[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CXESJNV0KVCX4TNK1V2ZB0":3,"skill-same:01M7CXESJNV0KVCX4TNK1V2ZB0":60},{"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":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":6,"ownerDescription":39,"updatedAt":40,"install":41,"resources":53},"01M7CXESJNV0KVCX4TNK1V2ZB0","training-report",null,"Produce a professional training\u002Fworkshop report as a .docx file. Use this skill whenever the user mentions \"training report\", \"workshop report\", \"compte rendu\", \"compte rendu de formation\", \"formation report\", \"debriefing a workshop\", \"write up a training session\", \"résumé de formation\", or any request to document a training session, workshop, or onboarding event with individual participant feedback and recommendations. Also trigger when the user says things like \"I just ran a workshop and need to write it up\", \"help me summarize what happened in my training session\", or \"I need to report back to management about a session I ran\". Always use this skill — for short or long sessions, across any discipline (technical, soft skills, creative, compliance, onboarding, etc.) — whenever a structured written deliverable about a training event is needed.","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\u002Fsamber-cc-skills\u002Ftraining-report\u002FSkill.md",[],[],"2026-11-15 14:19:17",false,"---\nname: training-report\ndescription: 'Produce a professional training\u002Fworkshop report as a .docx file. Use this skill whenever the user mentions \"training report\", \"workshop report\", \"compte rendu\", \"compte rendu de formation\", \"formation report\", \"debriefing a workshop\", \"write up a training session\", \"résumé de formation\", or any request to document a training session, workshop, or onboarding event with individual participant feedback and recommendations. Also trigger when the user says things like \"I just ran a workshop and need to write it up\", \"help me summarize what happened in my training session\", or \"I need to report back to management about a session I ran\". Always use this skill — for short or long sessions, across any discipline (technical, soft skills, creative, compliance, onboarding, etc.) — whenever a structured written deliverable about a training event is needed.'\nuser-invocable: true\nlicense: MIT\ncompatibility: Designed for Claude or similar AI agents.\nmetadata:\n  author: samber\n  version: \"1.0.1\"\n  openclaw:\n    emoji: \"📚\"\n    homepage: https:\u002F\u002Fgithub.com\u002Fsamber\u002Fcc-skills\nallowed-tools: Read Edit Write Glob Grep Agent AskUserQuestion\n---\n\n# Training Report\n\nIterate the full report in **Markdown first**. Generate the **.docx last**, once, when the content is final. The .md is the canonical artifact; the .docx is a terminal derivative.\n\nDiscipline-agnostic: coding workshop, leadership seminar, safety training, onboarding, creative workshop — all apply equally.\n\n> **Voice mode:** this conversation may be conducted by voice. Transcription can introduce homophones, missing punctuation, or ambiguous proper nouns (names, company names, tool names). If any answer is unclear after transcription, ask a short clarifying question before moving on — do not guess.\n\n## Reference files\n\nLoad these files at the steps indicated. Do not load them all upfront.\n\n| File | Load at |\n| --- | --- |\n| `references\u002Ftone-of-voice.md` | Step 1 (after language + audience confirmed) |\n| `references\u002Fmarkdown-draft.md` | Step 5 (before writing the draft) |\n| `references\u002Fdocx-generation.md` | Step 6 (before generating the .docx) |\n\n## Step 0 — Check dependencies\n\n**Before asking the user anything**, verify skill availability.\n\n**`docx` skill (required for Step 6)**\n\n- If found: note it; load it at Step 6\n- If not found: warn the user — it is required to generate the final Word document and can be installed from Anthropic's official skill library. Offer to proceed with the Markdown draft in the meantime.