[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71SS2M2VYRMRDPEHP9XMK2E":3,"skill-same:01M71SS2M2VYRMRDPEHP9XMK2E":90},{"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":28,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":55,"repositoryHtmlUrl":56,"repositoryHomepageUrl":57,"ownerHtmlUrl":58,"ownerBlogUrl":59,"ownerDescription":60,"updatedAt":61,"install":62,"resources":75},"01M71SS2M2VYRMRDPEHP9XMK2E","pr-size-budget",null,"Use when opening a PR or planning slices — defines the soft 300 LOC budget, the exclusion list, the shared gate prompt for ship\u002Fflow\u002Fstack-pr, and the override syntax.","HigorAlves\u002Forc","HigorAlves","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F11262976?v=4","01M71S79EZEMHZ8PQSV0XQJHYY","Higor Alves","01M71S79FKKTCHCN1EDR8DSTWQ",7,"MIT","https:\u002F\u002Fgithub.com\u002FHigorAlves\u002Forc\u002Fblob\u002Fmain\u002Forc\u002Fskills\u002Fpr-size-budget\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000040","财务","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"pr size budget","pr","size","Budget","opening a pr","gate","loc","prompt","use","for","planning","ship","list","flow","syntax","stack","when","shared","2026-11-10 13:02:02",false,"---\nname: pr-size-budget\ndescription: Use when opening a PR or planning slices — defines the soft 300 LOC budget, the exclusion list, the shared gate prompt for ship\u002Fflow\u002Fstack-pr, and the override syntax.\n---\n\n# PR size budget\n\n## Overview\n\nBig PRs starve review quality. orc enforces a **soft iron rule** at PR-creation time: the diff (additions + deletions, post-exclusion) is computed against the base branch and compared to a budget. When over budget, the user picks one of three paths — never silently ignored, never hard-blocked.\n\nThis skill is the single source of truth. `\u002Forc:ship`, `\u002Forc:flow`, and `\u002Forc:stack-pr` all call the `orc-pr-size` CLI (plugin `bin\u002F`, on PATH while orc is enabled) and present the gate prompt defined here. If you're tempted to reimplement LOC math or the prompt elsewhere — don't.\n\n**Announce at start:** \"I'm using the pr-size-budget skill because this command opens or sizes a PR.\"\n\n## Budget resolution order\n\nHighest precedence wins:\n\n1. **CLI flag** — `--max-loc \u003CN>` on `\u002Forc:ship`, `\u002Forc:flow`, `\u002Forc:stack-pr`.\n2. **Environment** — `$ORC_PR_LOC_BUDGET` (per-shop default, e.g. set in shell init).\n3. **Per-repo config** — `\u003Crepo_root>\u002F.orc\u002Fpr-budget.json#budget`.\n4. **Plugin setting** — userConfig `pr_size_budget` (prompted at plugin enable; exported as `CLAUDE_PLUGIN_OPTION_PR_SIZE_BUDGET`). Per-repo intent deliberately beats this per-user default.\n5. **Built-in default** — `300`.\n\n`--no-size-gate` bypasses the gate entirely (records nothing in the PR body). Use sparingly — typically only for emergency fixes where review-cycle time is the dominant cost.\n\n## What counts toward the budget\n\n`additions + deletions` of the diff `base...HEAD` (three-dot, the symmetric-difference form `gh pr create` uses), **after applying the exclusion pathspecs**. Modified lines count as `1 add + 1 del = 2 LOC` — same as `git diff --shortstat` reports.\n\n## Default exclusion globs\n\nThese never count:\n\n- **Lockfiles** — `package-lock.json`, `pnpm-lock.yaml`, `yarn.lock`, `Cargo.lock`, `go.sum`, `Gemfile.lock`, `composer.lock`, `poetry.lock`, `uv.lock`, any `*.lock` \u002F `*.lockb`.\n- **Snapshots \u002F generated** — `**\u002F__snapshots__\u002F**`, `**\u002F__generated__\u002F**`, `**\u002Fgenerated\u002F**`, `**\u002F*.gen.{ts,go}`, `**\u002F*.pb.{go,ts}`, `**\u002F*_pb2.py`.\n- **Build artifacts** — `**\u002Fdist\u002F**`, `**\u002Fbuild\u002F**`, `**\u002F.next\u002F**`.\n- **Generated browser-QA proof** — `e2e\u002Fspecs\u002F**`, `e2e\u002Ftests\u002F**` (Playwright plans + tests written by `\u002Forc:qa`'s planner\u002Fgenerator; reviewers see them, the budget doesn't count them).