[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ASF16YBJ6WTHAECZTMZZHD":3,"skill-same:01M7ASF16YBJ6WTHAECZTMZZHD":45},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7ASF16YBJ6WTHAECZTMZZHD","cross-linker",null,"Scan the Obsidian wiki and automatically discover missing cross-references between pages. Use this skill when the user says \"link my pages\", \"find missing links\", \"cross-reference\", \"connect my wiki\", \"add wikilinks\", \"what pages should be linked\", or after any large ingestion to ensure new pages are woven into the existing knowledge graph. Also trigger when the user mentions \"orphan pages\" in the context of wanting to connect them, or says things like \"my wiki feels disconnected\" or \"pages aren't linked well\". This is a write-heavy skill — it actually modifies pages to add links, unlike wiki-lint which just reports issues.","saski\u002Farnesto","saski","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F140356?v=4","01M7ASBDSNXTRYDYB4K1PEA1RV","01M7ASBDTAKBDAAV99S1GE7HK6",6,"Unlicense","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcross-linker\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: cross-linker\ndescription: >\n  Scan the Obsidian wiki and automatically discover missing cross-references between pages.\n  Use this skill when the user says \"link my pages\", \"find missing links\", \"cross-reference\",\n  \"connect my wiki\", \"add wikilinks\", \"what pages should be linked\", or after any large ingestion\n  to ensure new pages are woven into the existing knowledge graph. Also trigger when the user\n  mentions \"orphan pages\" in the context of wanting to connect them, or says things like\n  \"my wiki feels disconnected\" or \"pages aren't linked well\". This is a write-heavy skill —\n  it actually modifies pages to add links, unlike wiki-lint which just reports issues.\n---\n\n# Cross-Linker — Automated Wiki Cross-Referencing\n\nYou are weaving the wiki's knowledge graph tighter by finding and inserting missing `[[wikilinks]]` between pages that should reference each other but currently don't.\n\n**Follow the Retrieval Primitives table in `llm-wiki\u002FSKILL.md`.** Build the registry in Step 1 by grepping frontmatter only (not full pages). Reserve full `Read` for the unlinked-mention detection pass, and even there, only read pages whose summaries\u002Ftitles make them plausible link targets. Blind full-vault reads are what this framework exists to avoid.\n\n## Before You Start\n\n1. Read `.env` to get `OBSIDIAN_VAULT_PATH`\n2. Read `index.md` to get the full inventory of pages and their one-line descriptions\n3. Skim `log.md` to see what was recently ingested (focus linking effort on new pages)\n\n## Step 1: Build the Page Registry\n\nGlob all `.md` files in the vault (excluding `_archives\u002F`, `.obsidian\u002F`). For each page, extract:\n\n- **Filename** (without `.md`) — this is the wikilink target\n- **Title** from frontmatter\n- **Aliases** from frontmatter (if any)\n- **Tags** from frontmatter\n- **Category** from frontmatter or directory inference\n- **One-line summary** — first sentence or `title` field\n\nBuild a lookup table:\n\n```\npage_name → { path, title, aliases, tags, summary }\n```\n\nThis is your \"vocabulary\" — every entry in this table is a valid wikilink target.\n\n## Step 2: Scan for Missing Links\n\nFor each page in the vault:\n\n1. **Read the full content**\n2. **Extract existing wikilinks** — find all `[[...]]` references already present\n3. **Search for unlinked mentions** — check if the page's text contains any of these, without being wrapped in `[[...]]`:\n   - Page filenames (e.g., the word \"MyProject\" appears but `[[projects\u002Fmy-project\u002Fmy-project]]` is missing)\n   - Page titles from frontmatter\n   - Aliases from frontmatter\n   - Entity names, project names, concept names from the registry\n\n4. **Check for semantic connections** — pages that share multiple tags or are in the same project directory but don't link to each other\n\n### Matching Rules\n\n- **Case-insensitive matching** for names (e.g., \"my-project\" matches page `MyProject`)\n- **Diacritic-insensitive matching** — normalize both the page name and the body text with Unicode NFKD (decompose accented characters to base + combining marks, strip combining marks) before comparing. This ensures body text \"Muller\" matches page `[[entities\u002Fmüller]]` and vice versa.