\n\n**Humanizer skill (recommended)**\n\n- After Step 1, look for a humanizer skill matching the chosen language\n- If found: load it and apply it during the humanization pass in Step 5\n- If not found: tell the user once, then fall back to inline humanization rules (Step 5b). Suggest installing a humanizer skill for the chosen language.\n\n## Step 1 — Language & audience\n\nAsk:\n\n1. \"In what language should I write the report? (French \u002F English \u002F other)\"\n2. \"Who is the primary reader? (executive \u002F HR \u002F direct management \u002F external client \u002F internal archive)\"\n\nThen load `references\u002Ftone-of-voice.md` and apply its guidance throughout.\n\n## Step 2 — Template\n\nAsk:\n\n> \"Do you have a Word (.docx) template for this report? (company header\u002Ffooter, logo, branded fonts, color scheme)\"\n\n- **Yes** → ask them to upload it; use it as the base at Step 6 (unpack\u002Finject\u002Frepack)\n- **No** → proceed with a clean document; ask for a brand color before defaulting to blue `#2E75B6`\n\n## Step 3 — Interview\n\nConduct a structured interview in batches. Wait for answers before moving on. Extract what the user already told you from the conversation before asking.\n\n### Batch A — Session metadata\n\n- Trainer name and role\n- Date, location, company\u002Fteam name\n- Duration\n- Total number of participants\n- Confirm or refine: who is the document for?\n\n### Batch B — Session context\n\n- Stated goal of the training\n- Subject, topic, tool, or material used as practical support\n- Any rules or constraints set at the start\n- Materials, accounts, licenses, or equipment provided to participants\n\n### Batch C — Starting levels\n\n- Distribution of familiarity across the group (any beginners? any experts?)\n- Notable outliers at either end\n\n### Batch D — Session walkthrough\n\nWalk through the session step by step. For each step:\n\n- Objective\n- What participants actually did\n- Materials, tools, or exercises involved\n- First exposure to this concept or not\n- How it landed; any difficulties\n\nProbe until complete: \"What happened next?\", \"Did anything go differently than planned?\", \"Were there any pivots?\"\n\n### Batch E — Deliverables\n\nAsk: \"Did participants produce anything during the session?\"\n\nProbe for:\n\n- Documents, files, diagrams, prototypes, or any output created during exercises\n- Collaborative work produced as a group\n- Individual work produced autonomously\n- Anything left incomplete or started but not finished\n\nThese may appear in the Annexes and\u002For be referenced in the Session Walkthrough.\n\n### Batch F — General observations\n\n- Overall energy and engagement of the group\n- Any incidents, surprises, or notable moments\n- Schedule: did it hold, or were sections cut\u002Fextended?\n- Logistical issues (room, materials, setup)\n\nGeneral Observations is **optional**. If the trainer has nothing notable to add beyond the walkthrough, skip this section entirely.\n\n### Batch G — Individual feedback\n\nAsk: \"Do you have specific observations for any individual participant?\"\n\nFor each named participant, extract:\n\n- Role or background\n- Starting level\n- Behavior\u002Fengagement (positive and negative)\n- Notable evolution, breakthrough, or resistance\n- How they ended the session\n\n**Individual Feedback is optional.** Only write it if the trainer explicitly provides meaningful observations. Do not prompt for feedback on every participant.\n\nBe diplomatic. Describe behaviors, not character. Name problems factually; do not editorialize. When writing for an external client about a team you don't know, consider whether naming individuals is appropriate at all.\n\nSee `references\u002Ftone-of-voice.md` — Diplomatic framing section.\n\n### Batch H — Recommendations & next steps\n\nAsk: \"What would you recommend to the direction\u002Fclient to build on this session?