[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BKEGDNRRMEEV1GSTEE14X7":3,"skill-same:01M7BKEGDNRRMEEV1GSTEE14X7":53},{"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":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":6,"ownerDescription":38,"updatedAt":39,"install":40,"resources":52},"01M7BKEGDNRRMEEV1GSTEE14X7","blog-flow",null,"FLOW framework integration for bloggers. Evidence-led content workflow using the Find, Optimize, Win loop with stage-specific AI prompts from the FLOW knowledge base (30 blog-applicable prompts, CC BY 4.0). Use when user says \"FLOW\", \"FLOW framework\", \"blog flow\", \"evidence-led blogging\", \"find optimize win\", or wants stage-specific blog prompts.","om-scogo\u002Fskillsh-scraper","om-scogo","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160466840?v=4","01M79AWB6DFVCQ7RK70CS34B96","Om Achrekar","01M79AWB6ZM9SKR8KDH1WSSM22",0,"MIT","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fagricidaniel-claude-blog\u002Fblog-flow\u002Fskills\u002Fblog-flow\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: blog-flow\ndescription: >\n  FLOW framework integration for bloggers. Evidence-led content workflow using\n  the Find, Optimize, Win loop with stage-specific AI prompts from the FLOW\n  knowledge base (30 blog-applicable prompts, CC BY 4.0). Use when user says\n  \"FLOW\", \"FLOW framework\", \"blog flow\", \"evidence-led blogging\", \"find optimize\n  win\", or wants stage-specific blog prompts.\nuser-invokable: true\nargument-hint: \"[stage] [url|topic]\"\nlicense: MIT\ncompatibility: Requires Claude Code and Python 3.11+ for the sync script\nmetadata:\n  author: AgriciDaniel\n  version: \"1.9.1\"\n  category: blog\n---\n\n# FLOW Framework for Bloggers (Find, Optimize, Win)\n\n> Framework and prompts (c) Daniel Agrici, CC BY 4.0. Source: github.com\u002FAgriciDaniel\u002Fflow\n\nFLOW is an evidence-led operating model built for the AI-search era. Claude Blog\nintegrates the FLOW prompt library so writers can drive their workflow with\nstructured, source-backed AI prompts instead of improvised queries.\n\nThis skill exposes the three blog-relevant stages (Find, Optimize, Win) and keeps\nthe single Leverage prompt available through the prompts index. The local-SEO\nprompts (GBP, citations, local audits) are intentionally excluded because they\ntarget brick-and-mortar work, not blogs.\n\n**Runtime context.** Load `references\u002Fflow-framework.md` on every `\u002Fblog flow`\nactivation. Load prompt files on demand only, scoped to the stage the user\nrequests.\n\n---\n\n## Commands\n\n| Command | What it does |\n|---------|-------------|\n| `\u002Fblog flow` | Show FLOW overview and stage menu |\n| `\u002Fblog flow find [topic\\|url]` | Find-stage: keyword discovery, intent mapping, gap analysis (5 prompts) |\n| `\u002Fblog flow optimize [url]` | Optimize-stage: select 2 to 3 most relevant prompts of 21 based on context |\n| `\u002Fblog flow win [url]` | Win-stage: BOFU, conversion, dual-surface scorecard (3 prompts) |\n| `\u002Fblog flow prompts` | Full index of all 30 blog-applicable prompts (Find, Leverage, Optimize, Win) |\n| `\u002Fblog flow sync` | Pull latest prompt files from github.com\u002FAgriciDaniel\u002Fflow |\n\nThe single Leverage prompt (off-site authority) is reachable through\n`\u002Fblog flow prompts` and is not promoted to a top-level command, since most\nblog workflows route off-site work elsewhere.\n\n---\n\n## Orchestration Logic\n\n### On `\u002Fblog flow` (no sub-command)\n1. Read `references\u002Fflow-framework.md`.\n2. Show the FLOW stage overview with a one-line description of each stage.