[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BQF849YC558ZJE73TH2BZX":3,"skill-same:01M7BQF849YC558ZJE73TH2BZX":144},{"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":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":38,"ownerHtmlUrl":39,"ownerBlogUrl":6,"ownerDescription":40,"updatedAt":41,"install":42,"resources":55},"01M7BQF849YC558ZJE73TH2BZX","od-contribute",null,"One-click contribution flow for Open Design (nexu-io\u002Fopen-design) — even for non-coders. Pick one of four cards (ship a Skill or Design System you made with OD; translate docs; fix a typo \u002F write a blog; report a bug), the agent validates and opens a PR (or issue) for you. Trigger words contribute to open design, ship my OD skill, ship my OD design system, translate OD docs, report an OD bug, od-contribute.","YYC-Cube\u002FYYC3-Knowledge-Base","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79J2PHVK3F6ZBYT8K2SCZCW",1,"MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002F.claude\u002Fskills\u002Fod-contribute\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: od-contribute\ndescription: One-click contribution flow for Open Design (nexu-io\u002Fopen-design) — even for non-coders. Pick one of four cards (ship a Skill or Design System you made with OD; translate docs; fix a typo \u002F write a blog; report a bug), the agent validates and opens a PR (or issue) for you. Trigger words contribute to open design, ship my OD skill, ship my OD design system, translate OD docs, report an OD bug, od-contribute.\nallowed-tools:\n  - Bash\n  - Read\n  - Write\n  - Edit\n  - AskUserQuestion\n  - TaskCreate\n  - TaskUpdate\n  - WebFetch\n---\n\n# od-contribute — first-contribution flow for Open Design\n\nLocked to `nexu-io\u002Fopen-design`. Branches by **contribution type**, not by issue. Replaces the dev-loop with type-specific no-code validators. Designed so a product user with zero coding background can ship a real PR.\n\n## Language\n\nMirror the user's language in every user-facing message — `AskUserQuestion` labels and descriptions, status updates, error explanations. Detect from their first message; when uncertain, default to English.\n\n**Generated artifacts (PR titles, commit messages, PR\u002Fissue body files, branch names) MUST be English** regardless of the user's chat language. GitHub conventions, maintainer review, and search all assume English. The templates under `templates\u002F` are already English — keep them that way when rendering.\n\nScripts live under `scripts\u002F`. Source the shared helpers from any script:\n\n```bash\nsource \"$(dirname \"$0\")\u002Fconfig.sh\"\n```\n\n`SKILL_DIR` below = the directory that contains this `SKILL.md`.\n\n---\n\n## Step 1 — Prereq check (always first)\n\n```bash\nbash \"$SKILL_DIR\u002Fscripts\u002Fcheck-prereqs.sh\"\n```\n\n- Exit 0: capture `GH_USER=\u003Clogin>` from stdout. Default `TARGET_FORK=\"${GH_USER}\u002Fopen-design\"`.\n- Exit 2: surface the printed install \u002F auth hint **verbatim** and stop. Do not attempt token workarounds.\n\nIf `gh repo view \"$TARGET_FORK\"` fails, ask the user (one `AskUserQuestion`) whether to fork now via `gh repo fork nexu-io\u002Fopen-design --clone=false`. Default to yes.\n\n## Step 2 — Pick contribution type\n\nSingle `AskUserQuestion` (header: \"Contribution\", multiSelect: false), four options. Translate option labels\u002Fdescriptions into the user's chat language; the branch routing is unchanged.\n\n1. **🎨 Ship something I made with OD** — _a Skill, Design System, HyperFrame, or template I want to contribute upstream_ → branch `3a`\n2. **🌍 Translate OD docs** — _README \u002F QUICKSTART \u002F CONTRIBUTING into a new language_ → branch `3b`\n3. **📝 Fix docs \u002F write a blog \u002F fix a typo** — _typo fix, dead link, use-case writeup_ → branch `3c`\n4. **🐛 Report a bug** — _something broke; I'll help turn it into a high-quality issue_ → branch `3d` (issue path, no PR)\n\nEach branch below is self-contained. Steps 7–8 (preview + push) are shared across branches `3a`\u002F`3b`\u002F`3c`. Branch `3d` skips them entirely.\n\n---\n\n### Step 3a — OD product submission (Skill \u002F Design System)\n\n**3a.1** Ask user: \"What's the local path to the artifact you want to ship?\" (single free-text, translated into the user's chat language). Common: a folder path (Skill) or a single `DESIGN.md` file (Design System).\n\n**3a.2** Sniff type:\n\n```bash\n# Skill: folder containing SKILL.md with frontmatter.\n# Design System: file matching DESIGN.md anatomy.\n```\n\nIf ambiguous, ask the user to confirm.\n\n**3a.3** Run setup:\n\n```bash\nbash \"$SKILL_DIR\u002Fscripts\u002Fsetup-workspace.sh\" skill \u003Cslug>\n# or\nbash \"$SKILL_DIR\u002Fscripts\u002Fsetup-workspace.sh\" design-system \u003Cslug>\n```\n\n`\u003Cslug>` is `od::slugify` of the Skill `name` frontmatter field or of the brand name. Capture `WORKDIR` from stdout.