\n\n## Migrations and per-repo config\n\nMigrations (`**\u002Fmigrations\u002F**\u002F*.sql`, `prisma\u002Fmigrations\u002F**`, `db\u002Fmigrate\u002F**`) are **excluded by default**; the gate prompt always surfaces the count + LOC of excluded migration files. Read [CONFIG.md](references\u002FCONFIG.md) when a repo needs `\u003Crepo_root>\u002F.orc\u002Fpr-budget.json` — the schema for `budget`, `exclude_migrations`, `additional_excludes`.\n\n## The gate prompt (canonical)\n\nWhen `loc > budget`, the calling command MUST surface this `AskUserQuestion` shape (paraphrased per command — `\u002Forc:flow` adds a fourth option; the first three are identical everywhere):\n\n> **Question:** \"This PR is **{loc} LOC** vs the **{budget} LOC** budget. How would you like to proceed?\"\n>\n> **Header:** `PR size`\n>\n> **Options:**\n>\n> 1. **Stack it (Recommended)** — Hand off to `\u002Forc:stack-pr` to break this into a stack of smaller PRs. Reviewers can approve incrementally.\n>\n> 2. **Open as one big PR** — Requires a one-line reason. Reason is recorded as a `Size-budget-override:` trailer in the PR body.\n>\n> 3. **Abort** — Go back to the implementation, resize, then re-run.\n\nBefore the prompt, **always** print the Gate callout (per the `orc:callouts` terminal palette — **⛔ Gate — PR size**, no `[!TYPE]` tag), then the breakdown in a fence (never inside the callout — blockquotes reflow and break alignment):\n\n```markdown\n> **⛔ Gate — PR size**\n>\n> Diff vs \u003Cbase>: **\u003Cloc> LOC** across \u003CN> files vs the **\u003Cbudget> LOC** budget — OVER by \u003Cloc - budget> LOC.\n```\n\n```\nTop contributors:\n\u003Corc_pr_loc_breakdown table — first 10 files>\n\n\u003Corc_pr_excluded_summary one-liner>\n```\n\nThis is non-negotiable: the user cannot make an informed choice without seeing where the LOC went and what was already discounted. The breakdown is what stops \"the budget is too low\" complaints — usually the answer is \"no, you have an 800-line config file in this PR.\"\n\n## Override syntax\n\nWhen the user picks **\"Open as one big PR\"**, prompt for a one-line reason via free-text input (use `AskUserQuestion` with `Other` as the path). Reason MUST be non-empty. Append to the PR body as a trailer (after any Jira \u002F `Closes #N` trailers):\n\n```\nSize-budget-override: \u003Creason>\n```\n\nAcceptable and unacceptable reasons, with why the trailer stays unlinted: [OVERRIDE-EXAMPLES.md](references\u002FOVERRIDE-EXAMPLES.md).\n\n## The CLI (`bin\u002Forc-pr-size`, on PATH while orc is enabled)\n\nOne call powers the whole gate:\n\n```bash\nbase=$(git symbolic-ref refs\u002Fremotes\u002Forigin\u002FHEAD --short | sed 's@^origin\u002F@@')\norc-pr-size gate --base \"origin\u002F$base\" ${ARG_MAX_LOC:+--max-loc \"$ARG_MAX_LOC\"}\n# → base:\u002Floc:\u002Fbudget:\u002Fverdict: lines, then the top-10 breakdown table,\n#   then the excluded-files one-liner.\n# verdict: over → render the \"⛔ Gate — PR size\" callout from\n# \"The gate prompt\" section above, then AskUserQuestion as above.\n```\n\nOther subcommands (`loc`, `breakdown`, `excluded`, `budget`) and the `lib\u002Fpr-size-budget.sh` functions for hook scripts: [CLI.md](references\u002FCLI.md).\n\n## Workspace mode\n\nIn workspace mode, the gate fires **per repo**, not per workspace. Each `gh pr create` in the per-repo loop runs its own size-gate computation against the per-repo `base`. One repo can stack while another opens single — they're independent decisions.\n\nPer-repo config files (`\u003Crepo>\u002F.orc\u002Fpr-budget.json`) take precedence over the workspace-level default.\n\n## Iron rule\n\nThis skill exists because of **`using-orc` Rule 8: No PR over the size budget without a recorded choice**. The choice is always one of: stack, big-with-reason trailer, or abort. There is no fourth option of \"ignore the gate.\" `--no-size-gate` exists as an escape hatch for emergencies — it is not a daily-driver flag.\n","# PR size budget\n\n## Overview\n\nBig PRs starve review quality. orc enforces a **soft iron rule** at PR-creation time: the diff (additions + deletions, post-exclusion) is computed against the base branch and compared to a budget. When over budget, the user picks one of three paths — never silently ignored, never hard-blocked.