[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79CXBBSNH50ME4G1ZCPXAPR":3,"skill-same:01M79CXBBSNH50ME4G1ZCPXAPR":64},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M79CXBBSNH50ME4G1ZCPXAPR","refactor",null,"Refactor explicitly scoped changes while preserving behavior, validating the result, and producing a concise handoff.","JanMichaelSE\u002Fagentic-marketplace","JanMichaelSE","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F55473580?v=4","01M79CW862FGHY91NG8DDRRFJC","Jan M Montalvo","01M79CW86M2NJQNRZ41VP9AJ51",1,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FJanMichaelSE\u002Fagentic-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fai-workflow\u002Fskills\u002Frefactor\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: refactor\ndescription: Refactor explicitly scoped changes while preserving behavior, validating the result, and producing a concise handoff.\n---\n\n# Refactor\n\nRefactor an explicit code boundary after implementation or during standalone cleanup. Keep behavior unchanged, improve maintainability, and leave clear validation evidence.\n\nUse this skill when the user supplies either workflow inputs from a feature root or a standalone boundary such as a branch comparison, commit range, staged diff, working-tree diff, or file\u002Fdirectory scope.\n\n## Required Inputs\n\nBefore editing, confirm one mode.\n\nWorkflow mode requires:\n\n- A feature root, for example `.scratch\u002F\u003Cfeature-slug>\u002F`.\n- One or more implementation summary paths from that feature root.\n- One concrete refactor boundary for the complete implemented workflow, such as a working-tree diff, staged diff, commit range, branch comparison, or explicit file\u002Fdirectory scope.\n\nStandalone mode requires one explicit boundary:\n\n- Branch comparison.\n- Commit range.\n- Staged diff.\n- Working-tree diff.\n- File or directory scope.\n\nIf the boundary is missing, ambiguous, or repo-wide without a concrete reason, ask for a narrower scope before editing. Standalone mode does not require workflow artifacts or a feature root.\n\n## Reference Files\n\nRead these reference files before doing non-trivial refactor work:\n\n- [Lens agent brief](references\u002Flens-agent-brief.md)\n- [Refactor lenses](references\u002Flenses.md)\n- [Refactor summary template](references\u002Frefactor-summary-template.md)\n\n## Process\n\n### 1. Inspect Scope and State\n\nInspect the supplied source inputs fully. In workflow mode, read the feature root, all supplied implementation summaries, and the execution plan when it is discoverable. Read related slices only when needed to understand the supplied boundary or implementation evidence. Treat those files as inputs; do not mutate implementation summaries, slice files, or execution plans.\n\nInspect and report the initial git state, including tracked modifications and relevant untracked files. A dirty working tree is not a blocker by itself. Stop before editing if unrelated dirty changes overlap the requested boundary in a way that makes ownership unsafe.\n\n### 2. Rediscover Guardrails\n\nRediscover current repo guardrails at execution time. Check applicable agent instructions, README or contributing docs, validation scripts, nearby implementation patterns, nearby tests, and dependency rules.\n\nDo not add dependencies, change public behavior, rewrite governing docs, create or change branches, commit, push, create pull requests, post pull request comments, update Jira, or perform external workflow actions. If a user explicitly requests one of these actions, treat it as separate authorization outside the default refactor workflow.\n\n### 3. Run Refactor Lenses\n\nFor non-trivial scopes, strongly prefer lens agents. Give each lens agent the shared [lens agent brief](references\u002Flens-agent-brief.md), the relevant lens from [lenses](references\u002Flenses.md), the source inputs, and the current diff or scoped files.\n\nLens agents are findings-only. They do not edit files, run broad rewrites, decide final scope, or write the durable refactor summary. The refactor workflow owns aggregation, edit decisions, validation, and final handoff.\n\nIf lens agents are unavailable, the scope is trivial, or the client cannot run parallel agents, perform the lenses sequentially yourself and record that fallback in the summary or chat handoff.