\n\n**3a.4** Copy artifact into workspace at the right target dir:\n- Skill → `$WORKDIR\u002Fskills\u002F\u003Cslug>\u002F`\n- Design System → `$WORKDIR\u002Fdesign-systems\u002F\u003Cbrand-slug>\u002FDESIGN.md` (+ any sibling assets in the same folder)\n\n**3a.5** Validate:\n\n```bash\nbash \"$SKILL_DIR\u002Fscripts\u002Fvalidate-skill-submission.sh\" \"$WORKDIR\u002Fskills\u002F\u003Cslug>\"\n# or, with 1-2 reference DESIGN.md files passed in:\nbash \"$SKILL_DIR\u002Fscripts\u002Fvalidate-design-system.sh\" \\\n  \"$WORKDIR\u002Fdesign-systems\u002F\u003Cslug>\u002FDESIGN.md\" \\\n  --reference \"$WORKDIR\u002Fdesign-systems\u002Fairbnb\u002FDESIGN.md\" \\\n  --reference \"$WORKDIR\u002Fdesign-systems\u002Fapple\u002FDESIGN.md\"\n```\n\nIf validation fails, surface the FAIL lines verbatim, ask the user to fix, retry. **Never push a failing artifact.**\n\n**3a.6** Ask 3 short questions via `AskUserQuestion` (translate the labels into the user's chat language):\n- \"What name should we credit you under in the PR?\" — free-text\n- \"One-line pitch for this Skill \u002F Design System?\" — free-text\n- \"Path to a screenshot (optional)?\" — free-text\n\n**3a.7** Render `templates\u002FPR-BODY-skill.md` (or `PR-BODY-design-system.md`) with substitutions:\n- `{{SKILL_NAME}}`, `{{SKILL_SLUG}}` (or `{{BRAND_NAME}}`, `{{BRAND_SLUG}}`)\n- `{{PITCH}}` (the one-line)\n- `{{MOTIVATION}}` (free-text — agent can offer to draft this from the skill body, but user confirms)\n- `{{TRY_PROMPT}}` (a prompt they recommend trying — agent suggests a default, user confirms)\n- `{{SCREENSHOT_BLOCK}}` (Markdown image block if a screenshot path was given, else empty)\n- `{{DISCORD_INVITE}}` from `$OD_DISCORD_INVITE`\n\nWrite to `$WORKDIR\u002F.od-contrib\u002FPR-BODY.md`.\n\n→ Jump to **Step 7**.\n\n---\n\n### Step 3b — i18n translation\n\n**3b.1** Setup workspace (slug = `translate-\u003Cdoc>-\u003Clang>` if known, else `translate`):\n\n```bash\nbash \"$SKILL_DIR\u002Fscripts\u002Fsetup-workspace.sh\" i18n translate\n# capture WORKDIR\n```\n\n**3b.2** Discover gaps:\n\n```bash\nbash \"$SKILL_DIR\u002Fscripts\u002Fdiscover-i18n-gaps.sh\" \"$WORKDIR\" > \u002Ftmp\u002Fod-i18n-gaps.json\n```\n\nEach line is JSON. Rank by:\n- `status: \"missing\"` first (missing language is highest leverage)\n- then `status: \"stale\"` ordered by `english_commits_since_translation` desc\n- README family before QUICKSTART before CONTRIBUTING\n\n**3b.3** Take the top 3–4 gaps and present via `AskUserQuestion` (header: \"Translation target\"). Each option label like: `README → 한국어 (Korean)` \u002F `QUICKSTART (zh-CN) refresh — 12 commits behind`. Translate the header text into the user's chat language but keep the option labels descriptive (the language names belong in their native script).\n\n**3b.4** Once user picks, **rename branch** to be specific:\n```bash\ngit -C \"$WORKDIR\" branch -m \"od-contrib\u002Fi18n\u002F\u003Cdoc>-\u003Clang>-\u003Cdate>\"\n```\n(or pre-set the slug in step 3b.1 if the user confirmed earlier.)\n\n**3b.5** Translate. Read the English source. Translate **structure-preserving**:\n- Code blocks: leave untranslated\n- Brand \u002F product names: leave untranslated\n- Filenames in inline code: leave untranslated\n- Image \u002F link targets: leave untranslated; if a localized version of a linked doc exists, swap the link to the localized file\n- Headings: translate, keep the heading depth identical\n- Tables: translate cell text only, keep alignment \u002F pipes\n\nWrite the result to `$WORKDIR\u002F\u003CTRANSLATED_PATH>` (e.g. `QUICKSTART.es.md`). Show user a unified diff vs. the English source for visual sanity-check (line-count delta within ±15% is a healthy signal).\n\n**3b.6** Validate the translated file against the English source. The `--reference` flag tells the validator to ignore relative refs that were already broken in the source — OD docs frequently link to website route slugs (e.g. `skills\u002Fblog-post\u002F`) that aren't files on disk; we don't want a structure-preserving translation to fail because of pre-existing dead refs.\n\n```bash\nbash \"$SKILL_DIR\u002Fscripts\u002Fvalidate-markdown.sh\" \\\n  \"$WORKDIR\u002F\u003CTRANSLATED_PATH>\" \\\n  --reference \"$WORKDIR\u002F\u003CENGLISH_PATH>\"\n```\n\nIf FAIL → surface verbatim, fix, retry.\n\n**3b.7** Render `templates\u002FPR-BODY-i18n.md` with `{{DOC_NAME}}`, `{{LANG_DISPLAY_NAME}}`, `{{LANG_CODE}}`, `{{TRANSLATED_PATH}}`, `{{ENGLISH_PATH}}`, `{{STATUS}}`, `{{TRANSLATION_NOTES}}` (one paragraph from the agent: anything tricky, untranslated terms it kept, etc.), `{{DISCORD_INVITE}}`.\n\n→ **Step 7**.