[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72V4YZPZPW0J3RS1Q5WF885":3,"skill-same:01M72V4YZPZPW0J3RS1Q5WF885":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":5,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M72V4YZPZPW0J3RS1Q5WF885","diff-walkthrough",null,"Produce a guided walkthrough of a code diff, pull request, merge request, commit range, or staged changes. Use when the user asks to explain, narrate, summarize, review, or walk through a diff. Supports configurable depth and output formats, defaults to HTML, and uses Plannotator when available.","roerohan\u002Fskills","roerohan","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F42958812?v=4","01M72V46MPJK55W3BZ44Y869D1","Rohan Mukherjee","01M72V46N9GPDNRC4RHVRR2YCB",29,"MIT","https:\u002F\u002Fgithub.com\u002Froerohan\u002Fskills\u002Fblob\u002Fmain\u002Fdiff-walkthrough\u002FSKILL.md",[],[],"2026-11-10 22:39:42",false,"---\nname: diff-walkthrough\ndescription: Produce a guided walkthrough of a code diff, pull request, merge request, commit range, or staged changes. Use when the user asks to explain, narrate, summarize, review, or walk through a diff. Supports configurable depth and output formats, defaults to HTML, and uses Plannotator when available.\n---\n\n# Diff Walkthrough\n\nGenerate a grounded, reader-friendly walkthrough of a code change. Explain the change in the order a human should read it, not in filesystem or diff order.\n\nUse the references for detailed rules when the diff is non-trivial:\n\n- [`references\u002Ffile-roles.md`](references\u002Ffile-roles.md) for classifying changed files\n- [`references\u002Freading-order.md`](references\u002Freading-order.md) for motif-based ordering\n- [`references\u002Fannotations.md`](references\u002Fannotations.md) for inline callouts and concerns\n- [`references\u002Foutput-formats.md`](references\u002Foutput-formats.md) for HTML, Markdown, terminal, and JSON output contracts\n\n## Invocation\n\nTrigger on requests like:\n\n| User says | Behavior |\n|-----------|----------|\n| \"walk me through this diff\" | Explain the current unstaged or provided diff |\n| \"explain my staged changes\" | Use `git diff --staged` |\n| \"summarize this PR\u002FMR\" | Fetch the hosted review with available tools, then explain it |\n| \"walk through HEAD~3..HEAD\" | Use the requested commit range |\n| \"review this diff\" | Include concerns and risks, not just narration |\n\nIf the source is ambiguous, prefer the safest local source in this order: explicitly provided URL\u002Frange, staged diff, unstaged diff. Ask one short question only if multiple real sources exist and choosing one would materially change the answer.\n\n## Options\n\nParse options from the user's prompt. If omitted, use `depth=standard`, `format=html`, `concerns=off`, and `coverage=collapsed`.\n\n| Option | Values | Meaning |\n|--------|--------|---------|\n| `depth` | `skim`, `standard`, `deep`, `teaching` | Controls detail and vocabulary |\n| `format` | `html`, `markdown`, `terminal`, `json` | Controls output format |\n| `concerns` | `off`, `on` | Adds review-style risks only when requested or implied by \"review\" |\n| `coverage` | `collapsed`, `full` | Collapses noisy files by default; shows everything in full mode |\n\nDepth behavior:\n\n| Depth | Use When | Output |\n|-------|----------|--------|\n| `skim` | \"quick\", \"brief\", \"tldr\" | Intent, impact, reading order, major files only |\n| `standard` | Default | Narrative per meaningful file\u002Fgroup with representative hunks |\n| `deep` | \"deep\", \"thorough\", \"detailed\" | Cross-file relationships, edge cases, tests, migrations, risks |\n| `teaching` | \"novice\", \"teach me\", \"explain simply\" | Plain language, diagrams, definitions, why each layer matters |\n\nFormat behavior:\n\n| Format | Output |\n|--------|--------|\n| `html` | Write or serve a standalone walkthrough artifact and return how to view it |\n| `markdown` | Return or write Markdown, using Mermaid diagrams when useful |\n| `terminal` | Return a concise plain-text walkthrough with ASCII diagrams\u002Ftables |\n| `json` | Return structured data for another tool to render |\n\nIf the user asks for a path, write there. Otherwise write generated walkthrough artifacts under `\u002Ftmp` using `mktemp`; do not place default generated walkthrough files in the repository workspace.\n\n## Source Fetching\n\nUse the most specific available tool for the source:\n\n1. Local git: use `git diff`, `git diff --staged`, `git show`, or `git diff \u003Crange>`.