\n\n### 4. Refactor\n\nMake one consolidated behavior-preserving edit pass based on the lens findings and current repo patterns. In workflow mode, refactor once for the supplied feature-level boundary; do not run per-slice refactor passes.\n\nAllowed refactors include simplifying control flow, reducing duplication, improving names, tightening module boundaries, improving test clarity without weakening assertions, removing unnecessary work, and removing dead code only when proven dead inside the explicit boundary.\n\nAvoid broad cleanup sweeps and speculative abstractions. New abstractions must remove real duplication, reduce meaningful complexity, clarify a repeated concept, or match an established local pattern.\n\nIf necessary supporting edits fall just outside the boundary, keep them minimal and record why. Stop and ask before expanding into unrelated modules, changing acceptance behavior, or weakening tests.\n\n### 5. Validate\n\nRun focused validation that matches the touched files and repo guardrails. Run broader validation when shared contracts, broad utilities, generated artifacts, or higher-risk behavior are touched.\n\nUse up to three focused refactor attempts total. If validation still fails, stop and report `blocked` with the failing evidence and remaining risk.\n\n### 6. Write Summary and Handoff\n\nWorkflow mode writes exactly one feature-level refactor summary at:\n\n```text\n.scratch\u002F\u003Cfeature-slug>\u002Frefactor\u002F\u003Cscope-stem>-refactor-summary.md\n```\n\nDerive `\u003Cscope-stem>` from the supplied refactor boundary when possible, such as `working-tree`, `staged`, a commit range label, a branch comparison label, or a concise file\u002Fdirectory scope label.\n\nUse the [refactor summary template](references\u002Frefactor-summary-template.md). The summary status must be `refactored`, `no-op`, or `blocked`.\n\nStandalone mode returns a concise chat handoff by default. Write a durable artifact only when the user requests one or provides a `.scratch` context.\n\nAll modes require a final chat handoff with:\n\n- Status.\n- Summary path, if written.\n- Files changed.\n- Validation evidence.\n- Behavior-preservation notes.\n- Skipped or escalated findings.\n- Remaining risks or follow-up.\n- Whether changes remain uncommitted.\n","# Refactor\n\nRefactor an explicit code boundary after implementation or during standalone cleanup. Keep behavior unchanged, improve maintainability, and leave clear validation evidence.\n\nUse this skill when the user supplies either workflow inputs from a feature root or a standalone boundary such as a branch comparison, commit range, staged diff, working-tree diff, or file\u002Fdirectory scope.\n\n## Required Inputs\n\nBefore editing, confirm one mode.\n\nWorkflow mode requires:\n\n- A feature root, for example `.scratch\u002F\u003Cfeature-slug>\u002F`.\n- One or more implementation summary paths from that feature root.\n- One concrete refactor boundary for the complete implemented workflow, such as a working-tree diff, staged diff, commit range, branch comparison, or explicit file\u002Fdirectory scope.\n\nStandalone mode requires one explicit boundary:\n\n- Branch comparison.\n- Commit range.\n- Staged diff.\n- Working-tree diff.\n- File or directory scope.\n\nIf the boundary is missing, ambiguous, or repo-wide without a concrete reason, ask for a narrower scope before editing. Standalone mode does not require workflow artifacts or a feature root.\n\n## Reference Files\n\nRead these reference files before doing non-trivial refactor work:\n\n- [Lens agent brief](references\u002Flens-agent-brief.md)\n- [Refactor lenses](references\u002Flenses.md)\n- [Refactor summary template](references\u002Frefactor-summary-template.md)\n\n## Process\n\n### 1. Inspect Scope and State\n\nInspect the supplied source inputs fully. In workflow mode, read the feature root, all supplied implementation summaries, and the execution plan when it is discoverable. Read related slices only when needed to understand the supplied boundary or implementation evidence. Treat those files as inputs; do not mutate implementation summaries, slice files, or execution plans.\n\nInspect and report the initial git state, including tracked modifications and relevant untracked files. A dirty working tree is not a blocker by itself. Stop before editing if unrelated dirty changes overlap the requested boundary in a way that makes ownership unsafe.