\n\n---\n\n### Step 3c — Docs \u002F blog \u002F typo\n\n**3c.1** Setup workspace (slug `docs`):\n\n```bash\nbash \"$SKILL_DIR\u002Fscripts\u002Fsetup-workspace.sh\" docs \u003Cslug>\n```\n\n**3c.2** Ask user (one `AskUserQuestion`):\n1. **Auto-discover small fixes** (run discover-doc-gaps, pick something)\n2. **I have a specific fix in mind** (free-text)\n3. **I want to write a blog \u002F case study** (free-text — what's the use case?)\n\n**3c.3 (Auto-discover branch)** Run:\n\n```bash\nbash \"$SKILL_DIR\u002Fscripts\u002Fdiscover-doc-gaps.sh\" \"$WORKDIR\" > \u002Ftmp\u002Fod-doc-gaps.json\n```\n\nGroup by `kind` (typo \u002F deadlink \u002F todo). Show the user up to 6 candidates via `AskUserQuestion`. Once picked, apply the fix in code (typo: replace word; deadlink: ask user for the new URL; todo: that's a proper task, ask user to write the missing prose).\n\n**3c.4 (Specific-fix branch)** Read the file, apply user's described change. Confirm via diff.\n\n**3c.5 (Blog branch)** First check whether OD has a blog directory:\n\n```bash\nls \"$WORKDIR\u002Fdocs\" 2>\u002Fdev\u002Fnull\n```\n\nIf a `docs\u002Fblog\u002F` or similar exists, place the new post there. If not, ask the user where it should live, defaulting to `docs\u002F\u003Cslug>.md`. Generate an outline → user fills in user-specific bits (their use case, screenshots, the prompt they used, the rendered output) → agent stitches into a final Markdown.\n\n**3c.6** Validate every changed\u002Fadded file. For files that already exist in the repo (typo fix, dead-link fix, doc edit), pass `--reference` pointing at HEAD's version so we only fail on relative refs the user *introduced*, not on pre-existing route slugs:\n\n```bash\n# For modifications to existing files:\ngit -C \"$WORKDIR\" show \"HEAD:\u003Cpath>\" > \"\u002Ftmp\u002Fod-contrib-orig-\u003Cbasename>\" 2>\u002Fdev\u002Fnull\nbash \"$SKILL_DIR\u002Fscripts\u002Fvalidate-markdown.sh\" \\\n  \"$WORKDIR\u002F\u003Cchanged-path>\" \\\n  --reference \"\u002Ftmp\u002Fod-contrib-orig-\u003Cbasename>\"\n\n# For brand-new files (e.g. a blog post the user is creating from scratch),\n# omit --reference. The validator will skip the relative-ref check entirely\n# (since it can't tell route slugs from real paths in isolation).\n```\n\n**3c.7** Render `templates\u002FPR-BODY-docs.md` with `{{ONE_LINE_SUMMARY}}`, `{{DETAILS}}`, `{{FILES_LIST}}`, `{{DISCORD_INVITE}}`.\n\n→ **Step 7**.\n\n---\n\n### Step 3d — Bug report (issue path, no PR)\n\n**3d.1** Read OD's actual schema at runtime to make sure we mirror it:\n\n```bash\ngh api \"repos\u002F${TARGET_REPO}\u002Fcontents\u002F.github\u002FISSUE_TEMPLATE\u002Fbug-report.yml\" --jq .content | base64 -d > \u002Ftmp\u002Fod-bug-report.yml\n```\n\nIf the schema has drifted from the template (`templates\u002FISSUE-BODY-bug.md`), regenerate the body to match.\n\n**3d.2** Ask the user via `AskUserQuestion`, one structured prompt per critical field. Use **plain language**, not the YAML field names:\n\n| Bug-report field | Prompt to user |\n|---|---|\n| `description` | \"What went wrong? One sentence is fine.\" |\n| `steps` | \"How can I reproduce it? Walk me through step by step.\" |\n| `expected` | \"What did you expect to happen?\" |\n| `version` | \"Which OD version are you running? (About menu, or `od --version`)\" |\n| `platform` | dropdown: macOS (Apple Silicon) \u002F macOS (Intel) \u002F Windows \u002F Linux \u002F Other |\n| `logs` | \"Any error logs you can paste? Skip if you don't have them.\" |\n| `screenshots` | \"Path to a screenshot? Skip if you don't have one.\" |\n\nTranslate every prompt above into the user's chat language at runtime.\n\n**3d.3** Auto-collect what we can (these don't need to ask the user):\n- OS family from `uname`\n- Node version from `node -v` if relevant\n\n**3d.4** Dedupe: extract 3–5 keywords from the description, run:\n\n```bash\ngh search issues \"\u003Ckeywords>\" --repo \"$TARGET_REPO\" --state open --limit 5 --json number,title,url\n```\n\nIf matches exist, present them to the user via `AskUserQuestion` (translate to user's language): \"These existing issues look related. Do you want to: (a) comment on an existing one, (b) open a new issue anyway, (c) cancel?\"\n\n**3d.5** If proceeding with new issue, render `templates\u002FISSUE-BODY-bug.md` and submit:\n\n```bash\nbash \"$SKILL_DIR\u002Fscripts\u002Fcreate-issue.sh\" \\\n  --title \"$TITLE\" \\\n  --body-file \"$WORKDIR_OR_TMP\u002F.od-contrib\u002FISSUE-BODY.md\" \\\n  --dedupe-keywords \"\u003Ckeywords>\"\n```\n\n**3d.6** Print the issue URL on its own line. **Do not** push branches or open PRs from this branch.\n\n---\n\n## Step 7 — Preview + confirm (shared, PR branches only)\n\nShow the user a clean summary:\n\n```text\nAbout to commit:\n  Branch:  od-contrib\u002F\u003Ctype>\u002F\u003Cslug>-\u003Cdate>\n  Files:\n    + skills\u002Ffoo\u002FSKILL.md            (1.2 KB)\n    + skills\u002Ffoo\u002Fpreview.png         (54 KB)\n  Push to:  \u003Cfork or upstream>\n  Open PR:  nexu-io\u002Fopen-design:main ← \u003Cfork>:\u003Cbranch>\n```\n\nThen `git -C \"$WORKDIR\" diff --stat` and a `head -40` of the rendered PR body for visual sanity.