\"\n\nProbe for:\n\n- Resources and access to provide (licenses, books, platforms, communities)\n- Practices to anchor in daily work\n- What to pace carefully — basics before advanced material\n- Follow-up sessions (refresher, coaching, Q&A after a few weeks)\n- Assessment and validation (quiz, practical challenge, peer review, checklist)\n- Knowledge-sharing rituals (Slack\u002FTeams channel, recurring meeting, Loom demos, buddy system, monthly show-and-tell)\n- Management involvement (protect practice time, 1:1 check-ins, celebrate wins)\n- External resources (books, courses, certifications) for self-driven participants\n- Specific warnings or caveats for management\n\n### Batch I — Annexes\n\nAsk: \"Do you have any annexes to attach to the report?\"\n\nAnnexes can include:\n\n- Photos from the session\n- Satisfaction survey results (NPS, ratings, verbatim comments)\n- Slides or handouts distributed during the session\n- Work produced by participants (exercises, prototypes, documents, diagrams)\n- Reference documents used during the session\n- Any other supporting material\n\nFor each annex:\n\n- **Image** → attempt auto-embed at Step 6\n- **File** (PDF, slides, spreadsheet) → reference in the Annexes section; do not embed\n- **Survey data** → synthesize in Step 4, then include as a dedicated section in the doc\n- **Participant deliverable** → reference in the relevant Walkthrough step AND in Annexes\n\n### Batch J — Closing & contact\n\nAsk: \"May I include a closing note thanking the team for the invitation, and your contact details for future collaboration? (email + phone)\"\n\nIf yes: collect name, email, phone. The closing is written in the document language, personal in tone, brief. See `references\u002Fmarkdown-draft.md` — Closing paragraph section.\n\n## Step 4 — Feedback synthesis (if survey data provided)\n\nProduce a synthesis in the conversation before drafting:\n\n- Overall score \u002F NPS\n- Rating distribution\n- Top 3 positive themes\n- Top 3 areas for improvement\n- Any outlier responses\n\nAsk the user to confirm before it enters the document.\n\n## Step 4b — Confirm outline\n\n```\nHere's what I'll draft:\n1. Context\n2. Starting Levels\n3. Session Walkthrough (N steps)\n4. General Observations         [optional — include if trainer provided content]\n5. Participant Satisfaction     [only if survey data provided]\n6. Individual Feedback          [optional — include if trainer provided feedback]\n7. Recommendations & Next Steps\n8. Annexes                      [only if annexes provided]\n[Closing + contact]\n\nLanguage: [language] | Audience: [target] | Template: [yes\u002Fno]\n```\n\nAsk: \"Anything to adjust before I start the draft?\"\n\n## Step 5 — Markdown draft\n\n**Load `references\u002Fmarkdown-draft.md` before writing.** It contains the full section-by- section writing guide, Markdown limitations, HTML table workarounds, and closing paragraph guidance.\n\n### Humanization pass\n\nBefore presenting the draft, apply the humanizer skill (loaded in Step 0). If no humanizer skill is available, apply these rules inline:\n\n- Cut all AI throat-clearing openers and sentence starters\n- Cut adjective doublets — pick the more precise word\n- Replace passive voice with active wherever natural\n- Replace vague praise or criticism with specific behaviors or facts\n- Short sentences over long ones\n- Adapt to the document language (see `references\u002Ftone-of-voice.md`)\n\nDo not present an un-humanized draft.\n\n### Iteration loop\n\nPresent the draft inline in the conversation. Let the user lead. Update the `.md` file for every change. One canonical file, no versions. Only move to Step 6 when the user explicitly confirms the content is final.\n\n## Step 6 — Final .docx generation\n\n**Load `references\u002Fdocx-generation.md` and the `docx` skill before starting.**\n\nThis step runs once. It is terminal: if the user requests changes after the .docx is generated, update the `.md` and regenerate from scratch.\n\nDeliver both files. If the environment supports inline file delivery (e.g. `present_files` on Claude.ai), use it. Otherwise, print the absolute paths to both files.