[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FDDRBCY2SFA803PTKEM98S":3,"skill-same:01M7FDDRBCY2SFA803PTKEM98S":45},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7FDDRBCY2SFA803PTKEM98S","perf-worklist",null,"Work off a plugin's performance task list (`\u003Cplugin>\u002Fdocs\u002FTASKS.md`) job by job with a Workflow - one sequential subagent per open task with a model and effort picked per task (cap opus, xhigh), commit and push after every job, then a fresh performance analysis. Runs the analysis first when no open task exists. Use when the user asks to work through, burn down or re-run the performance analysis and task list of a plugin.","kwitsch\u002Fclaude-plugins-development","kwitsch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F10324063?v=4","01M7FDD9EEY7P0P5C9QDQA74VK","Kwitsch","01M7FDD9FHJK7MPGWB04GTNV1M",0,"MIT","https:\u002F\u002Fgithub.com\u002Fkwitsch\u002Fclaude-plugins-development\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fperf-worklist\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: perf-worklist\ndescription: Work off a plugin's performance task list (`\u003Cplugin>\u002Fdocs\u002FTASKS.md`) job by job with a Workflow - one sequential subagent per open task with a model and effort picked per task (cap opus, xhigh), commit and push after every job, then a fresh performance analysis. Runs the analysis first when no open task exists. Use when the user asks to work through, burn down or re-run the performance analysis and task list of a plugin.\nargument-hint: \"\u003Cplugin-name>\"\n---\n\n# perf-worklist\n\nSystematic run over `\u003Cplugin>\u002Fdocs\u002F` (layout and task rules: `.claude\u002Frules\u002Fplugin-docs-tasks.md`, pattern from `dprint\u002Fdocs\u002F`). The argument is the plugin directory name; stop with one line if `\u003Cplugin>\u002Fpackage.json` does not exist.\n\nThe user's request for this skill is the opt-in for the Workflow tool (load `workflow-authoring` first if it is not loaded).\n\n## Start: worktree and branch\n\nFirst action, before reading anything: check whether the session already is in a linked git worktree (`git rev-parse --git-dir` ends in `\u002Fworktrees\u002F\u003Cname>`, or `--git-common-dir` differs from `--git-dir`). If not, call `EnterWorktree` (load it via ToolSearch if deferred) with `name: \"perf-\u003Cplugin>\"` to switch into a new one, then `git switch -c perf\u002F\u003Cplugin>-\u003CYYYY-MM-DD>` (one branch and one draft PR for the whole run). In an existing linked worktree only create that branch when the current one has no commits of its own. Never nest. Note the worktree's absolute path and today's date: both go into the workflow `args`.\n\n## Step 1: open tasks to jobs\n\n1. Read `\u003Cplugin>\u002Fdocs\u002FTASKS.md`. An open task is an unchecked `- [ ]` entry (tags `open`, `partial`, `docs-only`, `measurement-only`) or a task document with `status: open|partial|docs-only`. Read each open task's `tasks\u002F\u003Cid>-\u003Cslug>.md`.\n2. **No open task** (or no list): run the analysis first (step 3 with `mode: \"analyse\"`), then repeat this step with the new list. Nothing open after the analysis: report that and stop.\n3. **One job per open task**, in the order of the `Dependencies` section of `TASKS.md` (else priority, then id). For every job pick `model` and `effort` (hard cap: `opus` and `xhigh`, never `max`):\n   - Ask jev-api once per task (`mcp__jev-api__batch`, state = the task document text): `score` \"How large and risky is the change?\" with levels `[S: docs or one line, M: one function with tests, L: several functions or modules, XL: cross-cutting, concurrency or protocol change]`, rounded to the nearest level. Low confidence (below 0.5), an error or no configuration: judge it yourself from the same criteria and say so in one line.