\n3. Ask the user which stage matches their current situation.\n\n### On `\u002Fblog flow find [topic|url]`\n1. Read all files in `references\u002Fprompts\u002Ffind\u002F`.\n2. Apply each prompt to the topic or URL, capturing demand and intent signals.\n3. Cross-reference: \"For deeper briefs and outlines, see `\u002Fblog brief \u003Ctopic>`,\n   `\u002Fblog outline \u003Ctopic>`, and `\u002Fblog cannibalization` to detect overlap with\n   existing posts.\"\n\n### On `\u002Fblog flow optimize [url]`\n1. Read the file names in `references\u002Fprompts\u002Foptimize\u002F`.\n2. Read prior context (target URL, niche, any prior skill output in this\n   conversation, scoring deltas from `\u002Fblog analyze`).\n3. Select 2 to 3 most relevant prompts, then load only those files.\n4. Apply the selected prompts; note that the rest are accessible via\n   `\u002Fblog flow prompts`.\n5. Cross-reference: \"For deeper rewrites and validation, see `\u002Fblog rewrite\n   \u003Cfile>`, `\u002Fblog seo-check \u003Cfile>`, `\u002Fblog geo \u003Cfile>`, `\u002Fblog schema \u003Cfile>`,\n   and `\u002Fblog factcheck \u003Cfile>`.\"\n\n### On `\u002Fblog flow win [url]`\n1. Read all files in `references\u002Fprompts\u002Fwin\u002F`.\n2. Apply each prompt to the URL's conversion and BOFU context.\n3. Cross-reference: \"For repurposing, full-site health, and quality scoring,\n   see `\u002Fblog repurpose \u003Cfile>`, `\u002Fblog audit`, and `\u002Fblog analyze \u003Cfile>`.\"\n\n### On `\u002Fblog flow prompts`\n1. Read `references\u002Fprompts\u002FREADME.md`.\n2. Display the full index: 30 prompts grouped by stage (Find, Leverage,\n   Optimize, Win) with name and trigger conditions.\n3. State that local-SEO prompts are excluded by design; point users to\n   `claude-seo` (`\u002Fseo flow local`) if they need them.\n\n### On `\u002Fblog flow sync`\n1. Run: `python3 scripts\u002Fsync_flow.py`.\n2. Display the JSON summary (files added, updated, unchanged).\n3. Show the attribution notice after the sync completes.\n\n---\n\n## Context Matching (Optimize stage)\n\nThe optimize stage has 21 prompts. Dumping all 21 is noise. Select by priority:\n\n1. **Niche** (SaaS or B2B blog leans on-page plus technical; lifestyle leans\n   freshness plus E-E-A-T; publisher leans authority plus citations).\n2. **Prior skill output** (`\u002Fblog analyze` E-E-A-T gap routes to authority\n   prompts; `\u002Fblog seo-check` failures route to on-page prompts; `\u002Fblog geo`\n   gaps route to extraction-format prompts).\n3. **URL signals** (commercial pages need conversion prompts; informational\n   posts need freshness plus answer-first prompts).\n\nAlways surface exactly 2 to 3 prompts. State which prompts you chose and why.\n\n---\n\n## Reference Files\n\nLoad on demand. Do NOT load all at startup.\n\n- `references\u002Fflow-framework.md`. FLOW operating model. Load on every `\u002Fblog\n  flow` activation.\n- `references\u002Fbibliography.md`. Evidence sources. Load when citing studies or\n  statistics.\n- `references\u002Fprompts\u002FREADME.md`. Prompt index. Load for `\u002Fblog flow prompts`.\n- `references\u002Fprompts\u002Ffind\u002F`. 5 prompts. Load for `\u002Fblog flow find`.\n- `references\u002Fprompts\u002Fleverage\u002F`. 1 prompt. Load only when surfaced through\n  `\u002Fblog flow prompts`.\n- `references\u002Fprompts\u002Foptimize\u002F`. 21 prompts. Load selectively for `\u002Fblog flow\n  optimize`.\n- `references\u002Fprompts\u002Fwin\u002F`. 3 prompts. Load for `\u002Fblog flow win`.\n\nIf `references\u002F` is missing, instruct the user to run `\u002Fblog flow sync` first.