\n\n## Pitfalls\n\n- Don't fabricate details — only document what the trainer explicitly provided\n- Don't editorialize in General Observations — factual only\n- Don't write Individual Feedback unless explicitly provided — and stay diplomatic\n- Don't pad recommendations — 6 sharp ones beat 12 vague ones\n- Always include a Pacing recommendation in the Next Steps\n- This skill is not developer-specific — adapt vocabulary to the discipline\n- Never generate the .docx mid-conversation — Markdown is the draft stage\n- Never skip an annex or image — embed, reference, or placeholder\n","# Training Report\n\nIterate the full report in **Markdown first**. Generate the **.docx last**, once, when the content is final. The .md is the canonical artifact; the .docx is a terminal derivative.\n\nDiscipline-agnostic: coding workshop, leadership seminar, safety training, onboarding, creative workshop — all apply equally.\n\n> **Voice mode:** this conversation may be conducted by voice. Transcription can introduce homophones, missing punctuation, or ambiguous proper nouns (names, company names, tool names). If any answer is unclear after transcription, ask a short clarifying question before moving on — do not guess.\n\n## Reference files\n\nLoad these files at the steps indicated. Do not load them all upfront.\n\n| File | Load at |\n| --- | --- |\n| `references\u002Ftone-of-voice.md` | Step 1 (after language + audience confirmed) |\n| `references\u002Fmarkdown-draft.md` | Step 5 (before writing the draft) |\n| `references\u002Fdocx-generation.md` | Step 6 (before generating the .docx) |\n\n## Step 0 — Check dependencies\n\n**Before asking the user anything**, verify skill availability.\n\n**`docx` skill (required for Step 6)**\n\n- If found: note it; load it at Step 6\n- If not found: warn the user — it is required to generate the final Word document and can be installed from Anthropic's official skill library. Offer to proceed with the Markdown draft in the meantime.\n\n**Humanizer skill (recommended)**\n\n- After Step 1, look for a humanizer skill matching the chosen language\n- If found: load it and apply it during the humanization pass in Step 5\n- If not found: tell the user once, then fall back to inline humanization rules (Step 5b). Suggest installing a humanizer skill for the chosen language.\n\n## Step 1 — Language & audience\n\nAsk:\n\n1. \"In what language should I write the report? (French \u002F English \u002F other)\"\n2. \"Who is the primary reader? (executive \u002F HR \u002F direct management \u002F external client \u002F internal archive)\"\n\nThen load `references\u002Ftone-of-voice.md` and apply its guidance throughout.\n\n## Step 2 — Template\n\nAsk:\n\n> \"Do you have a Word (.docx) template for this report? (company header\u002Ffooter, logo, branded fonts, color scheme)\"\n\n- **Yes** → ask them to upload it; use it as the base at Step 6 (unpack\u002Finject\u002Frepack)\n- **No** → proceed with a clean document; ask for a brand color before defaulting to blue `#2E75B6`\n\n## Step 3 — Interview\n\nConduct a structured interview in batches. Wait for answers before moving on. Extract what the user already told you from the conversation before asking.\n\n### Batch A — Session metadata\n\n- Trainer name and role\n- Date, location, company\u002Fteam name\n- Duration\n- Total number of participants\n- Confirm or refine: who is the document for?\n\n### Batch B — Session context\n\n- Stated goal of the training\n- Subject, topic, tool, or material used as practical support\n- Any rules or constraints set at the start\n- Materials, accounts, licenses, or equipment provided to participants\n\n### Batch C — Starting levels\n\n- Distribution of familiarity across the group (any beginners? any experts?)\n- Notable outliers at either end\n\n### Batch D — Session walkthrough\n\nWalk through the session step by step. For each step:\n\n- Objective\n- What participants actually did\n- Materials, tools, or exercises involved\n- First exposure to this concept or not\n- How it landed; any difficulties\n\nProbe until complete: \"What happened next?\", \"Did anything go differently than planned?\", \"Were there any pivots?\"\n\n### Batch E — Deliverables\n\nAsk: \"Did participants produce anything during the session?\"\n\nProbe for:\n\n- Documents, files, diagrams, prototypes, or any output created during exercises\n- Collaborative work produced as a group\n- Individual work produced autonomously\n- Anything left incomplete or started but not finished\n\nThese may appear in the Annexes and\u002For be referenced in the Session Walkthrough.