\n- **Skip self-references** — a page shouldn't link to itself\n- **Skip common words** — don't link \"the\", \"and\", generic terms. Only match on distinctive names\n- **Prefer the shortest unambiguous wikilink path** — use `[[page-name]]` not `[[full\u002Fpath\u002Fto\u002Fpage-name]]` when the name is unique across the vault\n- **Don't link inside code blocks** or frontmatter\n- **Don't double-link** — if `[[foo]]` already appears on the page, don't add another\n\n## Step 3: Score and Rank Suggestions\n\nNot every possible link is worth adding. Score each candidate using a composite signal, then tag it with a confidence label.\n\n### Scoring\n\n| Signal | Points | Example |\n|---|---|---|\n| **Exact name match in text** | +4 | \"MyProject\" appears in body text → link to my-project.md |\n| **Shared tags (2+)** | +2 | Both tagged `#ai #agent` but no link between them |\n| **Same project, no link** | +2 | Both under `projects\u002Fmy-project\u002F` but don't reference each other |\n| **Mentioned entity\u002Fconcept** | +2 | Page mentions \"knowledge graphs\" → link to `[[concepts\u002Fknowledge-graphs]]` |\n| **Cross-category connection** | +2 | Source is in `concepts\u002F`, target is in `entities\u002F` (or `skills\u002F` ↔ `synthesis\u002F`) — different knowledge layers make this link more architecturally valuable |\n| **Peripheral→hub reach** | +2 | Source page has ≤ 2 total links (peripheral) but target has ≥ 8 (hub) — connecting a loose page to a load-bearing concept |\n| **Partial name match** | +1 | \"graph\" appears but page is `knowledge-graphs` — plausible but ambiguous |\n\n### Confidence labels\n\nTag each candidate with a confidence label based on its score:\n\n| Score | Label | Action |\n|---|---|---|\n| ≥ 6 | **EXTRACTED** | Link is effectively certain — exact mention or very strong match. Apply inline. |\n| 3–5 | **INFERRED** | Link is a reasonable inference — shared context, cross-category, peripheral→hub. Apply inline or as Related section. |\n| 1–2 | **AMBIGUOUS** | Weak or partial match. Skip unless user specifically asks to connect loose pages. |\n\nOnly act on **EXTRACTED** and **INFERRED** candidates. Include the confidence label in the Cross-Link Report so the user can review INFERRED links before trusting them.\n\n## Step 4: Apply Links\n\nFor each page with missing links:\n\n### 4a: Inline linking (preferred)\n\nFind the first natural mention of the term in the body text and wrap it in wikilinks:\n\n**Before:**\n```markdown\nThis project uses knowledge graphs to connect entities.\n```\n\n**After:**\n```markdown\nThis project uses [[concepts\u002Fknowledge-graphs|knowledge graphs]] to connect entities.\n```\n\nUse the `[[path|display text]]` format when the wikilink path differs from the display text.\n\n### 4b: Related section (fallback)\n\nIf the term isn't mentioned naturally in the body but the pages are semantically related (shared tags, same project), add a `## Related` section at the bottom of the page:\n\n```markdown\n## Related\n\n- [[projects\u002Fmy-project\u002Fmy-project]] — Also uses AI agents for research automation\n- [[concepts\u002Fknowledge-graphs]] — Core technique used in this project\n```\n\nIf a `## Related` section already exists, append to it. Don't duplicate existing entries.\n\n## Step 5: Score Misc Page Affinity\n\nAfter the main linking pass, update affinity scores for all pages in `misc\u002F` (pages with `promotion_status: misc` in their frontmatter, or located under the `misc\u002F` directory).\n\nFor each misc page:\n\n1. **Collect outgoing links** — all `[[wikilinks]]` in the page body\n2. **Collect incoming links** — grep the vault for `[[misc\u002F\u003Cslug>]]` and `[[\u003Cslug>]]` references\n3. For each linked page (both directions), check if it belongs to a project:\n   - Lives under `projects\u002F\u003Cproject-name>\u002F`\n   - Has a `project:` frontmatter field matching a project name\n4. Group by project name and sum: `outgoing_links + incoming_links`\n5. Update the `affinity` frontmatter block on the misc page:\n\n```yaml\naffinity:\n  obsidian-wiki: 3\n  another-project: 1\n```\n\n6. If any project's score ≥ 3: flag this page as a **promotion candidate** and record it for the report\n\n**Efficiency note:** only read the full body of misc pages — other pages only need a frontmatter grep to determine their project membership.