\n\n### 2. Rediscover Guardrails\n\nRediscover current repo guardrails at execution time. Check applicable agent instructions, README or contributing docs, validation scripts, nearby implementation patterns, nearby tests, and dependency rules.\n\nDo not add dependencies, change public behavior, rewrite governing docs, create or change branches, commit, push, create pull requests, post pull request comments, update Jira, or perform external workflow actions. If a user explicitly requests one of these actions, treat it as separate authorization outside the default refactor workflow.\n\n### 3. Run Refactor Lenses\n\nFor non-trivial scopes, strongly prefer lens agents. Give each lens agent the shared [lens agent brief](references\u002Flens-agent-brief.md), the relevant lens from [lenses](references\u002Flenses.md), the source inputs, and the current diff or scoped files.\n\nLens agents are findings-only. They do not edit files, run broad rewrites, decide final scope, or write the durable refactor summary. The refactor workflow owns aggregation, edit decisions, validation, and final handoff.\n\nIf lens agents are unavailable, the scope is trivial, or the client cannot run parallel agents, perform the lenses sequentially yourself and record that fallback in the summary or chat handoff.\n\n### 4. Refactor\n\nMake one consolidated behavior-preserving edit pass based on the lens findings and current repo patterns. In workflow mode, refactor once for the supplied feature-level boundary; do not run per-slice refactor passes.\n\nAllowed refactors include simplifying control flow, reducing duplication, improving names, tightening module boundaries, improving test clarity without weakening assertions, removing unnecessary work, and removing dead code only when proven dead inside the explicit boundary.\n\nAvoid broad cleanup sweeps and speculative abstractions. New abstractions must remove real duplication, reduce meaningful complexity, clarify a repeated concept, or match an established local pattern.\n\nIf necessary supporting edits fall just outside the boundary, keep them minimal and record why. Stop and ask before expanding into unrelated modules, changing acceptance behavior, or weakening tests.\n\n### 5. Validate\n\nRun focused validation that matches the touched files and repo guardrails. Run broader validation when shared contracts, broad utilities, generated artifacts, or higher-risk behavior are touched.\n\nUse up to three focused refactor attempts total. If validation still fails, stop and report `blocked` with the failing evidence and remaining risk.\n\n### 6. Write Summary and Handoff\n\nWorkflow mode writes exactly one feature-level refactor summary at:\n\n```text\n.scratch\u002F\u003Cfeature-slug>\u002Frefactor\u002F\u003Cscope-stem>-refactor-summary.md\n```\n\nDerive `\u003Cscope-stem>` from the supplied refactor boundary when possible, such as `working-tree`, `staged`, a commit range label, a branch comparison label, or a concise file\u002Fdirectory scope label.\n\nUse the [refactor summary template](references\u002Frefactor-summary-template.md). The summary status must be `refactored`, `no-op`, or `blocked`.\n\nStandalone mode returns a concise chat handoff by default. Write a durable artifact only when the user requests one or provides a `.scratch` context.\n\nAll modes require a final chat handoff with:\n\n- Status.\n- Summary path, if written.\n- Files changed.\n- Validation evidence.\n- Behavior-preservation notes.\n- Skipped or escalated findings.\n- Remaining risks or follow-up.\n- Whether changes remain uncommitted.\n",{"name":5,"description":7},"main","d9e185f133b5cbcd785341095a241d0c64d8310d","plugins\u002Fai-workflow\u002Fskills\u002Frefactor",0,"https:\u002F\u002Fgithub.com\u002FJanMichaelSE\u002Fagentic-marketplace","https:\u002F\u002Fgithub.com\u002FJanMichaelSE","Software Developer | B.S. Computer Science ","2026-11-14 06:36:51",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add JanMichaelSE\u002Fagentic-marketplace --skill refactor",{"tool":38,"command":39},"bunx","bunx skills add JanMichaelSE\u002Fagentic-marketplace --skill refactor",{"tool":41,"command":42},"pnpm","pnpm dlx skills add JanMichaelSE\u002Fagentic-marketplace --skill refactor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJanMichaelSE\u002Fagentic-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fai-workflow\u002Fskills\u002Frefactor\u002FSKILL.md",true,[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",107,"https:\u002F\u002Fgithub.com\u002FJanMichaelSE\u002Fagentic-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fai-workflow\u002Fskills\u002Frefactor\u002Fagents\u002Fopenai.yaml",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Flens-agent-brief.md",1314,"https:\u002F\u002Fgithub.com\u002FJanMichaelSE\u002Fagentic-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fai-workflow\u002Fskills\u002Frefactor\u002Freferences\u002Flens-agent-brief.