\n\n### Batch F — General observations\n\n- Overall energy and engagement of the group\n- Any incidents, surprises, or notable moments\n- Schedule: did it hold, or were sections cut\u002Fextended?\n- Logistical issues (room, materials, setup)\n\nGeneral Observations is **optional**. If the trainer has nothing notable to add beyond the walkthrough, skip this section entirely.\n\n### Batch G — Individual feedback\n\nAsk: \"Do you have specific observations for any individual participant?\"\n\nFor each named participant, extract:\n\n- Role or background\n- Starting level\n- Behavior\u002Fengagement (positive and negative)\n- Notable evolution, breakthrough, or resistance\n- How they ended the session\n\n**Individual Feedback is optional.** Only write it if the trainer explicitly provides meaningful observations. Do not prompt for feedback on every participant.\n\nBe diplomatic. Describe behaviors, not character. Name problems factually; do not editorialize. When writing for an external client about a team you don't know, consider whether naming individuals is appropriate at all.\n\nSee `references\u002Ftone-of-voice.md` — Diplomatic framing section.\n\n### Batch H — Recommendations & next steps\n\nAsk: \"What would you recommend to the direction\u002Fclient to build on this session?\"\n\nProbe for:\n\n- Resources and access to provide (licenses, books, platforms, communities)\n- Practices to anchor in daily work\n- What to pace carefully — basics before advanced material\n- Follow-up sessions (refresher, coaching, Q&A after a few weeks)\n- Assessment and validation (quiz, practical challenge, peer review, checklist)\n- Knowledge-sharing rituals (Slack\u002FTeams channel, recurring meeting, Loom demos, buddy system, monthly show-and-tell)\n- Management involvement (protect practice time, 1:1 check-ins, celebrate wins)\n- External resources (books, courses, certifications) for self-driven participants\n- Specific warnings or caveats for management\n\n### Batch I — Annexes\n\nAsk: \"Do you have any annexes to attach to the report?\"\n\nAnnexes can include:\n\n- Photos from the session\n- Satisfaction survey results (NPS, ratings, verbatim comments)\n- Slides or handouts distributed during the session\n- Work produced by participants (exercises, prototypes, documents, diagrams)\n- Reference documents used during the session\n- Any other supporting material\n\nFor each annex:\n\n- **Image** → attempt auto-embed at Step 6\n- **File** (PDF, slides, spreadsheet) → reference in the Annexes section; do not embed\n- **Survey data** → synthesize in Step 4, then include as a dedicated section in the doc\n- **Participant deliverable** → reference in the relevant Walkthrough step AND in Annexes\n\n### Batch J — Closing & contact\n\nAsk: \"May I include a closing note thanking the team for the invitation, and your contact details for future collaboration? (email + phone)\"\n\nIf yes: collect name, email, phone. The closing is written in the document language, personal in tone, brief. See `references\u002Fmarkdown-draft.md` — Closing paragraph section.\n\n## Step 4 — Feedback synthesis (if survey data provided)\n\nProduce a synthesis in the conversation before drafting:\n\n- Overall score \u002F NPS\n- Rating distribution\n- Top 3 positive themes\n- Top 3 areas for improvement\n- Any outlier responses\n\nAsk the user to confirm before it enters the document.\n\n## Step 4b — Confirm outline\n\n```\nHere's what I'll draft:\n1. Context\n2. Starting Levels\n3. Session Walkthrough (N steps)\n4. General Observations         [optional — include if trainer provided content]\n5. Participant Satisfaction     [only if survey data provided]\n6. Individual Feedback          [optional — include if trainer provided feedback]\n7. Recommendations & Next Steps\n8. Annexes                      [only if annexes provided]\n[Closing + contact]\n\nLanguage: [language] | Audience: [target] | Template: [yes\u002Fno]\n```\n\nAsk: \"Anything to adjust before I start the draft?