\n2. Hosted review URL: use the matching MCP first when available; only fall back to the matching CLI such as `gh` or `glab` when no suitable MCP is available, then use a local clone if present.\n3. Pasted diff: parse the provided unified diff directly.\n4. Patch files: read the file and treat it as the source diff.\n\nCollect enough context to explain the change accurately:\n\n- Unified diff per changed file\n- File list and line stats\n- Commit messages when available\n- Hosted review title, description, author, and target\u002Fsource refs when available\n- Nearby source context only when the diff alone is insufficient\n\nDo not assume vendor-specific infrastructure. This skill must work without hosted-review integrations or Plannotator.\n\n## Plannotator\n\nBefore producing HTML, check whether Plannotator is available with a lightweight probe such as `command -v plannotator` and, if needed, inspect its help output. Also check obvious repo scripts only if the repository already references Plannotator.\n\nUse Plannotator when all are true:\n\n- The requested format is `html`.\n- Plannotator is installed or clearly available through the repo tooling.\n- Its interface can render the prepared walkthrough without guessing unsupported flags.\n\nWhen Plannotator is available and suitable, write the prepared walkthrough as Markdown under `\u002Ftmp` using `mktemp`, then open that Markdown file with `plannotator annotate \u003Cfile.md> --gate` when the installed help shows `--gate` is supported. Return the Markdown path and the Plannotator command used.\n\nIf Plannotator returns reviewer comments from the annotation gate, handle them based on the source. For local sources that can be safely edited, treat comments as user feedback on the current changes: inspect the referenced code or docs, make the requested fixes when they are safe and clear, run the smallest relevant validation, then generate a new walkthrough artifact under `\u002Ftmp` and open it with Plannotator again. For remote reviews or other sources the agent cannot safely modify, do not attempt fixes; instead respond with an analysis of whether each comment is valid, grounded, in scope for the review, and what change would address it. If the feedback is ambiguous, destructive, or outside the requested diff, ask one short clarifying question before editing or recommending action. Continue the local-fix loop until the gate is approved, comments are exhausted, or the user stops the flow.\n\nIf Plannotator is missing, unsuitable, or its interface is unclear, generate a standalone HTML file under `\u002Ftmp` using `mktemp`, then open or serve it with a lightweight local viewer such as `python3 -m http.server \u003Cport> --directory \u003Cdir>`. Return the HTML path, server URL, and any command needed to stop the server. Do not make Plannotator a hard dependency.\n\nMention in the final response whether Plannotator was used or whether the direct HTML fallback was used.\n\n## Workflow\n\n### 1. Read The Whole Change\n\nFirst identify the motif before narrating files:\n\n- What is the one-sentence purpose of the change?\n- Is it a feature, bugfix, refactor, revert, migration, dependency update, or mechanical change?\n- Which files are the conceptual foundation, core behavior, wiring, UI, tests, docs, or noise?\n- What has to be understood before the rest makes sense?\n\nDo not summarize each file independently until you understand the cross-file story.\n\n### 2. Classify Files\n\nClassify each file as `foundation`, `core`, `wiring`, `ui`, `test`, `docs`, or `noise`; classify its change as `new`, `mod`, `del`, or `ren`. Collapse `noise` by default. In `coverage=full`, include every file but still label noisy files clearly. For detailed rules, follow [`references\u002Ffile-roles.md`](references\u002Ffile-roles.md).\n\n### 3. Choose Reading Order\n\nUse this default order unless the motif calls for an override: foundation, core behavior, wiring and integration, UI, tests, docs, then noise.\n\nOverrides:\n\n- Bugfix: start with the failing behavior or fix, then proof\u002Ftests, then supporting context.\n- Revert: explain what is being backed out and why; avoid over-narrating restored code.\n- Mechanical change: group files by repeated pattern and show one representative example.\n- Migration: start with the old-to-new model, then compatibility or data handling, then call sites.\n\nFor mixed or mechanical diffs, follow [`references\u002Freading-order.md`](references\u002Freading-order.md).