\n   - Map: S -> `haiku`\u002F`low` (docs-only and closed-without-code decisions: `sonnet`\u002F`low`), M -> `sonnet`\u002F`medium`, L -> `opus`\u002F`high`, XL -> `opus`\u002F`xhigh`. A `measurement-only` task is at least `sonnet`\u002F`medium`.\n   - Show the table (id, title, size, model, effort) in the reply before starting.\n\n## Step 2: jobs (Workflow, sequential)\n\nRun the script below with `Workflow`, `args = { mode: \"jobs\", plugin, worktree, date, jobs: [{ id, file, title, model, effort }] }`. Every cache, buffer or merged request a job adds names its invalidation points and gets one test per point (`.claude\u002Frules\u002Fhook-caches-and-tests.md`): in the jevfort run most later bugs were regressions of exactly these. Jobs run one after the other in the same worktree (no `isolation`; they all edit the same files). Every job commits and pushes itself. A `blocked` job stops the run; report it and leave the rest open.\n\nAfter the last job and before the analysis, a review job runs (when at least one job shipped code or docs): `\u002Fsimplify` once, then `\u002Fcode-review high --fix` on the branch, then build, lint and tests again, commit and push of what changed (`opus`\u002F`high`; `high` is the ceiling here, never `max`). A blocked review also skips the analysis.\n\n## Step 3: analysis\n\nThe script's last phase (and `mode: \"analyse\"`) runs one analysis agent (`opus`\u002F`xhigh`, read-only on code, writes docs only): method of `\u003Cplugin>\u002Fdocs\u002FEVALUATION-*.md` (same machine, built output, 5+ repetitions where cheap, a comparison with the previous evaluation, never edit old numbers), new findings as `tasks\u002F\u003Cid>-\u003Cslug>.md` with the next free `F\u003Cnn>` id and `status: open`, `TASKS.md` updated. It commits and pushes, and returns the new open ids.\n\nThe review and the analysis commit and push their own changes like every job; the run ends with a clean `git status` and the branch head equal to its upstream.\n\nNew open tasks after the closing analysis are reported, not worked in the same run: a new run of this skill works them off.\n\n## Finish\n\nAfter the workflow: `gh pr create --draft` for the branch when none exists (`gh pr view` first), title `\u003Cplugin>: performance task list (\u003Cn> jobs)`, body = per-job table with status and commit. No attribution lines. Report the PR URL, the per-job outcome and the new open ids.\n\n## Workflow script\n\n```js\nexport const meta = {\n  name: 'perf-worklist',\n  description: 'Work off a plugin perf task list job by job (commit + push each), then re-run the analysis',\n  phases: [\n    { title: 'Jobs', detail: 'one subagent per open task, sequential' },\n    { title: 'Review', detail: '\u002Fsimplify, then \u002Fcode-review --fix on the branch' },\n    { title: 'Analysis', detail: 'fresh performance analysis' },\n  ],\n}\n\nconst JOB = { type: 'object', properties: { status: { enum: ['done', 'closed', 'blocked'] }, commit: { type: 'string' }, summary: { type: 'string' } }, required: ['status', 'summary'] }\nconst REVIEW = { type: 'object', properties: { status: { enum: ['clean', 'fixed', 'blocked'] }, commit: { type: 'string' }, summary: { type: 'string' } }, required: ['status', 'summary'] }\nconst ANALYSIS = { type: 'object', properties: { newOpen: { type: 'array', items: { type: 'string' } }, summary: { type: 'string' } }, required: ['newOpen', 'summary'] }\nconst { plugin, worktree, date } = args\n\n\u002F\u002F No human reads the agents' text: no narration between tool calls, only the structured result.\nconst QUIET = '\\n\\nNo narration: no text between tool calls, no plans, no progress notes, no recap. Call tools silently and end with the structured result only.'\nconst run = (prompt, opts) => agent(prompt + QUIET, opts)\n\nconst jobPrompt = (j) => `Work performance task ${j.id} (${j.title}) of plugin \"${plugin}\" in the git worktree ${worktree} (stay there; run git and pnpm from its root).