\n\n---\n\n## Sync Script\n\n`scripts\u002Fsync_flow.py` pulls prompt files from github.com\u002FAgriciDaniel\u002Fflow and\nwrites them under `skills\u002Fblog-flow\u002Freferences\u002F`. Stdlib only, HTTPS only,\nhost-allowlisted to `api.github.com`, 5 MB response cap, atomic writes,\npath-traversal guarded.\n\nModes:\n\n- `python3 scripts\u002Fsync_flow.py`. Sync the latest version of every blog-relevant\n  stage to disk and refresh the lockfile.\n- `python3 scripts\u002Fsync_flow.py --dry-run`. Report planned changes without\n  writing.\n- `python3 scripts\u002Fsync_flow.py --ref \u003Csha>`. Pin fetches to a specific FLOW\n  commit SHA for reproducible installs.\n\nThe lockfile lives at\n`skills\u002Fblog-flow\u002Freferences\u002Fflow-prompts.lock` and uses sha256sum-compatible\nformat. Drift between the on-disk content and the lockfile is reported on every\nsync run.\n\nThe script syncs only blog-applicable stages (`find`, `leverage`, `optimize`,\n`win`). The `local` stage is intentionally skipped to keep the references\ndirectory aligned with the skill's surface area.\n\nGitHub API calls are anonymous by default. If `GITHUB_TOKEN` is set in the\nenvironment, or `gh auth token` returns a token after a 403 response, the\nscript retries the request with that token. No tokens are written to disk.\n\n---\n\n## Attribution\n\nEvery `\u002Fblog flow` activation (any sub-command) outputs before analysis:\n\n```\nFramework and prompts (c) Daniel Agrici, CC BY 4.0. Source: github.com\u002FAgriciDaniel\u002Fflow\n```\n\nDo not omit or modify the attribution. Synced files also carry an HTML comment\nlicense header injected by the sync script.\n\n---\n\n## Error Handling\n\n| Scenario | Action |\n|----------|--------|\n| `references\u002Fflow-framework.md` missing | \"FLOW reference files not synced. Run: `\u002Fblog flow sync`.\" |\n| Prompt file missing | \"Run `\u002Fblog flow sync` to pull the latest prompts from the FLOW repo.\" |\n| `sync_flow.py` network error | Display the script's stderr. Check rate limits with `gh api rate_limit` if `gh` is installed. |\n| `sync_flow.py` 403 after retry | Set `GITHUB_TOKEN` or run `gh auth login`, then retry. |\n| Path-traversal abort | The sync target tried to escape the references directory. Inspect the upstream repo and pin to a known-good `--ref`. |\n","# FLOW Framework for Bloggers (Find, Optimize, Win)\n\n> Framework and prompts (c) Daniel Agrici, CC BY 4.0. Source: github.com\u002FAgriciDaniel\u002Fflow\n\nFLOW is an evidence-led operating model built for the AI-search era. Claude Blog\nintegrates the FLOW prompt library so writers can drive their workflow with\nstructured, source-backed AI prompts instead of improvised queries.\n\nThis skill exposes the three blog-relevant stages (Find, Optimize, Win) and keeps\nthe single Leverage prompt available through the prompts index. The local-SEO\nprompts (GBP, citations, local audits) are intentionally excluded because they\ntarget brick-and-mortar work, not blogs.\n\n**Runtime context.** Load `references\u002Fflow-framework.md` on every `\u002Fblog flow`\nactivation. Load prompt files on demand only, scoped to the stage the user\nrequests.\n\n---\n\n## Commands\n\n| Command | What it does |\n|---------|-------------|\n| `\u002Fblog flow` | Show FLOW overview and stage menu |\n| `\u002Fblog flow find [topic\\|url]` | Find-stage: keyword discovery, intent mapping, gap analysis (5 prompts) |\n| `\u002Fblog flow optimize [url]` | Optimize-stage: select 2 to 3 most relevant prompts of 21 based on context |\n| `\u002Fblog flow win [url]` | Win-stage: BOFU, conversion, dual-surface scorecard (3 prompts) |\n| `\u002Fblog flow prompts` | Full index of all 30 blog-applicable prompts (Find, Leverage, Optimize, Win) |\n| `\u002Fblog flow sync` | Pull latest prompt files from github.com\u002FAgriciDaniel\u002Fflow |\n\nThe single Leverage prompt (off-site authority) is reachable through\n`\u002Fblog flow prompts` and is not promoted to a top-level command, since most\nblog workflows route off-site work elsewhere.