\n\nThis skill is the single source of truth. `\u002Forc:ship`, `\u002Forc:flow`, and `\u002Forc:stack-pr` all call the `orc-pr-size` CLI (plugin `bin\u002F`, on PATH while orc is enabled) and present the gate prompt defined here. If you're tempted to reimplement LOC math or the prompt elsewhere — don't.\n\n**Announce at start:** \"I'm using the pr-size-budget skill because this command opens or sizes a PR.\"\n\n## Budget resolution order\n\nHighest precedence wins:\n\n1. **CLI flag** — `--max-loc \u003CN>` on `\u002Forc:ship`, `\u002Forc:flow`, `\u002Forc:stack-pr`.\n2. **Environment** — `$ORC_PR_LOC_BUDGET` (per-shop default, e.g. set in shell init).\n3. **Per-repo config** — `\u003Crepo_root>\u002F.orc\u002Fpr-budget.json#budget`.\n4. **Plugin setting** — userConfig `pr_size_budget` (prompted at plugin enable; exported as `CLAUDE_PLUGIN_OPTION_PR_SIZE_BUDGET`). Per-repo intent deliberately beats this per-user default.\n5. **Built-in default** — `300`.\n\n`--no-size-gate` bypasses the gate entirely (records nothing in the PR body). Use sparingly — typically only for emergency fixes where review-cycle time is the dominant cost.\n\n## What counts toward the budget\n\n`additions + deletions` of the diff `base...HEAD` (three-dot, the symmetric-difference form `gh pr create` uses), **after applying the exclusion pathspecs**. Modified lines count as `1 add + 1 del = 2 LOC` — same as `git diff --shortstat` reports.\n\n## Default exclusion globs\n\nThese never count:\n\n- **Lockfiles** — `package-lock.json`, `pnpm-lock.yaml`, `yarn.lock`, `Cargo.lock`, `go.sum`, `Gemfile.lock`, `composer.lock`, `poetry.lock`, `uv.lock`, any `*.lock` \u002F `*.lockb`.\n- **Snapshots \u002F generated** — `**\u002F__snapshots__\u002F**`, `**\u002F__generated__\u002F**`, `**\u002Fgenerated\u002F**`, `**\u002F*.gen.{ts,go}`, `**\u002F*.pb.{go,ts}`, `**\u002F*_pb2.py`.\n- **Build artifacts** — `**\u002Fdist\u002F**`, `**\u002Fbuild\u002F**`, `**\u002F.next\u002F**`.\n- **Generated browser-QA proof** — `e2e\u002Fspecs\u002F**`, `e2e\u002Ftests\u002F**` (Playwright plans + tests written by `\u002Forc:qa`'s planner\u002Fgenerator; reviewers see them, the budget doesn't count them).\n\n## Migrations and per-repo config\n\nMigrations (`**\u002Fmigrations\u002F**\u002F*.sql`, `prisma\u002Fmigrations\u002F**`, `db\u002Fmigrate\u002F**`) are **excluded by default**; the gate prompt always surfaces the count + LOC of excluded migration files. Read [CONFIG.md](references\u002FCONFIG.md) when a repo needs `\u003Crepo_root>\u002F.orc\u002Fpr-budget.json` — the schema for `budget`, `exclude_migrations`, `additional_excludes`.\n\n## The gate prompt (canonical)\n\nWhen `loc > budget`, the calling command MUST surface this `AskUserQuestion` shape (paraphrased per command — `\u002Forc:flow` adds a fourth option; the first three are identical everywhere):\n\n> **Question:** \"This PR is **{loc} LOC** vs the **{budget} LOC** budget. How would you like to proceed?\"\n>\n> **Header:** `PR size`\n>\n> **Options:**\n>\n> 1. **Stack it (Recommended)** — Hand off to `\u002Forc:stack-pr` to break this into a stack of smaller PRs. Reviewers can approve incrementally.\n>\n> 2. **Open as one big PR** — Requires a one-line reason. Reason is recorded as a `Size-budget-override:` trailer in the PR body.\n>\n> 3. **Abort** — Go back to the implementation, resize, then re-run.\n\nBefore the prompt, **always** print the Gate callout (per the `orc:callouts` terminal palette — **⛔ Gate — PR size**, no `[!TYPE]` tag), then the breakdown in a fence (never inside the callout — blockquotes reflow and break alignment):\n\n```markdown\n> **⛔ Gate — PR size**\n>\n> Diff vs \u003Cbase>: **\u003Cloc> LOC** across \u003CN> files vs the **\u003Cbudget> LOC** budget — OVER by \u003Cloc - budget> LOC.