\nRead ${plugin}\u002Fdocs\u002Ftasks\u002F${j.file}, ${plugin}\u002Fdocs\u002FTASKS.md, ${plugin}\u002FCLAUDE.md, .claude\u002Frules\u002Fplugin-docs-tasks.md and the rules the task names.\n1. Check the task against the CURRENT code (moved files, renamed symbols, drift). Obsolete or not worth doing: status closed with the reason in the task document, no code.\n2. Otherwise: failing test first (it must fail without the fix), then the smallest root-cause change in ${plugin}\u002Fsrc, never in plugin\u002F**\u002F*.mjs. Measure before and after where the task asks for it.\n3. Run \\`pnpm --filter ${plugin} build\\`, \\`pnpm lint\\`, \\`pnpm --filter ${plugin} test\\`; fix until green. Read the output; never claim green unseen.\n4. Update the task document (status, Verification with the test and numbers, the version that ships it) and TASKS.md in the same commit. Bump ${plugin}\u002Fpackage.json version (patch, minor for behaviour) only if \\`git diff origin\u002Fmain -- ${plugin}\u002Fpackage.json\\` shows no version change yet, then rebuild.\n5. \\`git add\\` only what this job changed, commit (message \"${plugin}: ${j.id} \u003Cwhat>\", no Co-Authored-By, no generated-with footer), \\`git push -u origin HEAD\\`.\nReturn status done|closed|blocked (blocked: tests cannot be made green or the task needs a user decision; commit nothing broken), the commit sha, and one summary sentence.`\n\nconst reviewPrompt = () => `Review the work of this run on the branch in the git worktree ${worktree} (everything since origin\u002Fmain for plugin \"${plugin}\"; stay in the worktree).\n1. Invoke the Skill \"simplify\" once on the branch changes and apply its fixes.\n2. Invoke the Skill \"code-review\" with args \"high --fix\" (never max) on the branch.\n3. Run \\`pnpm --filter ${plugin} build\\`, \\`pnpm lint\\`, \\`pnpm --filter ${plugin} test\\` and fix until green; read the output.\n4. If anything changed: \\`git add\\` it, commit (\"${plugin}: simplify and review fixes\", no Co-Authored-By) and \\`git push\\`. Never touch plugin\u002F**\u002F*.mjs by hand. Then check that \\`git status --short\\` is empty and \\`git rev-parse HEAD\\` equals \\`git rev-parse @{u}\\`; otherwise commit and push again.\nReturn status clean (nothing to change), fixed or blocked (not green), the commit sha and one summary sentence.`\n\nconst analysisPrompt = () => `Run a fresh performance analysis of plugin \"${plugin}\" in the git worktree ${worktree}. Follow .claude\u002Frules\u002Fplugin-docs-tasks.md and the method of the latest ${plugin}\u002Fdocs\u002FEVALUATION-*.md (and ${plugin}\u002Fdocs\u002FREADME.md if present). Date: ${date}.\nWrite ${plugin}\u002Fdocs\u002FEVALUATION-${date}.md (a dated file; never edit old numbers; state what was and was not run). New findings: ${plugin}\u002Fdocs\u002Ftasks\u002FF\u003Cnext free nn>-\u003Cslug>.md with status open, frontmatter and sections per the rule; update TASKS.md. Docs only: do not change code.\n\\`git add\\` the docs, commit (\"${plugin}: performance analysis ${date}\", no Co-Authored-By) and \\`git push -u origin HEAD\\`. Then check that \\`git status --short\\` is empty and \\`git rev-parse HEAD\\` equals \\`git rev-parse @{u}\\`; otherwise commit and push again. Return the ids of the new open tasks.`\n\nconst results = []\nif (args.mode === 'jobs') {\n  phase('Jobs')\n  for (const j of args.jobs) {\n    const r = await run(jobPrompt(j), { label: j.id, phase: 'Jobs', model: j.model, effort: j.effort, schema: JOB })\n    results.push({ id: j.id, ...(r ?? { status: 'blocked', summary: 'agent failed' }) })\n    log(`${j.id}: ${results.at(-1).status}`)\n    if (results.at(-1).status === 'blocked') break\n  }\n}\n\nlet proceed = results.every((r) => r.status !== 'blocked')\nlet review = null\nif (proceed && results.some((r) => r.status === 'done')) {\n  phase('Review')\n  review = await run(reviewPrompt(), { label: 'simplify + code-review', phase: 'Review', model: 'opus', effort: 'high', schema: REVIEW })\n  log(`review: ${review?.status ?? 