\n\n## Step 6: Report\n\nPresent a summary:\n\n```markdown\n## Cross-Link Report\n\n### Links Added: 23 across 12 pages\n\n| Page | Links Added | Confidence | Type |\n|---|---|---|---|\n| `projects\u002Fmy-project\u002Fmy-project.md` | 3 | EXTRACTED | 2 inline, 1 related |\n| `entities\u002Fjane-doe.md` | 5 | INFERRED | 3 inline, 2 related |\n| ... | | | |\n\n### Orphan Pages Remaining: 2\n- `references\u002Ffoo.md` — no incoming or outgoing links found\n- `concepts\u002Fbar.md` — could not find related pages\n\n### Misc Promotion Candidates: N\nPages in misc\u002F that have ≥ 3 connections to a single project — ready to be promoted:\n\n| Page | Top Project | Score |\n|---|---|---|\n| `misc\u002Fweb-martinfowler-articles-microservices.md` | `obsidian-wiki` | 4 |\n\nTo promote: move the page to `projects\u002F\u003Cproject-name>\u002Freferences\u002F` and update all backlinks.\n\n### Pages Skipped: 3\n- `index.md`, `log.md` — special files\n- `_archives\u002F*` — archived content\n```\n\n## Step 7: Update Log and Hot Cache\n\nAppend to `log.md`:\n```\n- [TIMESTAMP] CROSS_LINK pages_scanned=N links_added=M pages_modified=P orphans_remaining=Q misc_affinity_updated=R promotion_candidates=S\n```\n\n**`hot.md`** — Read `$OBSIDIAN_VAULT_PATH\u002Fhot.md` (create from the template in `wiki-ingest` if missing). Update **Recent Activity** with a one-line summary of what was linked — e.g. \"Cross-linked 23 mentions across 12 pages; 2 orphans remain.\" Keep the last 3 operations. Update `updated` timestamp.\n\n## Tips\n\n- **Run after every ingest.** New pages are almost always poorly connected. This is the fix.\n- **Be conservative with inline links.** Only link the first natural mention, not every occurrence.\n- **Don't touch pages in `_archives\u002F`.** Those are frozen snapshots.\n- **Respect existing structure.** If a page carefully curates its links in a `## Key Concepts` section, add to that section rather than creating a separate `## Related`.\n- **Entity pages are link magnets.** An entity like `jane-doe` should be linked from almost every project page. Prioritize these.\n","# Cross-Linker — Automated Wiki Cross-Referencing\n\nYou are weaving the wiki's knowledge graph tighter by finding and inserting missing `[[wikilinks]]` between pages that should reference each other but currently don't.\n\n**Follow the Retrieval Primitives table in `llm-wiki\u002FSKILL.md`.** Build the registry in Step 1 by grepping frontmatter only (not full pages). Reserve full `Read` for the unlinked-mention detection pass, and even there, only read pages whose summaries\u002Ftitles make them plausible link targets. Blind full-vault reads are what this framework exists to avoid.\n\n## Before You Start\n\n1. Read `.env` to get `OBSIDIAN_VAULT_PATH`\n2. Read `index.md` to get the full inventory of pages and their one-line descriptions\n3. Skim `log.md` to see what was recently ingested (focus linking effort on new pages)\n\n## Step 1: Build the Page Registry\n\nGlob all `.md` files in the vault (excluding `_archives\u002F`, `.obsidian\u002F`). For each page, extract:\n\n- **Filename** (without `.md`) — this is the wikilink target\n- **Title** from frontmatter\n- **Aliases** from frontmatter (if any)\n- **Tags** from frontmatter\n- **Category** from frontmatter or directory inference\n- **One-line summary** — first sentence or `title` field\n\nBuild a lookup table:\n\n```\npage_name → { path, title, aliases, tags, summary }\n```\n\nThis is your \"vocabulary\" — every entry in this table is a valid wikilink target.\n\n## Step 2: Scan for Missing Links\n\nFor each page in the vault:\n\n1. **Read the full content**\n2. **Extract existing wikilinks** — find all `[[...]]` references already present\n3. **Search for unlinked mentions** — check if the page's text contains any of these, without being wrapped in `[[...]]`:\n   - Page filenames (e.g., the word \"MyProject\" appears but `[[projects\u002Fmy-project\u002Fmy-project]]` is missing)\n   - Page titles from frontmatter\n   - Aliases from frontmatter\n   - Entity names, project names, concept names from the registry\n\n4. **Check for semantic connections** — pages that share multiple tags or are in the same project directory but don't link to each other\n\n### Matching Rules\n\n- **Case-insensitive matching** for names (e.g., \"my-project\" matches page `MyProject`)\n- **Diacritic-insensitive matching** — normalize both the page name and the body text with Unicode NFKD (decompose accented characters to base + combining marks, strip combining marks) before comparing. This ensures body text \"Muller\" matches page `[[entities\u002Fmüller]]` and vice versa.