\n```\n\n```\nTop contributors:\n\u003Corc_pr_loc_breakdown table — first 10 files>\n\n\u003Corc_pr_excluded_summary one-liner>\n```\n\nThis is non-negotiable: the user cannot make an informed choice without seeing where the LOC went and what was already discounted. The breakdown is what stops \"the budget is too low\" complaints — usually the answer is \"no, you have an 800-line config file in this PR.\"\n\n## Override syntax\n\nWhen the user picks **\"Open as one big PR\"**, prompt for a one-line reason via free-text input (use `AskUserQuestion` with `Other` as the path). Reason MUST be non-empty. Append to the PR body as a trailer (after any Jira \u002F `Closes #N` trailers):\n\n```\nSize-budget-override: \u003Creason>\n```\n\nAcceptable and unacceptable reasons, with why the trailer stays unlinted: [OVERRIDE-EXAMPLES.md](references\u002FOVERRIDE-EXAMPLES.md).\n\n## The CLI (`bin\u002Forc-pr-size`, on PATH while orc is enabled)\n\nOne call powers the whole gate:\n\n```bash\nbase=$(git symbolic-ref refs\u002Fremotes\u002Forigin\u002FHEAD --short | sed 's@^origin\u002F@@')\norc-pr-size gate --base \"origin\u002F$base\" ${ARG_MAX_LOC:+--max-loc \"$ARG_MAX_LOC\"}\n# → base:\u002Floc:\u002Fbudget:\u002Fverdict: lines, then the top-10 breakdown table,\n#   then the excluded-files one-liner.\n# verdict: over → render the \"⛔ Gate — PR size\" callout from\n# \"The gate prompt\" section above, then AskUserQuestion as above.\n```\n\nOther subcommands (`loc`, `breakdown`, `excluded`, `budget`) and the `lib\u002Fpr-size-budget.sh` functions for hook scripts: [CLI.md](references\u002FCLI.md).\n\n## Workspace mode\n\nIn workspace mode, the gate fires **per repo**, not per workspace. Each `gh pr create` in the per-repo loop runs its own size-gate computation against the per-repo `base`. One repo can stack while another opens single — they're independent decisions.\n\nPer-repo config files (`\u003Crepo>\u002F.orc\u002Fpr-budget.json`) take precedence over the workspace-level default.\n\n## Iron rule\n\nThis skill exists because of **`using-orc` Rule 8: No PR over the size budget without a recorded choice**. The choice is always one of: stack, big-with-reason trailer, or abort. There is no fourth option of \"ignore the gate.\" `--no-size-gate` exists as an escape hatch for emergencies — it is not a daily-driver flag.\n",{"name":5,"description":7},"main","7522fd7266944e30052204c2f6df287d8b5516be","orc\u002Fskills\u002Fpr-size-budget",0,"https:\u002F\u002Fgithub.com\u002FHigorAlves\u002Forc","https:\u002F\u002Forc.novacstack.com\u002F","https:\u002F\u002Fgithub.com\u002FHigorAlves","higoralves.dev","Software Engineering","2026-11-07 07:26:38",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add HigorAlves\u002Forc --skill pr-size-budget",{"tool":68,"command":69},"bunx","bunx skills add HigorAlves\u002Forc --skill pr-size-budget",{"tool":71,"command":72},"pnpm","pnpm dlx skills add HigorAlves\u002Forc --skill pr-size-budget","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHigorAlves\u002Forc\u002Fblob\u002Fmain\u002Forc\u002Fskills\u002Fpr-size-budget\u002FSKILL.md",true,[76,82,86],{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002FCLI.md","REFERENCE","参考文档",974,"https:\u002F\u002Fgithub.com\u002FHigorAlves\u002Forc\u002Fblob\u002Fmain\u002Forc\u002Fskills\u002Fpr-size-budget\u002Freferences\u002FCLI.md",{"path":83,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002FCONFIG.md",1217,"https:\u002F\u002Fgithub.com\u002FHigorAlves\u002Forc\u002Fblob\u002Fmain\u002Forc\u002Fskills\u002Fpr-size-budget\u002Freferences\u002FCONFIG.md",{"path":87,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002FOVERRIDE-EXAMPLES.md",709,"https:\u002F\u002Fgithub.com\u002FHigorAlves\u002Forc\u002Fblob\u002Fmain\u002Forc\u002Fskills\u002Fpr-size-budget\u002Freferences\u002FOVERRIDE-EXAMPLES.md",[91,124,148,168,190,210],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":106,"publishedAt":47},"01M71SW40F9TAAEDKBYYBCM814","writing-plans","Write a comprehensive implementation plan of bite-sized TDD tasks that an engineer with zero codebase context could execute — exact files, code, tests, and verification