'agent failed'}`)\n  proceed = review !== null && review.status !== 'blocked'\n}\n\nlet analysis = null\nif (args.mode === 'analyse' || proceed) {\n  phase('Analysis')\n  analysis = await run(analysisPrompt(), { label: 'analysis', phase: 'Analysis', model: 'opus', effort: 'xhigh', schema: ANALYSIS })\n} else {\n  log('Analysis skipped: a job or the review is blocked')\n}\nreturn { results, analysis }\n```\n","# perf-worklist\n\nSystematic run over `\u003Cplugin>\u002Fdocs\u002F` (layout and task rules: `.claude\u002Frules\u002Fplugin-docs-tasks.md`, pattern from `dprint\u002Fdocs\u002F`). The argument is the plugin directory name; stop with one line if `\u003Cplugin>\u002Fpackage.json` does not exist.\n\nThe user's request for this skill is the opt-in for the Workflow tool (load `workflow-authoring` first if it is not loaded).\n\n## Start: worktree and branch\n\nFirst action, before reading anything: check whether the session already is in a linked git worktree (`git rev-parse --git-dir` ends in `\u002Fworktrees\u002F\u003Cname>`, or `--git-common-dir` differs from `--git-dir`). If not, call `EnterWorktree` (load it via ToolSearch if deferred) with `name: \"perf-\u003Cplugin>\"` to switch into a new one, then `git switch -c perf\u002F\u003Cplugin>-\u003CYYYY-MM-DD>` (one branch and one draft PR for the whole run). In an existing linked worktree only create that branch when the current one has no commits of its own. Never nest. Note the worktree's absolute path and today's date: both go into the workflow `args`.\n\n## Step 1: open tasks to jobs\n\n1. Read `\u003Cplugin>\u002Fdocs\u002FTASKS.md`. An open task is an unchecked `- [ ]` entry (tags `open`, `partial`, `docs-only`, `measurement-only`) or a task document with `status: open|partial|docs-only`. Read each open task's `tasks\u002F\u003Cid>-\u003Cslug>.md`.\n2. **No open task** (or no list): run the analysis first (step 3 with `mode: \"analyse\"`), then repeat this step with the new list. Nothing open after the analysis: report that and stop.\n3. **One job per open task**, in the order of the `Dependencies` section of `TASKS.md` (else priority, then id). For every job pick `model` and `effort` (hard cap: `opus` and `xhigh`, never `max`):\n   - Ask jev-api once per task (`mcp__jev-api__batch`, state = the task document text): `score` \"How large and risky is the change?\" with levels `[S: docs or one line, M: one function with tests, L: several functions or modules, XL: cross-cutting, concurrency or protocol change]`, rounded to the nearest level. Low confidence (below 0.5), an error or no configuration: judge it yourself from the same criteria and say so in one line.\n   - Map: S -> `haiku`\u002F`low` (docs-only and closed-without-code decisions: `sonnet`\u002F`low`), M -> `sonnet`\u002F`medium`, L -> `opus`\u002F`high`, XL -> `opus`\u002F`xhigh`. A `measurement-only` task is at least `sonnet`\u002F`medium`.\n   - Show the table (id, title, size, model, effort) in the reply before starting.\n\n## Step 2: jobs (Workflow, sequential)\n\nRun the script below with `Workflow`, `args = { mode: \"jobs\", plugin, worktree, date, jobs: [{ id, file, title, model, effort }] }`. Every cache, buffer or merged request a job adds names its invalidation points and gets one test per point (`.claude\u002Frules\u002Fhook-caches-and-tests.md`): in the jevfort run most later bugs were regressions of exactly these. Jobs run one after the other in the same worktree (no `isolation`; they all edit the same files). Every job commits and pushes itself. A `blocked` job stops the run; report it and leave the rest open.