\n\nRequired `AskUserQuestion` confirmation (translate to user's language): **\"Push this PR?\"** with three options:\n- **Ship it** — proceed to Step 8\n- **Let me revise** — return to the relevant Step 3 sub-step\n- **Cancel** — leave the workspace on disk, tell the user the path so they can return later, exit\n\nNever push without an explicit \"Ship it\".\n\n## Step 8 — Push & open PR\n\n```bash\nbash \"$SKILL_DIR\u002Fscripts\u002Fcreate-pr.sh\" \\\n  --workdir \"$WORKDIR\" \\\n  --type \"\u003Cskill|design-system|i18n|docs>\" \\\n  --title \"\u003CPR title from references\u002Fnewcomer-tone.md>\" \\\n  --body-file \"$WORKDIR\u002F.od-contrib\u002FPR-BODY.md\"\n```\n\nPrint the PR URL on its own line. Done.\n\n---\n\n## Safety rails (mandatory)\n\n- Never push to `main` \u002F `master` \u002F `develop`. The push scripts refuse.\n- Never `--force` push. Just don't.\n- All workspace activity stays under `$OD_WORK_ROOT` (default `$HOME\u002Fod-contrib-work`). `od::assert_in_workroot` enforces this.\n- Bug-report path **always** runs the dedupe search before `gh issue create`.\n- Honor user memory: skip GitHub user `xxiaoxiong` from any contributor lookup ([[feedback_no_outreach_xxiaoxiong]]).\n\n## When NOT to use this skill\n\n- The user wants to fix a daemon \u002F web bug or add a feature with code changes → use `auto-github-contributor` instead (it has the TDD loop). This skill deliberately doesn't run lint\u002Ftypecheck\u002Ftests because content paths don't need them.\n- The user wants to *generate* a Skill \u002F Design System from scratch → that's Open Design itself. Run OD first, get an artifact, then come back here to ship it.\n","# od-contribute — first-contribution flow for Open Design\n\nLocked to `nexu-io\u002Fopen-design`. Branches by **contribution type**, not by issue. Replaces the dev-loop with type-specific no-code validators. Designed so a product user with zero coding background can ship a real PR.\n\n## Language\n\nMirror the user's language in every user-facing message — `AskUserQuestion` labels and descriptions, status updates, error explanations. Detect from their first message; when uncertain, default to English.\n\n**Generated artifacts (PR titles, commit messages, PR\u002Fissue body files, branch names) MUST be English** regardless of the user's chat language. GitHub conventions, maintainer review, and search all assume English. The templates under `templates\u002F` are already English — keep them that way when rendering.\n\nScripts live under `scripts\u002F`. Source the shared helpers from any script:\n\n```bash\nsource \"$(dirname \"$0\")\u002Fconfig.sh\"\n```\n\n`SKILL_DIR` below = the directory that contains this `SKILL.md`.\n\n---\n\n## Step 1 — Prereq check (always first)\n\n```bash\nbash \"$SKILL_DIR\u002Fscripts\u002Fcheck-prereqs.sh\"\n```\n\n- Exit 0: capture `GH_USER=\u003Clogin>` from stdout. Default `TARGET_FORK=\"${GH_USER}\u002Fopen-design\"`.\n- Exit 2: surface the printed install \u002F auth hint **verbatim** and stop. Do not attempt token workarounds.\n\nIf `gh repo view \"$TARGET_FORK\"` fails, ask the user (one `AskUserQuestion`) whether to fork now via `gh repo fork nexu-io\u002Fopen-design --clone=false`. Default to yes.\n\n## Step 2 — Pick contribution type\n\nSingle `AskUserQuestion` (header: \"Contribution\", multiSelect: false), four options. Translate option labels\u002Fdescriptions into the user's chat language; the branch routing is unchanged.\n\n1. **🎨 Ship something I made with OD** — _a Skill, Design System, HyperFrame, or template I want to contribute upstream_ → branch `3a`\n2. **🌍 Translate OD docs** — _README \u002F QUICKSTART \u002F CONTRIBUTING into a new language_ → branch `3b`\n3. **📝 Fix docs \u002F write a blog \u002F fix a typo** — _typo fix, dead link, use-case writeup_ → branch `3c`\n4. **🐛 Report a bug** — _something broke; I'll help turn it into a high-quality issue_ → branch `3d` (issue path, no PR)\n\nEach branch below is self-contained. Steps 7–8 (preview + push) are shared across branches `3a`\u002F`3b`\u002F`3c`. Branch `3d` skips them entirely.\n\n---\n\n### Step 3a — OD product submission (Skill \u002F Design System)\n\n**3a.1** Ask user: \"What's the local path to the artifact you want to ship?\" (single free-text, translated into the user's chat language). Common: a folder path (Skill) or a single `DESIGN.md` file (Design System).\n\n**3a.2** Sniff type:\n\n```bash\n# Skill: folder containing SKILL.md with frontmatter.\n# Design System: file matching DESIGN.md anatomy.\n```\n\nIf ambiguous, ask the user to confirm.