\n\n---\n\n## Orchestration Logic\n\n### On `\u002Fblog flow` (no sub-command)\n1. Read `references\u002Fflow-framework.md`.\n2. Show the FLOW stage overview with a one-line description of each stage.\n3. Ask the user which stage matches their current situation.\n\n### On `\u002Fblog flow find [topic|url]`\n1. Read all files in `references\u002Fprompts\u002Ffind\u002F`.\n2. Apply each prompt to the topic or URL, capturing demand and intent signals.\n3. Cross-reference: \"For deeper briefs and outlines, see `\u002Fblog brief \u003Ctopic>`,\n   `\u002Fblog outline \u003Ctopic>`, and `\u002Fblog cannibalization` to detect overlap with\n   existing posts.\"\n\n### On `\u002Fblog flow optimize [url]`\n1. Read the file names in `references\u002Fprompts\u002Foptimize\u002F`.\n2. Read prior context (target URL, niche, any prior skill output in this\n   conversation, scoring deltas from `\u002Fblog analyze`).\n3. Select 2 to 3 most relevant prompts, then load only those files.\n4. Apply the selected prompts; note that the rest are accessible via\n   `\u002Fblog flow prompts`.\n5. Cross-reference: \"For deeper rewrites and validation, see `\u002Fblog rewrite\n   \u003Cfile>`, `\u002Fblog seo-check \u003Cfile>`, `\u002Fblog geo \u003Cfile>`, `\u002Fblog schema \u003Cfile>`,\n   and `\u002Fblog factcheck \u003Cfile>`.\"\n\n### On `\u002Fblog flow win [url]`\n1. Read all files in `references\u002Fprompts\u002Fwin\u002F`.\n2. Apply each prompt to the URL's conversion and BOFU context.\n3. Cross-reference: \"For repurposing, full-site health, and quality scoring,\n   see `\u002Fblog repurpose \u003Cfile>`, `\u002Fblog audit`, and `\u002Fblog analyze \u003Cfile>`.\"\n\n### On `\u002Fblog flow prompts`\n1. Read `references\u002Fprompts\u002FREADME.md`.\n2. Display the full index: 30 prompts grouped by stage (Find, Leverage,\n   Optimize, Win) with name and trigger conditions.\n3. State that local-SEO prompts are excluded by design; point users to\n   `claude-seo` (`\u002Fseo flow local`) if they need them.\n\n### On `\u002Fblog flow sync`\n1. Run: `python3 scripts\u002Fsync_flow.py`.\n2. Display the JSON summary (files added, updated, unchanged).\n3. Show the attribution notice after the sync completes.\n\n---\n\n## Context Matching (Optimize stage)\n\nThe optimize stage has 21 prompts. Dumping all 21 is noise. Select by priority:\n\n1. **Niche** (SaaS or B2B blog leans on-page plus technical; lifestyle leans\n   freshness plus E-E-A-T; publisher leans authority plus citations).\n2. **Prior skill output** (`\u002Fblog analyze` E-E-A-T gap routes to authority\n   prompts; `\u002Fblog seo-check` failures route to on-page prompts; `\u002Fblog geo`\n   gaps route to extraction-format prompts).\n3. **URL signals** (commercial pages need conversion prompts; informational\n   posts need freshness plus answer-first prompts).\n\nAlways surface exactly 2 to 3 prompts. State which prompts you chose and why.\n\n---\n\n## Reference Files\n\nLoad on demand. Do NOT load all at startup.\n\n- `references\u002Fflow-framework.md`. FLOW operating model. Load on every `\u002Fblog\n  flow` activation.\n- `references\u002Fbibliography.md`. Evidence sources. Load when citing studies or\n  statistics.