\n\nAfter the last job and before the analysis, a review job runs (when at least one job shipped code or docs): `\u002Fsimplify` once, then `\u002Fcode-review high --fix` on the branch, then build, lint and tests again, commit and push of what changed (`opus`\u002F`high`; `high` is the ceiling here, never `max`). A blocked review also skips the analysis.\n\n## Step 3: analysis\n\nThe script's last phase (and `mode: \"analyse\"`) runs one analysis agent (`opus`\u002F`xhigh`, read-only on code, writes docs only): method of `\u003Cplugin>\u002Fdocs\u002FEVALUATION-*.md` (same machine, built output, 5+ repetitions where cheap, a comparison with the previous evaluation, never edit old numbers), new findings as `tasks\u002F\u003Cid>-\u003Cslug>.md` with the next free `F\u003Cnn>` id and `status: open`, `TASKS.md` updated. It commits and pushes, and returns the new open ids.\n\nThe review and the analysis commit and push their own changes like every job; the run ends with a clean `git status` and the branch head equal to its upstream.\n\nNew open tasks after the closing analysis are reported, not worked in the same run: a new run of this skill works them off.\n\n## Finish\n\nAfter the workflow: `gh pr create --draft` for the branch when none exists (`gh pr view` first), title `\u003Cplugin>: performance task list (\u003Cn> jobs)`, body = per-job table with status and commit. No attribution lines. Report the PR URL, the per-job outcome and the new open ids.\n\n## Workflow script\n\n```js\nexport const meta = {\n  name: 'perf-worklist',\n  description: 'Work off a plugin perf task list job by job (commit + push each), then re-run the analysis',\n  phases: [\n    { title: 'Jobs', detail: 'one subagent per open task, sequential' },\n    { title: 'Review', detail: '\u002Fsimplify, then \u002Fcode-review --fix on the branch' },\n    { title: 'Analysis', detail: 'fresh performance analysis' },\n  ],\n}\n\nconst JOB = { type: 'object', properties: { status: { enum: ['done', 'closed', 'blocked'] }, commit: { type: 'string' }, summary: { type: 'string' } }, required: ['status', 'summary'] }\nconst REVIEW = { type: 'object', properties: { status: { enum: ['clean', 'fixed', 'blocked'] }, commit: { type: 'string' }, summary: { type: 'string' } }, required: ['status', 'summary'] }\nconst ANALYSIS = { type: 'object', properties: { newOpen: { type: 'array', items: { type: 'string' } }, summary: { type: 'string' } }, required: ['newOpen', 'summary'] }\nconst { plugin, worktree, date } = args\n\n\u002F\u002F No human reads the agents' text: no narration between tool calls, only the structured result.\nconst QUIET = '\\n\\nNo narration: no text between tool calls, no plans, no progress notes, no recap. Call tools silently and end with the structured result only.'\nconst run = (prompt, opts) => agent(prompt + QUIET, opts)\n\nconst jobPrompt = (j) => `Work performance task ${j.id} (${j.title}) of plugin \"${plugin}\" in the git worktree ${worktree} (stay there; run git and pnpm from its root).\nRead ${plugin}\u002Fdocs\u002Ftasks\u002F${j.file}, ${plugin}\u002Fdocs\u002FTASKS.md, ${plugin}\u002FCLAUDE.md, .claude\u002Frules\u002Fplugin-docs-tasks.md and the rules the task names.\n1. Check the task against the CURRENT code (moved files, renamed symbols, drift). Obsolete or not worth doing: status closed with the reason in the task document, no code.\n2. Otherwise: failing test first (it must fail without the fix), then the smallest root-cause change in ${plugin}\u002Fsrc, never in plugin\u002F**\u002F*.mjs. Measure before and after where the task asks for it.\n3. Run \\`pnpm --filter ${plugin} build\\`, \\`pnpm lint\\`, \\`pnpm --filter ${plugin} test\\`; fix until green. Read the output; never claim green unseen.\n4. Update the task document (status, Verification with the test and numbers, the version that ships it) and TASKS.md in the same commit. Bump ${plugin}\u002Fpackage.json version (patch, minor for behaviour) only if \\`git diff origin\u002Fmain -- ${plugin}\u002Fpackage.json\\` shows no version change yet, then rebuild.