\n\n**3a.3** Run setup:\n\n```bash\nbash \"$SKILL_DIR\u002Fscripts\u002Fsetup-workspace.sh\" skill \u003Cslug>\n# or\nbash \"$SKILL_DIR\u002Fscripts\u002Fsetup-workspace.sh\" design-system \u003Cslug>\n```\n\n`\u003Cslug>` is `od::slugify` of the Skill `name` frontmatter field or of the brand name. Capture `WORKDIR` from stdout.\n\n**3a.4** Copy artifact into workspace at the right target dir:\n- Skill → `$WORKDIR\u002Fskills\u002F\u003Cslug>\u002F`\n- Design System → `$WORKDIR\u002Fdesign-systems\u002F\u003Cbrand-slug>\u002FDESIGN.md` (+ any sibling assets in the same folder)\n\n**3a.5** Validate:\n\n```bash\nbash \"$SKILL_DIR\u002Fscripts\u002Fvalidate-skill-submission.sh\" \"$WORKDIR\u002Fskills\u002F\u003Cslug>\"\n# or, with 1-2 reference DESIGN.md files passed in:\nbash \"$SKILL_DIR\u002Fscripts\u002Fvalidate-design-system.sh\" \\\n  \"$WORKDIR\u002Fdesign-systems\u002F\u003Cslug>\u002FDESIGN.md\" \\\n  --reference \"$WORKDIR\u002Fdesign-systems\u002Fairbnb\u002FDESIGN.md\" \\\n  --reference \"$WORKDIR\u002Fdesign-systems\u002Fapple\u002FDESIGN.md\"\n```\n\nIf validation fails, surface the FAIL lines verbatim, ask the user to fix, retry. **Never push a failing artifact.**\n\n**3a.6** Ask 3 short questions via `AskUserQuestion` (translate the labels into the user's chat language):\n- \"What name should we credit you under in the PR?\" — free-text\n- \"One-line pitch for this Skill \u002F Design System?\" — free-text\n- \"Path to a screenshot (optional)?\" — free-text\n\n**3a.7** Render `templates\u002FPR-BODY-skill.md` (or `PR-BODY-design-system.md`) with substitutions:\n- `{{SKILL_NAME}}`, `{{SKILL_SLUG}}` (or `{{BRAND_NAME}}`, `{{BRAND_SLUG}}`)\n- `{{PITCH}}` (the one-line)\n- `{{MOTIVATION}}` (free-text — agent can offer to draft this from the skill body, but user confirms)\n- `{{TRY_PROMPT}}` (a prompt they recommend trying — agent suggests a default, user confirms)\n- `{{SCREENSHOT_BLOCK}}` (Markdown image block if a screenshot path was given, else empty)\n- `{{DISCORD_INVITE}}` from `$OD_DISCORD_INVITE`\n\nWrite to `$WORKDIR\u002F.od-contrib\u002FPR-BODY.md`.\n\n→ Jump to **Step 7**.\n\n---\n\n### Step 3b — i18n translation\n\n**3b.1** Setup workspace (slug = `translate-\u003Cdoc>-\u003Clang>` if known, else `translate`):\n\n```bash\nbash \"$SKILL_DIR\u002Fscripts\u002Fsetup-workspace.sh\" i18n translate\n# capture WORKDIR\n```\n\n**3b.2** Discover gaps:\n\n```bash\nbash \"$SKILL_DIR\u002Fscripts\u002Fdiscover-i18n-gaps.sh\" \"$WORKDIR\" > \u002Ftmp\u002Fod-i18n-gaps.json\n```\n\nEach line is JSON. Rank by:\n- `status: \"missing\"` first (missing language is highest leverage)\n- then `status: \"stale\"` ordered by `english_commits_since_translation` desc\n- README family before QUICKSTART before CONTRIBUTING\n\n**3b.3** Take the top 3–4 gaps and present via `AskUserQuestion` (header: \"Translation target\"). Each option label like: `README → 한국어 (Korean)` \u002F `QUICKSTART (zh-CN) refresh — 12 commits behind`. Translate the header text into the user's chat language but keep the option labels descriptive (the language names belong in their native script).\n\n**3b.4** Once user picks, **rename branch** to be specific:\n```bash\ngit -C \"$WORKDIR\" branch -m \"od-contrib\u002Fi18n\u002F\u003Cdoc>-\u003Clang>-\u003Cdate>\"\n```\n(or pre-set the slug in step 3b.1 if the user confirmed earlier.)\n\n**3b.5** Translate. Read the English source. Translate **structure-preserving**:\n- Code blocks: leave untranslated\n- Brand \u002F product names: leave untranslated\n- Filenames in inline code: leave untranslated\n- Image \u002F link targets: leave untranslated; if a localized version of a linked doc exists, swap the link to the localized file\n- Headings: translate, keep the heading depth identical\n- Tables: translate cell text only, keep alignment \u002F pipes\n\nWrite the result to `$WORKDIR\u002F\u003CTRANSLATED_PATH>` (e.g. `QUICKSTART.es.md`). Show user a unified diff vs. the English source for visual sanity-check (line-count delta within ±15% is a healthy signal).\n\n**3b.6** Validate the translated file against the English source. The `--reference` flag tells the validator to ignore relative refs that were already broken in the source — OD docs frequently link to website route slugs (e.g. `skills\u002Fblog-post\u002F`) that aren't files on disk; we don't want a structure-preserving translation to fail because of pre-existing dead refs.\n\n```bash\nbash \"$SKILL_DIR\u002Fscripts\u002Fvalidate-markdown.sh\" \\\n  \"$WORKDIR\u002F\u003CTRANSLATED_PATH>\" \\\n  --reference \"$WORKDIR\u002F\u003CENGLISH_PATH>\"\n```\n\nIf FAIL → surface verbatim, fix, retry.\n\n**3b.7** Render `templates\u002FPR-BODY-i18n.md` with `{{DOC_NAME}}`, `{{LANG_DISPLAY_NAME}}`, `{{LANG_CODE}}`, `{{TRANSLATED_PATH}}`, `{{ENGLISH_PATH}}`, `{{STATUS}}`, `{{TRANSLATION_NOTES}}` (one paragraph from the agent: anything tricky, untranslated terms it kept, etc.), `{{DISCORD_INVITE}}`.\n\n→ **Step 7**.