\n\n### 4. Explain With Diagrams\n\nPrefer diagrams or charts when they clarify relationships. Do not add decorative diagrams that repeat prose.\n\nUseful diagram types:\n\n- Reading-order map: foundation -> core -> wiring -> tests\n- Request\u002Fdata flow: input -> transformation -> storage\u002Foutput\n- Review feedback loop: walkthrough -> Plannotator comments -> fixes -> refreshed walkthrough\n- Code ownership or responsibility flow: caller -> adapter -> core logic -> output\n- Before\u002Fafter table for API or behavior changes\n- Risk matrix when `concerns=on`\n- File-role chart for large diffs\n\nPrefer flow diagrams when they reveal sequence, responsibility, or feedback loops that prose would force the reader to reconstruct. Avoid decorative diagrams that restate the same bullet list. For HTML, use simple inline SVG, CSS boxes, or tables so the output opens without a build step. For Markdown, use Mermaid when appropriate and include a plain table fallback if the diagram is essential. For terminal output, use ASCII arrows and compact tables.\n\n### 5. Write The Walkthrough\n\nFor each meaningful file or group:\n\n- State what changed concretely, naming symbols, functions, endpoints, commands, or types from the diff.\n- Explain how it relates to earlier and later files in the reading order.\n- Include representative hunks or short code snippets when they teach the change better than prose, especially for new contracts, changed control flow, boundary validation, API shape changes, or subtle removals. Keep snippets small and omit unrelated context.\n- Call out subtle behavior changes separately from obvious edits.\n- In `teaching` depth, define jargon before using it heavily.\n- In `deep` depth, cover edge cases, compatibility, tests, and operational impact.\n\nWhen `concerns=on`, add a clearly separate concerns section. Only include concerns grounded in the diff or inspected context. Do not invent risks.\n\nFor line-level annotations, use the categories and anti-hallucination rules in [`references\u002Fannotations.md`](references\u002Fannotations.md).\n\n### 6. Produce The Chosen Format\n\nHTML should include:\n\n- Title, source metadata, and generated timestamp\n- Executive summary\n- File-role chart or reading-order diagram when useful\n- Guided walkthrough in reading order\n- Representative diff hunks or code snippets\n- Tests and confidence section\n- Concerns section only when enabled\n\nMarkdown should mirror the same structure. Terminal output should be shorter and avoid large hunks. JSON should include at least `summary`, `source`, `options`, `files`, `readingOrder`, `diagrams`, `sections`, `tests`, and `concerns`.\n\nUse [`references\u002Foutput-formats.md`](references\u002Foutput-formats.md) as the output contract for larger walkthroughs or when another tool will consume the result.\n\n## Rules\n\n- Ground every claim in the diff, commit metadata, or inspected source context.\n- Prefer explanation over review unless the user asks for review or `concerns=on`.\n- Do not paste entire large diffs; choose representative hunks.\n- Do not fabricate line numbers, file paths, symbols, or intent.\n- Keep generated files local to the workspace or requested output path.\n- If verification is feasible, run the smallest relevant check for changed generated assets or scripts.\n- If the diff is too large to fully process, say what was covered and what was collapsed.\n","# Diff Walkthrough\n\nGenerate a grounded, reader-friendly walkthrough of a code change. Explain the change in the order a human should read it, not in filesystem or diff order.\n\nUse the references for detailed rules when the diff is non-trivial:\n\n- [`references\u002Ffile-roles.md`](references\u002Ffile-roles.md) for classifying changed files\n- [`references\u002Freading-order.md`](references\u002Freading-order.md) for motif-based ordering\n- [`references\u002Fannotations.md`](references\u002Fannotations.md) for inline callouts and concerns\n- [`references\u002Foutput-formats.md`](references\u002Foutput-formats.md) for HTML, Markdown, terminal, and JSON output contracts\n\n## Invocation\n\nTrigger on requests like:\n\n| User says | Behavior |\n|-----------|----------|\n| \"walk me through this diff\" | Explain the current unstaged or provided diff |\n| \"explain my staged changes\" | Use `git diff --staged` |\n| \"summarize this PR\u002FMR\" | Fetch the hosted review with available tools, then explain it |\n| \"walk through HEAD~3..HEAD\" | Use the requested commit range |\n| \"review this diff\" | Include concerns and risks, not just narration |\n\nIf the source is ambiguous, prefer the safest local source in this order: explicitly provided URL\u002Frange, staged diff, unstaged diff. Ask one short question only if multiple real sources exist and choosing one would materially change the answer.