\n5. \\`git add\\` only what this job changed, commit (message \"${plugin}: ${j.id} \u003Cwhat>\", no Co-Authored-By, no generated-with footer), \\`git push -u origin HEAD\\`.\nReturn status done|closed|blocked (blocked: tests cannot be made green or the task needs a user decision; commit nothing broken), the commit sha, and one summary sentence.`\n\nconst reviewPrompt = () => `Review the work of this run on the branch in the git worktree ${worktree} (everything since origin\u002Fmain for plugin \"${plugin}\"; stay in the worktree).\n1. Invoke the Skill \"simplify\" once on the branch changes and apply its fixes.\n2. Invoke the Skill \"code-review\" with args \"high --fix\" (never max) on the branch.\n3. Run \\`pnpm --filter ${plugin} build\\`, \\`pnpm lint\\`, \\`pnpm --filter ${plugin} test\\` and fix until green; read the output.\n4. If anything changed: \\`git add\\` it, commit (\"${plugin}: simplify and review fixes\", no Co-Authored-By) and \\`git push\\`. Never touch plugin\u002F**\u002F*.mjs by hand. Then check that \\`git status --short\\` is empty and \\`git rev-parse HEAD\\` equals \\`git rev-parse @{u}\\`; otherwise commit and push again.\nReturn status clean (nothing to change), fixed or blocked (not green), the commit sha and one summary sentence.`\n\nconst analysisPrompt = () => `Run a fresh performance analysis of plugin \"${plugin}\" in the git worktree ${worktree}. Follow .claude\u002Frules\u002Fplugin-docs-tasks.md and the method of the latest ${plugin}\u002Fdocs\u002FEVALUATION-*.md (and ${plugin}\u002Fdocs\u002FREADME.md if present). Date: ${date}.\nWrite ${plugin}\u002Fdocs\u002FEVALUATION-${date}.md (a dated file; never edit old numbers; state what was and was not run). New findings: ${plugin}\u002Fdocs\u002Ftasks\u002FF\u003Cnext free nn>-\u003Cslug>.md with status open, frontmatter and sections per the rule; update TASKS.md. Docs only: do not change code.\n\\`git add\\` the docs, commit (\"${plugin}: performance analysis ${date}\", no Co-Authored-By) and \\`git push -u origin HEAD\\`. Then check that \\`git status --short\\` is empty and \\`git rev-parse HEAD\\` equals \\`git rev-parse @{u}\\`; otherwise commit and push again. Return the ids of the new open tasks.`\n\nconst results = []\nif (args.mode === 'jobs') {\n  phase('Jobs')\n  for (const j of args.jobs) {\n    const r = await run(jobPrompt(j), { label: j.id, phase: 'Jobs', model: j.model, effort: j.effort, schema: JOB })\n    results.push({ id: j.id, ...(r ?? { status: 'blocked', summary: 'agent failed' }) })\n    log(`${j.id}: ${results.at(-1).status}`)\n    if (results.at(-1).status === 'blocked') break\n  }\n}\n\nlet proceed = results.every((r) => r.status !== 'blocked')\nlet review = null\nif (proceed && results.some((r) => r.status === 'done')) {\n  phase('Review')\n  review = await run(reviewPrompt(), { label: 'simplify + code-review', phase: 'Review', model: 'opus', effort: 'high', schema: REVIEW })\n  log(`review: ${review?.status ?? 'agent failed'}`)\n  proceed = review !== null && review.status !== 'blocked'\n}\n\nlet analysis = null\nif (args.mode === 'analyse' || proceed) {\n  phase('Analysis')\n  analysis = await run(analysisPrompt(), { label: 'analysis', phase: 'Analysis', model: 'opus', effort: 'xhigh', schema: ANALYSIS })\n} else {\n  log('Analysis skipped: a job or the review is blocked')\n}\nreturn { results, analysis }\n```\n",{"name":5,"description":7,"argument-hint":24},"\u003Cplugin-name>","main","bb893ea76ba6e0d3f64bb1f59d9020751fc5d618",".claude\u002Fskills\u002Fperf-worklist","https:\u002F\u002Fgithub.com\u002Fkwitsch\u002Fclaude-plugins-development","https:\u002F\u002Fgithub.com\u002Fkwitsch","2026-11-15 18:25:39",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add kwitsch\u002Fclaude-plugins-development --skill perf-worklist",{"tool":37,"command":38},"bunx","bunx skills add kwitsch\u002Fclaude-plugins-development --skill perf-worklist",{"tool":40,"command":41},"pnpm","pnpm dlx skills add kwitsch\u002Fclaude-plugins-development --skill perf-worklist","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkwitsch\u002Fclaude-plugins-development\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fperf-worklist\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M7FDF4DKMYQ2TTKD6TBJ6T0B","universal-lint","User-invoked. Takes a free-text description of a set of files (\"all files in src\u002F\", \"files changed in PR 123\", or an explicit list) and lints each of them exactly as this plugin's Write\u002FEdit hook would — read-only, no autofix — printing one aggregated findings report. Self-contained: depends on no other plugin.","https:\u002F\u002Fgithub.com\u002Fkwitsch\u002Fclaude-plugins-development\u002Fblob\u002Fmain\u002Funiversal-lint\u002Fplugin\u002Fskills\u002Funiversal-lint\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7FDEXH3PZGS7PPQBNV9RTRS","solve","Single entry point for any coding task (change, feature, refactor, bug). Triages the task through the jev-api tools and routes it to the right track, loading the phase references it needs. Flags --headless (the decider agent answers every question) and --size=\u003CS|M|L|XL>. Use when the user hands over a task to implement or fix.","https:\u002F\u002Fgithub.com\u002Fkwitsch\u002Fclaude-plugins-development\u002Fblob\u002Fmain\u002Fjev-solver\u002Fplugin\u002Fskills\u002Fsolve\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7FDEM07PDNZ9DBZF90CVDBZ","dprint","Runs dprint for the project. The first argument selects the action - init checks for the plugin's minimum dprint version, installs or updates dprint at user level after confirmation via AskUserQuestion, offers to create a dprint config when none exists and to add dprint plugins for file types the config does not cover; check [scope] runs dprint check; fmt [scope] runs dprint fmt and rewrites files; without an argument it runs fmt on the whole current directory. Use init when the user wants dprint set up, installed, updated, checked or its plugins completed; check when they want formatting verified with dprint; fmt only when they ask to format files with dprint. When invoking this skill yourself, always pass init, check or fmt as the first argument.","https:\u002F\u002Fgithub.com\u002Fkwitsch\u002Fclaude-plugins-development\u002Fblob\u002Fmain\u002Fdprint\u002Fplugin\u002Fskills\u002Fdprint\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7FDEENDBD9H0PK0BM3CG0CX","split-hooks-lib","Split the hooks module of a function-hooks plugin of this repository into a readable entry register.mts plus helper modules that the build bundles into one compressed plugin\u002Fhooks\u002Flib.mjs, to keep the shipped size small. Use when the user asks to split a plugin's register.mts, to make a plugin smaller, to move a plugin to register.mjs plus lib.mjs, or when a hooks module has grown too large for one file.","https:\u002F\u002Fgithub.com\u002Fkwitsch\u002Fclaude-plugins-development\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fsplit-hooks-lib\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7FDEBDF3CXHKQ9XDXRTT7RC","__SKILL_NAME__","__SKILL_DESCRIPTION__ Use when the user asks to …","https:\u002F\u002Fgithub.com\u002Fkwitsch\u002Fclaude-plugins-development\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fscaffold-plugin\u002Ftemplates\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7FDE5RSE231MVBRWM69TJ30","scaffold-plugin","Scaffold a new Claude Code plugin in this repository with the repo layout (\u003Cname>\u002Fpackage.json, plugin\u002F, src\u002F, tests\u002F). Use when the user asks to create, add, scaffold or start a new plugin here.","https:\u002F\u002Fgithub.com\u002Fkwitsch\u002Fclaude-plugins-development\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fscaffold-plugin\u002FSKILL.md",[],[]]