\n\n---\n\n### Step 3c — Docs \u002F blog \u002F typo\n\n**3c.1** Setup workspace (slug `docs`):\n\n```bash\nbash \"$SKILL_DIR\u002Fscripts\u002Fsetup-workspace.sh\" docs \u003Cslug>\n```\n\n**3c.2** Ask user (one `AskUserQuestion`):\n1. **Auto-discover small fixes** (run discover-doc-gaps, pick something)\n2. **I have a specific fix in mind** (free-text)\n3. **I want to write a blog \u002F case study** (free-text — what's the use case?)\n\n**3c.3 (Auto-discover branch)** Run:\n\n```bash\nbash \"$SKILL_DIR\u002Fscripts\u002Fdiscover-doc-gaps.sh\" \"$WORKDIR\" > \u002Ftmp\u002Fod-doc-gaps.json\n```\n\nGroup by `kind` (typo \u002F deadlink \u002F todo). Show the user up to 6 candidates via `AskUserQuestion`. Once picked, apply the fix in code (typo: replace word; deadlink: ask user for the new URL; todo: that's a proper task, ask user to write the missing prose).\n\n**3c.4 (Specific-fix branch)** Read the file, apply user's described change. Confirm via diff.\n\n**3c.5 (Blog branch)** First check whether OD has a blog directory:\n\n```bash\nls \"$WORKDIR\u002Fdocs\" 2>\u002Fdev\u002Fnull\n```\n\nIf a `docs\u002Fblog\u002F` or similar exists, place the new post there. If not, ask the user where it should live, defaulting to `docs\u002F\u003Cslug>.md`. Generate an outline → user fills in user-specific bits (their use case, screenshots, the prompt they used, the rendered output) → agent stitches into a final Markdown.\n\n**3c.6** Validate every changed\u002Fadded file. For files that already exist in the repo (typo fix, dead-link fix, doc edit), pass `--reference` pointing at HEAD's version so we only fail on relative refs the user *introduced*, not on pre-existing route slugs:\n\n```bash\n# For modifications to existing files:\ngit -C \"$WORKDIR\" show \"HEAD:\u003Cpath>\" > \"\u002Ftmp\u002Fod-contrib-orig-\u003Cbasename>\" 2>\u002Fdev\u002Fnull\nbash \"$SKILL_DIR\u002Fscripts\u002Fvalidate-markdown.sh\" \\\n  \"$WORKDIR\u002F\u003Cchanged-path>\" \\\n  --reference \"\u002Ftmp\u002Fod-contrib-orig-\u003Cbasename>\"\n\n# For brand-new files (e.g. a blog post the user is creating from scratch),\n# omit --reference. The validator will skip the relative-ref check entirely\n# (since it can't tell route slugs from real paths in isolation).\n```\n\n**3c.7** Render `templates\u002FPR-BODY-docs.md` with `{{ONE_LINE_SUMMARY}}`, `{{DETAILS}}`, `{{FILES_LIST}}`, `{{DISCORD_INVITE}}`.\n\n→ **Step 7**.\n\n---\n\n### Step 3d — Bug report (issue path, no PR)\n\n**3d.1** Read OD's actual schema at runtime to make sure we mirror it:\n\n```bash\ngh api \"repos\u002F${TARGET_REPO}\u002Fcontents\u002F.github\u002FISSUE_TEMPLATE\u002Fbug-report.yml\" --jq .content | base64 -d > \u002Ftmp\u002Fod-bug-report.yml\n```\n\nIf the schema has drifted from the template (`templates\u002FISSUE-BODY-bug.md`), regenerate the body to match.\n\n**3d.2** Ask the user via `AskUserQuestion`, one structured prompt per critical field. Use **plain language**, not the YAML field names:\n\n| Bug-report field | Prompt to user |\n|---|---|\n| `description` | \"What went wrong? One sentence is fine.\" |\n| `steps` | \"How can I reproduce it? Walk me through step by step.\" |\n| `expected` | \"What did you expect to happen?\" |\n| `version` | \"Which OD version are you running? (About menu, or `od --version`)\" |\n| `platform` | dropdown: macOS (Apple Silicon) \u002F macOS (Intel) \u002F Windows \u002F Linux \u002F Other |\n| `logs` | \"Any error logs you can paste? Skip if you don't have them.\" |\n| `screenshots` | \"Path to a screenshot? Skip if you don't have one.\" |\n\nTranslate every prompt above into the user's chat language at runtime.\n\n**3d.3** Auto-collect what we can (these don't need to ask the user):\n- OS family from `uname`\n- Node version from `node -v` if relevant\n\n**3d.4** Dedupe: extract 3–5 keywords from the description, run:\n\n```bash\ngh search issues \"\u003Ckeywords>\" --repo \"$TARGET_REPO\" --state open --limit 5 --json number,title,url\n```\n\nIf matches exist, present them to the user via `AskUserQuestion` (translate to user's language): \"These existing issues look related. Do you want to: (a) comment on an existing one, (b) open a new issue anyway, (c) cancel?\"\n\n**3d.5** If proceeding with new issue, render `templates\u002FISSUE-BODY-bug.md` and submit:\n\n```bash\nbash \"$SKILL_DIR\u002Fscripts\u002Fcreate-issue.sh\" \\\n  --title \"$TITLE\" \\\n  --body-file \"$WORKDIR_OR_TMP\u002F.od-contrib\u002FISSUE-BODY.md\" \\\n  --dedupe-keywords \"\u003Ckeywords>\"\n```\n\n**3d.6** Print the issue URL on its own line. **Do not** push branches or open PRs from this branch.