steps","https:\u002F\u002Fgithub.com\u002FHigorAlves\u002Forc\u002Fblob\u002Fmain\u002Forc\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[97,100,103],{"categoryNo":98,"categoryName":99,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":101,"categoryName":102,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师",{"categoryNo":104,"categoryName":105,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000036","内容创作者",[107,108,109,110,111,112,113,45,114,115,116,117,118,119,120,121,122,38,123,37],"writing","writing plans","plans","engineer","superpowers","implementation plan","files","you","code","tasks","verification","plan","write","steps","context","ZeRO","tests",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":133,"publishedAt":47},"01M71SW15KHE4MHJW9NEXV65X2","writing-for-agents","orc's doctrine layer for writing any document an agent consumes — skills, AGENTS.md\u002FCLAUDE.md, reference docs","https:\u002F\u002Fgithub.com\u002FHigorAlves\u002Forc\u002Fblob\u002Fmain\u002Forc\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[130,131,132],{"categoryNo":98,"categoryName":99,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":104,"categoryName":105,"taxonomyType":26,"taxonomyTypeDesc":27},[134,107,38,135,45,136,137,138,139,140,141,142,37,143,144,145,146,147],"writing for agents","matt pocock","inline","tuning","a skill","layer","doctrine","push","editing","document","github","https","reference","docs",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":155,"publishedAt":47},"01M71SVYQKXT743HHHWGHT3G13","workspace-mode","Use when cwd is a parent dir holding multiple sibling git repos — defines repo auto-detection, --repos\u002F--repo\u002F--all-repos\u002F--this-repo precedence, per-repo dispatch, and linked-PR mechanics.","https:\u002F\u002Fgithub.com\u002FHigorAlves\u002Forc\u002Fblob\u002Fmain\u002Forc\u002Fskills\u002Fworkspace-mode\u002FSKILL.md",[154],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[156,157,158,159,160,45,161,162,30,163,37,164,165,166,167],"workspace mode","mode","workspace","mechanics","auto","repos","git","repo","dispatch","auto-detection","detection","parent",{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":175,"publishedAt":47},"01M71SVVP3BXS06G9395P2K0RH","wizard","Generate an interactive bash wizard walking a human through work only they can perform — credentials, secrets, one-off migrations","https:\u002F\u002Fgithub.com\u002FHigorAlves\u002Forc\u002Fblob\u002Fmain\u002Forc\u002Fskills\u002Fwizard\u002FSKILL.md",[174],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[170,176,177,178,179,135,45,180,181,182,183,184,185,120,186,187,38,37,188,189],"condition","never","provisioning infrastructure","only","Bash","work","credentials","generate","human","secrets","infrastructure","do","one","interactive",{"skillNo":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":194,"categories":195,"keywords":196,"publishedAt":47},"01M71SVT4AR6NKAM5B077E7QSJ","wait-what","Stop and re-pitch — the last message did not land; say it again simply, in the project's own vocabulary.","https:\u002F\u002Fgithub.com\u002FHigorAlves\u002Forc\u002Fblob\u002Fmain\u002Forc\u002Fskills\u002Fwait-what\u002FSKILL.md",[],[197,198,199,200,201,135,202,203,204,205,144,145,206,207,208,209],"wait what","wait","project","re","true","pitch","last","say","message","land","it","stop","vocabulary",{"skillNo":211,"name":212,"nameZh":6,"description":213,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":214,"categories":215,"keywords":220,"publishedAt":47},"01M71SVQVYRA9QBQ6G8MWR8G6F","vitest","Vitest fast unit testing framework powered by Vite with Jest-compatible API","https:\u002F\u002Fgithub.com\u002FHigorAlves\u002Forc\u002Fblob\u002Fmain\u002Forc\u002Fskills\u002Fvitest\u002FSKILL.md",[216,219],{"categoryNo":217,"categoryName":218,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":101,"categoryName":102,"taxonomyType":26,"taxonomyTypeDesc":27},[212,221,222,223,224,225,107,45,226,227,228,229,230,231,232,233,234,235,123,236],"coverage","unit","testing","testing framework","generated","api","jest","2026","at","scripts","unit testing","antfu","framework","vite","mocking","dev"]