ID, and one still\nunchecked at merge stays `[PROPOSED P\u003Cn>]`. Never tell them the audit is\napproved when merged. Record a reclassification or change they ask for in the\naudit's Decisions section, on the same branch. Checked IDs become\n`[DECIDED \u003CYYYY-MM-DD>, PR #\u003Cpr>, P\u003Cn>]` after the merge (the role's Proposals\nsection), never in the open PR.\n\nNever write `tokens\u002F`, `brand\u002Fvisual-language.md`, or component specs from an\nunmerged audit. Stop after the PR.\n\n## Output\nThe PR link, the count of core \u002F candidate \u002F hero-specific items, the\ndistinctness flags, open questions for the owner (at most five, each with a\nrecommendation), and one next action, usually \"review the audit PR\", or after\nmerge, \"derive tokens from the checked core palette and type\".\n","# Brand audit\n\nRequest: `$ARGUMENTS`\n\nThe target is evidence, not a spec. This audit turns what it shows into\ndecisions the owner makes, one observation at a time. Nothing downstream (tokens,\nbrand docs, components) may cite the target directly: it cites the approved\naudit.\n\n## Preflight\n0. Run `.claude\u002Fbin\u002Frole require visual-designer ${CLAUDE_SESSION_ID}`. If it\n   fails, stop and tell the owner to run `\u002Frole visual-designer`.\n1. `git fetch origin`. Resolve the slug (`brands\u002F\u003Cslug>\u002F`). Read the imprint's\n   Notion \"Brand Kit Project Direction\" page (the role file or `brand\u002FREADME.md`\n   links it), any existing `brand\u002F` docs, and a previous `visual-audit.md`.\n\n## Freeze the target (`freeze`, or when `references\u002Ftarget-homepage.png` is missing)\n1. Fetch the image from the Notion page (the file block's download URL), and\n   save it as `references\u002Ftarget-homepage.png`. Never re-encode or resize it.\n2. Record its provenance in `references\u002FREADME.md`: the Notion page URL, file\n   name, pixel size, date fetched, and `sha256`.\n3. A target that changes later is a new freeze in its own commit, and the\n   audit gets a revision against it. Never overwrite silently.\n\n## Audit\nOpen the image and look at it, at full size and zoomed into each region.\nNever describe it from the Notion text alone. Fill `references\u002Faudit-template.md`:\n\n1. **Palette:** sample every distinct colour (`python3 -c` with Pillow, or\n   `magick … -unique-colors`, on regions you name), with hex values and\n   approximate area ratios. Note anything that looks like a generator\n   artefact (off-by-a-few greys, noise) rather than a colour decision.\n2. **Typography:** each text role (wordmark, display, body, mono metadata,\n   links, nav), with a likely typeface family or class, size ratio to body,\n   weight, case, and tracking. Name candidates for open-source, self-hostable\n   fonts, but choosing one is the owner's call.\n3. **Layout:** grid and columns, max width, gutters, vertical rhythm, rule\n   weights and where rules carry the layout.\n4. **Composition and image behavior:** how the hero sits (bleed, mask, empty\n   zone for type), crop behavior implied for mobile.\n5. **Navigation, mark, components:** header, nav, CTAs, cards and rows,\n   metadata blocks, footer. Each repeated pattern is a component candidate.\n6. **Line, texture, hierarchy, motifs:** line weights, texture layers, the\n   read order, and anything repeated.\n7. **Copy:** headlines, CTA wording, and voice signals visible in the image.\n8. **Tells:** pseudo-text, broken letterforms, impossible geometry, misspelt\n   names, wrong URLs. These are never core.\n\n## Classify\nEvery observation gets one class, marked `[PROPOSED P\u003Cn>]` (the next IDs\nunused in `brands\u002F\u003Cslug>\u002F`, per the role's Proposals section), with one line\nof reasoning:\n\n- **core identity:** persists across every application of the brand\n- **candidate motif:** worth testing in other applications before adopting\n- **hero-specific:** belongs to this composition only (it goes to a slot brief,\n  never to the brand docs)\n\nTest each proposed core item against the Notion page's direction (its\n\"character\", \"not\", and anti-pattern lists) and against the sibling\nimprints' approved audits. A core item that matches a sibling's core is a\ndistinctness flag: say so.\n\n## Ship\nThe audit goes in its own PR on a `design\u002F` branch, labeled\n`role:visual-designer`, after `\u002Fpre-pr`. The PR body has one checkbox per\nproposal, core items first, each at the start of a line:\n`- [ ] P\u003Cn>: \u003Cclass> — \u003Cobservation> (references\u002Fvisual-audit.md#\u003Csection>)`.\nThe owner decides at PR review: a checked box approves that ID, and one still\nunchecked at merge stays `[PROPOSED P\u003Cn>]`. Never tell them the audit is\napproved when merged. Record a reclassification or change they ask for in the\naudit's Decisions section, on the same branch. Checked IDs become\n`[DECIDED \u003CYYYY-MM-DD>, PR #\u003Cpr>, P\u003Cn>]` after the merge (the role's Proposals\nsection), never in the open PR.\n\nNever write `tokens\u002F`, `brand\u002Fvisual-language.md`, or component specs from an\nunmerged audit. Stop after the PR.\n\n## Output\nThe PR link, the count of core \u002F candidate \u002F hero-specific items, the\ndistinctness flags, open questions for the owner (at most five, each with a\nrecommendation), and one next action, usually \"review the audit PR\", or after\nmerge, \"derive tokens from the checked core palette and type\".