\n\n## Options\n\nParse options from the user's prompt. If omitted, use `depth=standard`, `format=html`, `concerns=off`, and `coverage=collapsed`.\n\n| Option | Values | Meaning |\n|--------|--------|---------|\n| `depth` | `skim`, `standard`, `deep`, `teaching` | Controls detail and vocabulary |\n| `format` | `html`, `markdown`, `terminal`, `json` | Controls output format |\n| `concerns` | `off`, `on` | Adds review-style risks only when requested or implied by \"review\" |\n| `coverage` | `collapsed`, `full` | Collapses noisy files by default; shows everything in full mode |\n\nDepth behavior:\n\n| Depth | Use When | Output |\n|-------|----------|--------|\n| `skim` | \"quick\", \"brief\", \"tldr\" | Intent, impact, reading order, major files only |\n| `standard` | Default | Narrative per meaningful file\u002Fgroup with representative hunks |\n| `deep` | \"deep\", \"thorough\", \"detailed\" | Cross-file relationships, edge cases, tests, migrations, risks |\n| `teaching` | \"novice\", \"teach me\", \"explain simply\" | Plain language, diagrams, definitions, why each layer matters |\n\nFormat behavior:\n\n| Format | Output |\n|--------|--------|\n| `html` | Write or serve a standalone walkthrough artifact and return how to view it |\n| `markdown` | Return or write Markdown, using Mermaid diagrams when useful |\n| `terminal` | Return a concise plain-text walkthrough with ASCII diagrams\u002Ftables |\n| `json` | Return structured data for another tool to render |\n\nIf the user asks for a path, write there. Otherwise write generated walkthrough artifacts under `\u002Ftmp` using `mktemp`; do not place default generated walkthrough files in the repository workspace.\n\n## Source Fetching\n\nUse the most specific available tool for the source:\n\n1. Local git: use `git diff`, `git diff --staged`, `git show`, or `git diff \u003Crange>`.\n2. Hosted review URL: use the matching MCP first when available; only fall back to the matching CLI such as `gh` or `glab` when no suitable MCP is available, then use a local clone if present.\n3. Pasted diff: parse the provided unified diff directly.\n4. Patch files: read the file and treat it as the source diff.\n\nCollect enough context to explain the change accurately:\n\n- Unified diff per changed file\n- File list and line stats\n- Commit messages when available\n- Hosted review title, description, author, and target\u002Fsource refs when available\n- Nearby source context only when the diff alone is insufficient\n\nDo not assume vendor-specific infrastructure. This skill must work without hosted-review integrations or Plannotator.\n\n## Plannotator\n\nBefore producing HTML, check whether Plannotator is available with a lightweight probe such as `command -v plannotator` and, if needed, inspect its help output. Also check obvious repo scripts only if the repository already references Plannotator.\n\nUse Plannotator when all are true:\n\n- The requested format is `html`.\n- Plannotator is installed or clearly available through the repo tooling.\n- Its interface can render the prepared walkthrough without guessing unsupported flags.\n\nWhen Plannotator is available and suitable, write the prepared walkthrough as Markdown under `\u002Ftmp` using `mktemp`, then open that Markdown file with `plannotator annotate \u003Cfile.md> --gate` when the installed help shows `--gate` is supported. Return the Markdown path and the Plannotator command used.\n\nIf Plannotator returns reviewer comments from the annotation gate, handle them based on the source. For local sources that can be safely edited, treat comments as user feedback on the current changes: inspect the referenced code or docs, make the requested fixes when they are safe and clear, run the smallest relevant validation, then generate a new walkthrough artifact under `\u002Ftmp` and open it with Plannotator again. For remote reviews or other sources the agent cannot safely modify, do not attempt fixes; instead respond with an analysis of whether each comment is valid, grounded, in scope for the review, and what change would address it. If the feedback is ambiguous, destructive, or outside the requested diff, ask one short clarifying question before editing or recommending action. Continue the local-fix loop until the gate is approved, comments are exhausted, or the user stops the flow.