\n- `references\u002Fprompts\u002FREADME.md`. Prompt index. Load for `\u002Fblog flow prompts`.\n- `references\u002Fprompts\u002Ffind\u002F`. 5 prompts. Load for `\u002Fblog flow find`.\n- `references\u002Fprompts\u002Fleverage\u002F`. 1 prompt. Load only when surfaced through\n  `\u002Fblog flow prompts`.\n- `references\u002Fprompts\u002Foptimize\u002F`. 21 prompts. Load selectively for `\u002Fblog flow\n  optimize`.\n- `references\u002Fprompts\u002Fwin\u002F`. 3 prompts. Load for `\u002Fblog flow win`.\n\nIf `references\u002F` is missing, instruct the user to run `\u002Fblog flow sync` first.\n\n---\n\n## Sync Script\n\n`scripts\u002Fsync_flow.py` pulls prompt files from github.com\u002FAgriciDaniel\u002Fflow and\nwrites them under `skills\u002Fblog-flow\u002Freferences\u002F`. Stdlib only, HTTPS only,\nhost-allowlisted to `api.github.com`, 5 MB response cap, atomic writes,\npath-traversal guarded.\n\nModes:\n\n- `python3 scripts\u002Fsync_flow.py`. Sync the latest version of every blog-relevant\n  stage to disk and refresh the lockfile.\n- `python3 scripts\u002Fsync_flow.py --dry-run`. Report planned changes without\n  writing.\n- `python3 scripts\u002Fsync_flow.py --ref \u003Csha>`. Pin fetches to a specific FLOW\n  commit SHA for reproducible installs.\n\nThe lockfile lives at\n`skills\u002Fblog-flow\u002Freferences\u002Fflow-prompts.lock` and uses sha256sum-compatible\nformat. Drift between the on-disk content and the lockfile is reported on every\nsync run.\n\nThe script syncs only blog-applicable stages (`find`, `leverage`, `optimize`,\n`win`). The `local` stage is intentionally skipped to keep the references\ndirectory aligned with the skill's surface area.\n\nGitHub API calls are anonymous by default. If `GITHUB_TOKEN` is set in the\nenvironment, or `gh auth token` returns a token after a 403 response, the\nscript retries the request with that token. No tokens are written to disk.\n\n---\n\n## Attribution\n\nEvery `\u002Fblog flow` activation (any sub-command) outputs before analysis:\n\n```\nFramework and prompts (c) Daniel Agrici, CC BY 4.0. Source: github.com\u002FAgriciDaniel\u002Fflow\n```\n\nDo not omit or modify the attribution. Synced files also carry an HTML comment\nlicense header injected by the sync script.\n\n---\n\n## Error Handling\n\n| Scenario | Action |\n|----------|--------|\n| `references\u002Fflow-framework.md` missing | \"FLOW reference files not synced. Run: `\u002Fblog flow sync`.\" |\n| Prompt file missing | \"Run `\u002Fblog flow sync` to pull the latest prompts from the FLOW repo.\" |\n| `sync_flow.py` network error | Display the script's stderr. Check rate limits with `gh api rate_limit` if `gh` is installed. |\n| `sync_flow.py` 403 after retry | Set `GITHUB_TOKEN` or run `gh auth login`, then retry. |\n| Path-traversal abort | The sync target tried to escape the references directory. Inspect the upstream repo and pin to a known-good `--ref`. |\n",{"name":5,"license":15,"metadata":24,"description":28,"argument-hint":29,"compatibility":30,"user-invokable":31},{"author":25,"version":26,"category":27},"AgriciDaniel","1.9.1","blog","FLOW framework integration for bloggers. Evidence-led content workflow using the Find, Optimize, Win loop with stage-specific AI prompts from the FLOW knowledge base (30 blog-applicable prompts, CC BY 4.0). Use when user says \"FLOW\", \"FLOW framework\", \"blog flow\", \"evidence-led blogging\", \"find optimize win\", or wants stage-specific blog prompts.