\n\n---\n\n## Step 7 — Preview + confirm (shared, PR branches only)\n\nShow the user a clean summary:\n\n```text\nAbout to commit:\n  Branch:  od-contrib\u002F\u003Ctype>\u002F\u003Cslug>-\u003Cdate>\n  Files:\n    + skills\u002Ffoo\u002FSKILL.md            (1.2 KB)\n    + skills\u002Ffoo\u002Fpreview.png         (54 KB)\n  Push to:  \u003Cfork or upstream>\n  Open PR:  nexu-io\u002Fopen-design:main ← \u003Cfork>:\u003Cbranch>\n```\n\nThen `git -C \"$WORKDIR\" diff --stat` and a `head -40` of the rendered PR body for visual sanity.\n\nRequired `AskUserQuestion` confirmation (translate to user's language): **\"Push this PR?\"** with three options:\n- **Ship it** — proceed to Step 8\n- **Let me revise** — return to the relevant Step 3 sub-step\n- **Cancel** — leave the workspace on disk, tell the user the path so they can return later, exit\n\nNever push without an explicit \"Ship it\".\n\n## Step 8 — Push & open PR\n\n```bash\nbash \"$SKILL_DIR\u002Fscripts\u002Fcreate-pr.sh\" \\\n  --workdir \"$WORKDIR\" \\\n  --type \"\u003Cskill|design-system|i18n|docs>\" \\\n  --title \"\u003CPR title from references\u002Fnewcomer-tone.md>\" \\\n  --body-file \"$WORKDIR\u002F.od-contrib\u002FPR-BODY.md\"\n```\n\nPrint the PR URL on its own line. Done.\n\n---\n\n## Safety rails (mandatory)\n\n- Never push to `main` \u002F `master` \u002F `develop`. The push scripts refuse.\n- Never `--force` push. Just don't.\n- All workspace activity stays under `$OD_WORK_ROOT` (default `$HOME\u002Fod-contrib-work`). `od::assert_in_workroot` enforces this.\n- Bug-report path **always** runs the dedupe search before `gh issue create`.\n- Honor user memory: skip GitHub user `xxiaoxiong` from any contributor lookup ([[feedback_no_outreach_xxiaoxiong]]).\n\n## When NOT to use this skill\n\n- The user wants to fix a daemon \u002F web bug or add a feature with code changes → use `auto-github-contributor` instead (it has the TDD loop). This skill deliberately doesn't run lint\u002Ftypecheck\u002Ftests because content paths don't need them.\n- The user wants to *generate* a Skill \u002F Design System from scratch → that's Open Design itself. Run OD first, get an artifact, then come back here to ship it.\n",{"name":5,"description":7,"allowed-tools":24},[25,26,27,28,29,30,31,32],"Bash","Read","Write","Edit","AskUserQuestion","TaskCreate","TaskUpdate","WebFetch","main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002F.claude\u002Fskills\u002Fod-contribute",0,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base","https:\u002F\u002Fkb.yyc3.top\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-10 10:37:32",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill od-contribute",{"tool":48,"command":49},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill od-contribute",{"tool":51,"command":52},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill od-contribute","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002F.claude\u002Fskills\u002Fod-contribute\u002FSKILL.md",true,[56,62,68,72,76,80,84,88,92,96,100,104,108,112,116,120,124,128,132,136,140],{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"agents\u002Fopenai.yaml","REFERENCE","参考文档",652,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002F.claude\u002Fskills\u002Fod-contribute\u002Fagents\u002Fopenai.yaml",{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"install.sh","SCRIPT","脚本",5225,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002F.claude\u002Fskills\u002Fod-contribute\u002Finstall.sh",{"path":69,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fdesign-system-anatomy.md",1997,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002F.claude\u002Fskills\u002Fod-contribute\u002Freferences\u002Fdesign-system-anatomy.md",{"path":73,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fnewcomer-tone.md",2717,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002F.claude\u002Fskills\u002Fod-contribute\u002Freferences\u002Fnewcomer-tone.md",{"path":77,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fod-repo-map.md",2291,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002F.claude\u002Fskills\u002Fod-contribute\u002Freferences\u002Fod-repo-map.md",{"path":81,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fskill-anatomy.md",2334,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002F.claude\u002Fskills\u002Fod-contribute\u002Freferences\u002Fskill-anatomy.md",{"path":85,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":86,"sourceHtmlUrl":87},"scripts\u002Fcheck-prereqs.sh",4217,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002F.claude\u002Fskills\u002Fod-contribute\u002Fscripts\u002Fcheck-prereqs.sh",{"path":89,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":90,"sourceHtmlUrl":91},"scripts\u002Fconfig.sh",2472,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002F.claude\u002Fskills\u002Fod-contribute\u002Fscripts\u002Fconfig.sh",{"path":93,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":94,"sourceHtmlUrl":95},"scripts\u002Fcreate-issue.sh",3803,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002F.claude\u002