\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":25},"Bash(.claude\u002Fbin\u002Frole:*) Bash(git log:*) Bash(git fetch:*) Bash(python3 -c:*) Bash(magick:*) Bash(identify:*)","\u003Cslug> [freeze \u003Cnotion-url> | revise]","main","b09e02324f59072fe61171d826fc4335ef9610e0","plugins\u002Fvalesor-dev\u002Fskills\u002Fbrand-audit","https:\u002F\u002Fgithub.com\u002Fvalesordev\u002Fautomate.valesordev.com","https:\u002F\u002Fgithub.com\u002Fvalesordev","https:\u002F\u002Fvalesordev.com","Engineering imprint. Open-source tools and systems under Apache-2.0. Not a company — no clients, nothing for sale.","2026-10-28 21:44:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add valesordev\u002Fautomate.valesordev.com --skill brand-audit",{"tool":40,"command":41},"bunx","bunx skills add valesordev\u002Fautomate.valesordev.com --skill brand-audit",{"tool":43,"command":44},"pnpm","pnpm dlx skills add valesordev\u002Fautomate.valesordev.com --skill brand-audit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fvalesordev\u002Fautomate.valesordev.com\u002Fblob\u002Fmain\u002Fplugins\u002Fvalesor-dev\u002Fskills\u002Fbrand-audit\u002FSKILL.md",true,[48,54],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Faudit-template.md","REFERENCE","参考文档",1922,"https:\u002F\u002Fgithub.com\u002Fvalesordev\u002Fautomate.valesordev.com\u002Fblob\u002Fmain\u002Fplugins\u002Fvalesor-dev\u002Fskills\u002Fbrand-audit\u002Freferences\u002Faudit-template.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fexamples.md",2456,"https:\u002F\u002Fgithub.com\u002Fvalesordev\u002Fautomate.valesordev.com\u002Fblob\u002Fmain\u002Fplugins\u002Fvalesor-dev\u002Fskills\u002Fbrand-audit\u002Freferences\u002Fexamples.md",[59,66,73,80,87,94],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7EJS7KYNN064KE3900K61TE","up-skill","Upstream skill, for when the dependency's job is asked for. Not for local work.","https:\u002F\u002Fgithub.com\u002Fvalesordev\u002Fautomate.valesordev.com\u002Fblob\u002Fmain\u002Ftoolkit\u002Ftests\u002Ffixtures\u002Fupstream\u002Fplugins\u002Fupstream\u002Fskills\u002Fup-skill\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7EJS51M78001SRFHNFGZXRG","do-thing","Do the thing when asked to do the thing. Not for other things.","https:\u002F\u002Fgithub.com\u002Fvalesordev\u002Fautomate.valesordev.com\u002Fblob\u002Fmain\u002Ftoolkit\u002Ftests\u002Ffixtures\u002Fhome\u002Fplugins\u002Ftools\u002Fskills\u002Fdo-thing\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7EJS13JJ2KBQCS5NMNFCHZV","sre-start-sprint","Work the active sprint as SRE, with stories as GitHub issues. Observability review of the sprint's drafts first (architecture's contract review waits on it), then instrumentation verification for stories at review, then SRE's own backlog. Run once PM has activated the sprint; it also resumes a sprint already under way.","https:\u002F\u002Fgithub.com\u002Fvalesordev\u002Fautomate.valesordev.com\u002Fblob\u002Fmain\u002Fplugins\u002Fvalesor-dev\u002Fskills\u002Fsre-start-sprint\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7EJRSVF4W8JHVS71Z2KVTQE","sprint-run","Plan the active sprint's role lanes and, once the owner confirms, start them in parallel. Reads the board, shows which stories and queues each role the repo runs as a lane (implementation, architecture, SRE, PM, and where the charters say so visual-designer and product) can pick up now and what everything else is waiting on, then runs one isolated `claude -p` session per lane (own worktree, role set, hooks on) via `.claude\u002Fbin\u002Fcoordinator`, and reports from live state. Trigger on \"run the sprint\", \"\u002Fsprint-run\", \"start the lanes\", \"what can the agents pick up\", \"kick off implementation and SRE\". Not for working one story yourself (impl-start-sprint), activating or closing a sprint (pm-start-sprint, pm-close-sprint), or merging.","https:\u002F\u002Fgithub.com\u002Fvalesordev\u002Fautomate.valesordev.com\u002Fblob\u002Fmain\u002Fplugins\u002Fvalesor-dev\u002Fskills\u002Fsprint-run\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7EJRNMZGC9HHV92QW3WD9BK","role","Set this session's role (e.g. pm, product, architecture, sre, implementation, visual-designer, or none) and load its charter, then start an optional task given after the role; or show the current role when run with no argument, or the repo's role catalog with `help`. The owner runs it at session start. Never invoke it on your own or to change roles mid-task.","https:\u002F\u002Fgithub.com\u002Fvalesordev\u002Fautomate.valesordev.com\u002Fblob\u002Fmain\u002Fplugins\u002Fvalesor-dev\u002Fskills\u002Frole\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7EJRFQGMTZJMX24KCPQJTPT","release-review","Review a release's readiness across every delivery planner's board and repo (each feature's success signal, the milestones and stories delivering it, blockers and who owns them) and recommend go, no-go, or cut, written to docs\u002Fproduct\u002Freviews\u002F (one file per review). Trigger on \"\u002Frelease-review\", \"where are we on R1\", \"are we ready to ship\", \"what's blocking the release\", \"go\u002Fno-go\", and when a planner closes the last milestone a release names. Requires the product role. Not for sprint or cycle status (project-sync, producer-close-cycle), changing release scope (release-plan), or shipping or announcing anything (the owner).","https:\u002F\u002Fgithub.com\u002Fvalesordev\u002Fautomate.valesordev.com\u002Fblob\u002Fmain\u002Fplugins\u002Fvalesor-dev\u002Fskills\u002Frelease-review\u002FSKILL.md",[],[]]