\"\n\n## Step 5 — Markdown draft\n\n**Load `references\u002Fmarkdown-draft.md` before writing.** It contains the full section-by- section writing guide, Markdown limitations, HTML table workarounds, and closing paragraph guidance.\n\n### Humanization pass\n\nBefore presenting the draft, apply the humanizer skill (loaded in Step 0). If no humanizer skill is available, apply these rules inline:\n\n- Cut all AI throat-clearing openers and sentence starters\n- Cut adjective doublets — pick the more precise word\n- Replace passive voice with active wherever natural\n- Replace vague praise or criticism with specific behaviors or facts\n- Short sentences over long ones\n- Adapt to the document language (see `references\u002Ftone-of-voice.md`)\n\nDo not present an un-humanized draft.\n\n### Iteration loop\n\nPresent the draft inline in the conversation. Let the user lead. Update the `.md` file for every change. One canonical file, no versions. Only move to Step 6 when the user explicitly confirms the content is final.\n\n## Step 6 — Final .docx generation\n\n**Load `references\u002Fdocx-generation.md` and the `docx` skill before starting.**\n\nThis step runs once. It is terminal: if the user requests changes after the .docx is generated, update the `.md` and regenerate from scratch.\n\nDeliver both files. If the environment supports inline file delivery (e.g. `present_files` on Claude.ai), use it. Otherwise, print the absolute paths to both files.\n\n## Pitfalls\n\n- Don't fabricate details — only document what the trainer explicitly provided\n- Don't editorialize in General Observations — factual only\n- Don't write Individual Feedback unless explicitly provided — and stay diplomatic\n- Don't pad recommendations — 6 sharp ones beat 12 vague ones\n- Always include a Pacing recommendation in the Next Steps\n- This skill is not developer-specific — adapt vocabulary to the discipline\n- Never generate the .docx mid-conversation — Markdown is the draft stage\n- Never skip an annex or image — embed, reference, or placeholder\n",{"name":5,"license":15,"metadata":24,"description":7,"allowed-tools":30,"compatibility":31,"user-invocable":32},{"author":25,"version":26,"openclaw":27},"samber","1.0.1",{"emoji":28,"homepage":29},"📚","https:\u002F\u002Fgithub.com\u002Fsamber\u002Fcc-skills","Read Edit Write Glob Grep Agent AskUserQuestion","Designed for Claude or similar AI agents.",true,"main","8859218955d9504cd18b59e7892100718039d3b4","data\u002Fskills\u002Fsamber-cc-skills\u002Ftraining-report",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":42,"prompt":52,"zipAvailable":32},[43,46,49],{"tool":44,"command":45},"npx","npx skills add om-scogo\u002Fskillsh-scraper --skill training-report",{"tool":47,"command":48},"bunx","bunx skills add om-scogo\u002Fskillsh-scraper --skill training-report",{"tool":50,"command":51},"pnpm","pnpm dlx skills add om-scogo\u002Fskillsh-scraper --skill training-report","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fsamber-cc-skills\u002Ftraining-report\u002FSkill.md",[54],{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"metadata.json","REFERENCE","参考文档",425,"https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fsamber-cc-skills\u002Ftraining-report\u002Fmetadata.json",[61,68,73,80,85,92],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"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":69,"name":63,"nameZh":6,"description":64,"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},"01M7D6M85CKKN87TA98VCQV4H7","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fyorkeccak-scientific-skills\u002Farxiv-search\u002FSkill.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"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":81,"name":75,"nameZh":6,"description":76,"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},"01M7D4ZHZKJD2RSNGAF63V14P4","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fworking-with-legacy-code\u002FSkill.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7D4Z4MVYVY3NMJ18BNV6WNA","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fweb-typography\u002FSkill.md",[],[]]