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Flenses.md",2600,"https:\u002F\u002Fgithub.com\u002FJanMichaelSE\u002Fagentic-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fai-workflow\u002Fskills\u002Frefactor\u002Freferences\u002Flenses.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Frefactor-summary-template.md",387,"https:\u002F\u002Fgithub.com\u002FJanMichaelSE\u002Fagentic-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fai-workflow\u002Fskills\u002Frefactor\u002Freferences\u002Frefactor-summary-template.md",[65,72,79,86,93,100],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M79D1SP72BJKFZDHH2W0VT9G","ui-ux-pro-max","UI\u002FUX design intelligence for web and mobile. Local database with 79 searchable styles (88 catalog entries), 192 color palettes, 74 font pairings, 192 product types, 119 UX guidelines, 105 curated icon entries, 17 GSAP motion presets, and 25 chart types across 22 stacks (React, Next.js, Vue, Nuxt, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn\u002Fui, Jetpack Compose, Angular, Laravel, JavaFX, WPF, WinUI, Avalonia, Uno Platform, UWP, Three.js, and HTML\u002FCSS). Use when designing, building, or reviewing UI: pages, components, color schemes, typography, layout, accessibility, animation, or data visualization.","https:\u002F\u002Fgithub.com\u002FJanMichaelSE\u002Fagentic-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fui-ux\u002Fskills\u002Fui-ux-pro-max\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M79D1NPRNKYC0GNSPQBG02AD","figma-mcp","Implement or compare UI against Figma designs using an available Figma MCP integration. Use for Figma-backed implementation, design-token extraction, or visual-parity gap analysis; Figma MCP access is optional and must already be configured by the user.","https:\u002F\u002Fgithub.com\u002FJanMichaelSE\u002Fagentic-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fui-ux\u002Fskills\u002Ffigma-mcp\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M79D1HW8E8EBKHYD0VRPAGDB","improve-codebase-architecture","Find evidence-based, active-change architecture improvements using shared design and domain-modeling guidance. Use when a user wants to reduce architectural friction, deepen a module, or make a current change safer, more testable, and easier to navigate.","https:\u002F\u002Fgithub.com\u002FJanMichaelSE\u002Fagentic-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fsoftware-architecture\u002Fskills\u002Fimprove-codebase-architecture\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M79D1E9DJ22BZN68FGNEY6H9","domain-modeling","Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing GLOSSARY.md or CONTEXT.md, or recording or editing an ADR.","https:\u002F\u002Fgithub.com\u002FJanMichaelSE\u002Fagentic-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fsoftware-architecture\u002Fskills\u002Fdomain-modeling\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M79D1BWY6DT3SDNRVRJV73PH","codebase-design","Provide the shared vocabulary and discipline for designing deep modules with clear interfaces and seams. Use when a user wants to design or improve a module, find deepening opportunities, choose a seam, or make code more testable and AI-navigable.","https:\u002F\u002Fgithub.com\u002FJanMichaelSE\u002Fagentic-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fsoftware-architecture\u002Fskills\u002Fcodebase-design\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M79D176DSM0779MS5PCW022A","test-coverage-review","MUST invoke to review whether added or updated tests cover code changes in a diff. Checks new logic, branches, error paths, and regression risk, producing a change-to-test matrix. Use requirements-to-tests-traceability for acceptance-criteria mapping and orchestrated-review for bundled reviews.","https:\u002F\u002Fgithub.com\u002FJanMichaelSE\u002Fagentic-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Freview-toolkit\u002Fskills\u002Ftest-coverage-review\u002FSKILL.md",[],[]]