\n","[stage] [url|topic]","Requires Claude Code and Python 3.11+ for the sync script",true,"main","8859218955d9504cd18b59e7892100718039d3b4","data\u002Fskills\u002Fagricidaniel-claude-blog\u002Fblog-flow\u002Fskills\u002Fblog-flow",1,"https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper","https:\u002F\u002Fgithub.com\u002Fom-scogo","SDE-1 @ Scogo ","2026-07-18 12:22:46",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":31},[42,45,48],{"tool":43,"command":44},"npx","npx skills add om-scogo\u002Fskillsh-scraper --skill blog-flow",{"tool":46,"command":47},"bunx","bunx skills add om-scogo\u002Fskillsh-scraper --skill blog-flow",{"tool":49,"command":50},"pnpm","pnpm dlx skills add om-scogo\u002Fskillsh-scraper --skill blog-flow","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fagricidaniel-claude-blog\u002Fblog-flow\u002Fskills\u002Fblog-flow\u002FSKILL.md",[],[54,61,66,73,78,85],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7D6MC9FAAEV4CMNYX8W7JTG","arxiv-search","Search arXiv physics, math, and computer science preprints using natural language queries. Powered by Valyu semantic search.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fyorkeccak-scientific-skills\u002Farxiv-search\u002Fskills\u002Farxiv-search\u002FSKILL.md",[],[],{"skillNo":62,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7D6M85CKKN87TA98VCQV4H7","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fyorkeccak-scientific-skills\u002Farxiv-search\u002FSkill.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7D4ZTCS4DR3CE4JY06X84T2","working-with-legacy-code","Safely change and test untested codebases using Feathers' \"Working Effectively with Legacy Code\". Use when the user mentions \"legacy code\", \"no tests\", \"untested codebase\", \"how do I test this\", \"seams\", \"characterization tests\", \"golden master\", \"sprout method\", \"afraid to change this code\", \"monster method\", \"dependency breaking\", or \"inherited a messy codebase\". Also trigger when changing code without tests safely, getting a class under test when constructors, statics, or singletons block it, adding features to tangled modules, or planning incremental test coverage for an old codebase. Covers the legacy-code change algorithm, seams, characterization tests, sprout\u002Fwrap, and dependency-breaking techniques. For refactoring code that already has tests, see refactoring-patterns. For day-to-day code quality, see clean-code.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fworking-with-legacy-code\u002Fworking-with-legacy-code\u002FSKILL.md",[],[],{"skillNo":74,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7D4ZHZKJD2RSNGAF63V14P4","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fworking-with-legacy-code\u002FSkill.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7D4ZB4CJBFW5JE67CPH2QRV","web-typography","Select, pair, and implement typefaces for web projects. Use when the user mentions \"font pairing\", \"which typeface\", \"line height\", \"responsive typography\", \"web font loading\", \"type hierarchy\", \"variable fonts\", \"FOUT\u002FFOIT\", \"typographic scale\", or \"the text is hard to read\". Also trigger when choosing between system fonts and web fonts, optimizing font-loading performance, or designing readable long-form content. Covers readability evaluation, CSS implementation, and performance optimization. For overall UI design systems, see refactoring-ui. For dramatic typographic experiences, see top-design.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fweb-typography\u002Fweb-typography\u002FSKILL.md",[],[],{"skillNo":86,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7D4Z4MVYVY3NMJ18BNV6WNA","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fweb-typography\u002FSkill.md",[],[]]