\n\nIf Plannotator is missing, unsuitable, or its interface is unclear, generate a standalone HTML file under `\u002Ftmp` using `mktemp`, then open or serve it with a lightweight local viewer such as `python3 -m http.server \u003Cport> --directory \u003Cdir>`. Return the HTML path, server URL, and any command needed to stop the server. Do not make Plannotator a hard dependency.\n\nMention in the final response whether Plannotator was used or whether the direct HTML fallback was used.\n\n## Workflow\n\n### 1. Read The Whole Change\n\nFirst identify the motif before narrating files:\n\n- What is the one-sentence purpose of the change?\n- Is it a feature, bugfix, refactor, revert, migration, dependency update, or mechanical change?\n- Which files are the conceptual foundation, core behavior, wiring, UI, tests, docs, or noise?\n- What has to be understood before the rest makes sense?\n\nDo not summarize each file independently until you understand the cross-file story.\n\n### 2. Classify Files\n\nClassify each file as `foundation`, `core`, `wiring`, `ui`, `test`, `docs`, or `noise`; classify its change as `new`, `mod`, `del`, or `ren`. Collapse `noise` by default. In `coverage=full`, include every file but still label noisy files clearly. For detailed rules, follow [`references\u002Ffile-roles.md`](references\u002Ffile-roles.md).\n\n### 3. Choose Reading Order\n\nUse this default order unless the motif calls for an override: foundation, core behavior, wiring and integration, UI, tests, docs, then noise.\n\nOverrides:\n\n- Bugfix: start with the failing behavior or fix, then proof\u002Ftests, then supporting context.\n- Revert: explain what is being backed out and why; avoid over-narrating restored code.\n- Mechanical change: group files by repeated pattern and show one representative example.\n- Migration: start with the old-to-new model, then compatibility or data handling, then call sites.\n\nFor mixed or mechanical diffs, follow [`references\u002Freading-order.md`](references\u002Freading-order.md).\n\n### 4. Explain With Diagrams\n\nPrefer diagrams or charts when they clarify relationships. Do not add decorative diagrams that repeat prose.\n\nUseful diagram types:\n\n- Reading-order map: foundation -> core -> wiring -> tests\n- Request\u002Fdata flow: input -> transformation -> storage\u002Foutput\n- Review feedback loop: walkthrough -> Plannotator comments -> fixes -> refreshed walkthrough\n- Code ownership or responsibility flow: caller -> adapter -> core logic -> output\n- Before\u002Fafter table for API or behavior changes\n- Risk matrix when `concerns=on`\n- File-role chart for large diffs\n\nPrefer flow diagrams when they reveal sequence, responsibility, or feedback loops that prose would force the reader to reconstruct. Avoid decorative diagrams that restate the same bullet list. For HTML, use simple inline SVG, CSS boxes, or tables so the output opens without a build step. For Markdown, use Mermaid when appropriate and include a plain table fallback if the diagram is essential. For terminal output, use ASCII arrows and compact tables.\n\n### 5. Write The Walkthrough\n\nFor each meaningful file or group:\n\n- State what changed concretely, naming symbols, functions, endpoints, commands, or types from the diff.\n- Explain how it relates to earlier and later files in the reading order.\n- Include representative hunks or short code snippets when they teach the change better than prose, especially for new contracts, changed control flow, boundary validation, API shape changes, or subtle removals. Keep snippets small and omit unrelated context.\n- Call out subtle behavior changes separately from obvious edits.\n- In `teaching` depth, define jargon before using it heavily.\n- In `deep` depth, cover edge cases, compatibility, tests, and operational impact.\n\nWhen `concerns=on`, add a clearly separate concerns section. Only include concerns grounded in the diff or inspected context. Do not invent risks.\n\nFor line-level annotations, use the categories and anti-hallucination rules in [`references\u002Fannotations.md`](references\u002Fannotations.md).