\n- **Skip self-references** — a page shouldn't link to itself\n- **Skip common words** — don't link \"the\", \"and\", generic terms. Only match on distinctive names\n- **Prefer the shortest unambiguous wikilink path** — use `[[page-name]]` not `[[full\u002Fpath\u002Fto\u002Fpage-name]]` when the name is unique across the vault\n- **Don't link inside code blocks** or frontmatter\n- **Don't double-link** — if `[[foo]]` already appears on the page, don't add another\n\n## Step 3: Score and Rank Suggestions\n\nNot every possible link is worth adding. Score each candidate using a composite signal, then tag it with a confidence label.\n\n### Scoring\n\n| Signal | Points | Example |\n|---|---|---|\n| **Exact name match in text** | +4 | \"MyProject\" appears in body text → link to my-project.md |\n| **Shared tags (2+)** | +2 | Both tagged `#ai #agent` but no link between them |\n| **Same project, no link** | +2 | Both under `projects\u002Fmy-project\u002F` but don't reference each other |\n| **Mentioned entity\u002Fconcept** | +2 | Page mentions \"knowledge graphs\" → link to `[[concepts\u002Fknowledge-graphs]]` |\n| **Cross-category connection** | +2 | Source is in `concepts\u002F`, target is in `entities\u002F` (or `skills\u002F` ↔ `synthesis\u002F`) — different knowledge layers make this link more architecturally valuable |\n| **Peripheral→hub reach** | +2 | Source page has ≤ 2 total links (peripheral) but target has ≥ 8 (hub) — connecting a loose page to a load-bearing concept |\n| **Partial name match** | +1 | \"graph\" appears but page is `knowledge-graphs` — plausible but ambiguous |\n\n### Confidence labels\n\nTag each candidate with a confidence label based on its score:\n\n| Score | Label | Action |\n|---|---|---|\n| ≥ 6 | **EXTRACTED** | Link is effectively certain — exact mention or very strong match. Apply inline. |\n| 3–5 | **INFERRED** | Link is a reasonable inference — shared context, cross-category, peripheral→hub. Apply inline or as Related section. |\n| 1–2 | **AMBIGUOUS** | Weak or partial match. Skip unless user specifically asks to connect loose pages. |\n\nOnly act on **EXTRACTED** and **INFERRED** candidates. Include the confidence label in the Cross-Link Report so the user can review INFERRED links before trusting them.\n\n## Step 4: Apply Links\n\nFor each page with missing links:\n\n### 4a: Inline linking (preferred)\n\nFind the first natural mention of the term in the body text and wrap it in wikilinks:\n\n**Before:**\n```markdown\nThis project uses knowledge graphs to connect entities.\n```\n\n**After:**\n```markdown\nThis project uses [[concepts\u002Fknowledge-graphs|knowledge graphs]] to connect entities.\n```\n\nUse the `[[path|display text]]` format when the wikilink path differs from the display text.\n\n### 4b: Related section (fallback)\n\nIf the term isn't mentioned naturally in the body but the pages are semantically related (shared tags, same project), add a `## Related` section at the bottom of the page:\n\n```markdown\n## Related\n\n- [[projects\u002Fmy-project\u002Fmy-project]] — Also uses AI agents for research automation\n- [[concepts\u002Fknowledge-graphs]] — Core technique used in this project\n```\n\nIf a `## Related` section already exists, append to it. Don't duplicate existing entries.\n\n## Step 5: Score Misc Page Affinity\n\nAfter the main linking pass, update affinity scores for all pages in `misc\u002F` (pages with `promotion_status: misc` in their frontmatter, or located under the `misc\u002F` directory).\n\nFor each misc page:\n\n1. **Collect outgoing links** — all `[[wikilinks]]` in the page body\n2. **Collect incoming links** — grep the vault for `[[misc\u002F\u003Cslug>]]` and `[[\u003Cslug>]]` references\n3. For each linked page (both directions), check if it belongs to a project:\n   - Lives under `projects\u002F\u003Cproject-name>\u002F`\n   - Has a `project:` frontmatter field matching a project name\n4. Group by project name and sum: `outgoing_links + incoming_links`\n5. Update the `affinity` frontmatter block on the misc page:\n\n```yaml\naffinity:\n  obsidian-wiki: 3\n  another-project: 1\n```\n\n6. If any project's score ≥ 3: flag this page as a **promotion candidate** and record it for the report\n\n**Efficiency note:** only read the full body of misc pages — other pages only need a frontmatter grep to determine their project membership.\n\n## Step 6: Report\n\nPresent a summary:\n\n```markdown\n## Cross-Link Report\n\n### Links Added: 23 across 12 pages\n\n| Page | Links Added | Confidence | Type |\n|---|---|---|---|\n| `projects\u002Fmy-project\u002Fmy-project.md` | 3 | EXTRACTED | 2 inline, 1 related |\n| `entities\u002Fjane-doe.md` | 5 | INFERRED | 3 inline, 2 related |\n| ... | | | |\n\n### Orphan Pages Remaining: 2\n- `references\u002Ffoo.md` — no incoming or outgoing links found\n- `concepts\u002Fbar.md` — could not find related pages\n\n### Misc Promotion Candidates: N\nPages in misc\u002F that have ≥ 3 connections to a single project — ready to be promoted:\n\n| Page | Top Project | Score |\n|---|---|---|\n| `misc\u002Fweb-martinfowler-articles-microservices.md` | `obsidian-wiki` | 4 |\n\nTo promote: move the page to `projects\u002F\u003Cproject-name>\u002Freferences\u002F` and update all backlinks.