Fskills\u002Fod-contribute\u002Fscripts\u002Fcreate-issue.sh",{"path":97,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":98,"sourceHtmlUrl":99},"scripts\u002Fcreate-pr.sh",3907,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002F.claude\u002Fskills\u002Fod-contribute\u002Fscripts\u002Fcreate-pr.sh",{"path":101,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":102,"sourceHtmlUrl":103},"scripts\u002Fdiscover-doc-gaps.sh",4063,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002F.claude\u002Fskills\u002Fod-contribute\u002Fscripts\u002Fdiscover-doc-gaps.sh",{"path":105,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":106,"sourceHtmlUrl":107},"scripts\u002Fdiscover-i18n-gaps.sh",4866,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002F.claude\u002Fskills\u002Fod-contribute\u002Fscripts\u002Fdiscover-i18n-gaps.sh",{"path":109,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":110,"sourceHtmlUrl":111},"scripts\u002Fsetup-workspace.sh",3476,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002F.claude\u002Fskills\u002Fod-contribute\u002Fscripts\u002Fsetup-workspace.sh",{"path":113,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":114,"sourceHtmlUrl":115},"scripts\u002Fvalidate-design-system.sh",3367,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002F.claude\u002Fskills\u002Fod-contribute\u002Fscripts\u002Fvalidate-design-system.sh",{"path":117,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":118,"sourceHtmlUrl":119},"scripts\u002Fvalidate-markdown.sh",7075,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002F.claude\u002Fskills\u002Fod-contribute\u002Fscripts\u002Fvalidate-markdown.sh",{"path":121,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":122,"sourceHtmlUrl":123},"scripts\u002Fvalidate-skill-submission.sh",5095,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002F.claude\u002Fskills\u002Fod-contribute\u002Fscripts\u002Fvalidate-skill-submission.sh",{"path":125,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":126,"sourceHtmlUrl":127},"templates\u002FISSUE-BODY-bug.md",451,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002F.claude\u002Fskills\u002Fod-contribute\u002Ftemplates\u002FISSUE-BODY-bug.md",{"path":129,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":130,"sourceHtmlUrl":131},"templates\u002FPR-BODY-design-system.md",1107,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002F.claude\u002Fskills\u002Fod-contribute\u002Ftemplates\u002FPR-BODY-design-system.md",{"path":133,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":134,"sourceHtmlUrl":135},"templates\u002FPR-BODY-docs.md",723,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002F.claude\u002Fskills\u002Fod-contribute\u002Ftemplates\u002FPR-BODY-docs.md",{"path":137,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":138,"sourceHtmlUrl":139},"templates\u002FPR-BODY-i18n.md",1243,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002F.claude\u002Fskills\u002Fod-contribute\u002Ftemplates\u002FPR-BODY-i18n.md",{"path":141,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":142,"sourceHtmlUrl":143},"templates\u002FPR-BODY-skill.md",1016,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002F.claude\u002Fskills\u002Fod-contribute\u002Ftemplates\u002FPR-BODY-skill.md",[145,152,159,166,173,180],{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":151,"publishedAt":19},"01M7CTDWHERCXPQCP0K03A86AS","vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fvercel-sandbox\u002FSKILL.md",[],[],{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":158,"publishedAt":19},"01M7CTD8D2BNJY54S65M47HEJA","slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fslack\u002FSKILL.md",[],[],{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":165,"publishedAt":19},"01M7CTCSSB8ZP3Q58C3YZDZK1W","electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Felectron\u002FSKILL.md",[],[],{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":172,"publishedAt":19},"01M7CTCBJY76688V4DCZGWFHGQ","dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app\u002Fsite\u002Fplatform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fdogfood\u002FSKILL.md",[],[],{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":179,"publishedAt":19},"01M7CTC4H0FFGVEAQR9PA4GA1A","agent-browser","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fagent-browser\u002FSKILL.md",[],[],{"skillNo":181,"name":182,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":184,"categories":185,"keywords":186,"publishedAt":19},"01M7CTBKVFYBG78FDSABSDJTTQ","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", \"switch to --preset\", and for building a design system or applying a DESIGN.md or brand spec to shadcn\u002Fui.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-UI-界面组件\u002FYYC3-UI-界面组件-ui\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[]]