\n\n### 6. Produce The Chosen Format\n\nHTML should include:\n\n- Title, source metadata, and generated timestamp\n- Executive summary\n- File-role chart or reading-order diagram when useful\n- Guided walkthrough in reading order\n- Representative diff hunks or code snippets\n- Tests and confidence section\n- Concerns section only when enabled\n\nMarkdown should mirror the same structure. Terminal output should be shorter and avoid large hunks. JSON should include at least `summary`, `source`, `options`, `files`, `readingOrder`, `diagrams`, `sections`, `tests`, and `concerns`.\n\nUse [`references\u002Foutput-formats.md`](references\u002Foutput-formats.md) as the output contract for larger walkthroughs or when another tool will consume the result.\n\n## Rules\n\n- Ground every claim in the diff, commit metadata, or inspected source context.\n- Prefer explanation over review unless the user asks for review or `concerns=on`.\n- Do not paste entire large diffs; choose representative hunks.\n- Do not fabricate line numbers, file paths, symbols, or intent.\n- Keep generated files local to the workspace or requested output path.\n- If verification is feasible, run the smallest relevant check for changed generated assets or scripts.\n- If the diff is too large to fully process, say what was covered and what was collapsed.\n",{"name":5,"description":7},"main","171fbdd3085ba76dacd148aa292d0559e8d913eb",1,"https:\u002F\u002Fgithub.com\u002Froerohan\u002Fskills","https:\u002F\u002Fgithub.com\u002Froerohan","https:\u002F\u002Froerohan.com","Engineer at @cloudflare | Founding Engineer at @dyte-in | CTFs | Ex-Tech Head at @csivitu (2020-21).","2026-09-04 18:05:21",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add roerohan\u002Fskills --skill diff-walkthrough",{"tool":38,"command":39},"bunx","bunx skills add roerohan\u002Fskills --skill diff-walkthrough",{"tool":41,"command":42},"pnpm","pnpm dlx skills add roerohan\u002Fskills --skill diff-walkthrough","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Froerohan\u002Fskills\u002Fblob\u002Fmain\u002Fdiff-walkthrough\u002FSKILL.md",true,[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fannotations.md","REFERENCE","参考文档",1915,"https:\u002F\u002Fgithub.com\u002Froerohan\u002Fskills\u002Fblob\u002Fmain\u002Fdiff-walkthrough\u002Freferences\u002Fannotations.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ffile-roles.md",3198,"https:\u002F\u002Fgithub.com\u002Froerohan\u002Fskills\u002Fblob\u002Fmain\u002Fdiff-walkthrough\u002Freferences\u002Ffile-roles.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Foutput-formats.md",3109,"https:\u002F\u002Fgithub.com\u002Froerohan\u002Fskills\u002Fblob\u002Fmain\u002Fdiff-walkthrough\u002Freferences\u002Foutput-formats.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Freading-order.md",3670,"https:\u002F\u002Fgithub.com\u002Froerohan\u002Fskills\u002Fblob\u002Fmain\u002Fdiff-walkthrough\u002Freferences\u002Freading-order.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},"01M72V6EQGTE5K3AP5B5AWJARB","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002Froerohan\u002Fskills\u002Fblob\u002Fmain\u002Fwhy\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},"01M72V6B7459ZDJMS003D65S02","using-git-worktrees","Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification","https:\u002F\u002Fgithub.com\u002Froerohan\u002Fskills\u002Fblob\u002Fmain\u002Fusing-git-worktrees\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},"01M72V69RJ26MA6Q5RZ07XTG9V","unslop","Cut AI tells from any writing. Must always apply.","https:\u002F\u002Fgithub.com\u002Froerohan\u002Fskills\u002Fblob\u002Fmain\u002Funslop\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},"01M72V66RS1KZVXMB9NGC4RDH1","tmux","Manage long-running commands in the user's current tmux session. Use when starting dev servers, watchers, background logs, or reading\u002Finteracting with named tmux panes.","https:\u002F\u002Fgithub.com\u002Froerohan\u002Fskills\u002Fblob\u002Fmain\u002Ftmux\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},"01M72V643VG4C97V3X764ZW12G","timesharing","Multiplexes one agent's attention across independent long-running external processes while preserving one reasoning context. Use for concurrent tests, builds, servers, watchers, REPLs, benchmarks, downloads, and other latency-bearing shell work; never use it to spawn or substitute subagents.","https:\u002F\u002Fgithub.com\u002Froerohan\u002Fskills\u002Fblob\u002Fmain\u002Ftimesharing\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},"01M72V62CFDFD6SJDA331JEWQ9","teach","Teach the user a new skill or concept, within this workspace.","https:\u002F\u002Fgithub.com\u002Froerohan\u002Fskills\u002Fblob\u002Fmain\u002Fteach\u002FSKILL.md",[],[]]