\n\n### Pages Skipped: 3\n- `index.md`, `log.md` — special files\n- `_archives\u002F*` — archived content\n```\n\n## Step 7: Update Log and Hot Cache\n\nAppend to `log.md`:\n```\n- [TIMESTAMP] CROSS_LINK pages_scanned=N links_added=M pages_modified=P orphans_remaining=Q misc_affinity_updated=R promotion_candidates=S\n```\n\n**`hot.md`** — Read `$OBSIDIAN_VAULT_PATH\u002Fhot.md` (create from the template in `wiki-ingest` if missing). Update **Recent Activity** with a one-line summary of what was linked — e.g. \"Cross-linked 23 mentions across 12 pages; 2 orphans remain.\" Keep the last 3 operations. Update `updated` timestamp.\n\n## Tips\n\n- **Run after every ingest.** New pages are almost always poorly connected. This is the fix.\n- **Be conservative with inline links.** Only link the first natural mention, not every occurrence.\n- **Don't touch pages in `_archives\u002F`.** Those are frozen snapshots.\n- **Respect existing structure.** If a page carefully curates its links in a `## Key Concepts` section, add to that section rather than creating a separate `## Related`.\n- **Entity pages are link magnets.** An entity like `jane-doe` should be linked from almost every project page. Prioritize these.\n",{"name":5,"description":7},"main","3c24fc2c035029b08c7326774bee3fef8fb95566",".agents\u002Fskills\u002Fcross-linker",0,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto","https:\u002F\u002Fgithub.com\u002Fsaski","http:\u002F\u002Fsaski.com","2026-11-12 20:09:16",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add saski\u002Farnesto --skill cross-linker",{"tool":37,"command":38},"bunx","bunx skills add saski\u002Farnesto --skill cross-linker",{"tool":40,"command":41},"pnpm","pnpm dlx skills add saski\u002Farnesto --skill cross-linker","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcross-linker\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":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"01M7AT7F5FSHNAMFMF01N0QA1X","visualize","Use \u002Fvisualize for creating compact charts, diagrams, or other visuals inline as part of the conversation itself. It chooses among Markdown tables, Mermaid, inline HTML, and other supported in-transcript forms. Use Canvas for durable artifacts outside the transcript that users may revisit, refine, or share.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fvisualize\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"01M7AT79MHSAR3JDDMP7DGERM9","update-cursor-settings","Modify Cursor\u002FVSCode user settings in settings.json. Use when you want to change editor settings, preferences, configuration, themes, font size, tab size, format on save, auto save, keybindings, or any settings.json values.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fupdate-cursor-settings\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M7AT73WF3Y22E0FKYAMCCJES","update-cli-config","View and modify Cursor CLI configuration settings in ~\u002F.cursor\u002Fcli-config.json. Use when the user wants to change CLI settings, configure permissions, switch approval mode, enable vim mode, toggle display options, configure sandbox, or manage any CLI preferences.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fupdate-cli-config\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M7AT6F3FBP85AJJ5BJNR8B5W","statusline","Configure a custom status line in the CLI. Use when the user mentions status line, statusline, statusLine, CLI status bar, prompt footer customization, or wants to add session context above the prompt.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fstatusline\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M7AT6D24QFS5XRAFN8S5XJ7W","split-to-prs","Split current work into small reviewable PRs. Use when the user asks to split a chat, set of changes, branch, or PR.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fsplit-to-prs\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M7AT69FYFN84XZKW452JV5DF","shell","Runs the rest of a \u002Fshell request as a literal shell command. Use only when the user explicitly invokes \u002Fshell and wants the following text executed directly in the terminal.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fshell\u002FSKILL.md",[],[]]