[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F2XRMV9E7NJ29ABR2808CM":3,"skill-same:01M7F2XRMV9E7NJ29ABR2808CM":89},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":12,"updatedAt":34,"install":35,"resources":48},"01M7F2XRMV9E7NJ29ABR2808CM","guide-recap",null,"Transform CHANGELOG entries into social content (LinkedIn, Twitter\u002FX, Newsletter, Slack) in FR + EN. Use after releases or weekly to generate release notes, announcements, social media posts, or recap summaries from guide updates.","313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace","313DEVGRP","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F34762848?v=4","01M7F2M535Z5X8XGHYD8TDVAB3","A-RMS by 313DEVGRP","01M7F2M54CR0P3631F4YM0D014",0,"MIT","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fguide-recap\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: guide-recap\ndescription: \"Transform CHANGELOG entries into social content (LinkedIn, Twitter\u002FX, Newsletter, Slack) in FR + EN. Use after releases or weekly to generate release notes, announcements, social media posts, or recap summaries from guide updates.\"\nallowed-tools: Read Bash\nargument-hint: \"\u003Clatest|vX.Y.Z|week [YYYY-MM-DD]> [--interactive] [--format=linkedin|twitter|newsletter|slack] [--lang=fr|en] [--save]\"\neffort: low\n---\n\n# Guide recap\n\nGenerate social media content from CHANGELOG.md entries. Produces 8 outputs by default (4 formats x 2 languages).\n\n## When to use\n\n- After running `\u002Frelease` to create social announcements\n- Weekly to summarize multiple releases\n- Before posting on LinkedIn, Twitter\u002FX, newsletter, or Slack\n\n## Usage\n\n```\n\u002Fguide-recap latest              # Latest released version\n\u002Fguide-recap v3.20.5             # Specific version\n\u002Fguide-recap week                # Current week (Monday to today)\n\u002Fguide-recap week 2026-01-27     # Specific week (Monday to Sunday)\n```\n\n### Flags\n\n| Flag | Effect | Default |\n|------|--------|---------|\n| `--interactive` | Guide mode: choose angle, audience, highlight | Off (auto-draft) |\n| `--format=X` | Single format: `linkedin`, `twitter`, `newsletter`, `slack` | All 4 formats |\n| `--lang=X` | Single language: `fr`, `en` | Both FR + EN |\n| `--save` | Save output to `[project-docs]\u002Fsocial-posts\u002F` | Display only |\n| `--force` | Generate even if only maintenance entries | Skip low-score |\n\n## Workflow (7 steps)\n\n### Step 1: Parse input\n\nParse `$ARGUMENTS` to determine mode:\n\n| Input | Mode | Target |\n|-------|------|--------|\n| `latest` | Single version | First `## [X.Y.Z]` after `[Unreleased]` |\n| `vX.Y.Z` or `X.Y.Z` | Single version | Exact version match |\n| `week` | Week range | Monday of current week -> today |\n| `week YYYY-MM-DD` | Week range | That Monday -> following Sunday |\n\nIf no argument or invalid argument, display usage and exit.\n\n### Step 2: Extract CHANGELOG entries\n\nRead `CHANGELOG.md` from the project root.\n\n**Single version:**\n1. Find line matching `## [{version}]`\n2. Extract all content until next `## [` line\n3. Parse `### Added`, `### Changed`, `### Fixed` sections\n\n**Week range:**\n1. Collect all `## [X.Y.Z] - YYYY-MM-DD` entries where date falls in range\n2. Parse all sections from all matching versions\n\n**Error: version not found** -> List last 5 versions, suggest `latest`.\n**Error: week has no entries** -> Show date of last release, suggest that version.\n\n### Step 3: Categorize entries\n\nFor each top-level entry (first-level bullet under `###`), assign a category:\n\n| Category | Weight | Detection |\n|----------|--------|-----------|\n| `NEW_CONTENT` | 3 | New files, new sections, new diagrams, new quiz questions |\n| `GROWTH_METRIC` | 2 | Line count growth, item count changes |\n| `RESEARCH` | 1 | Resource evaluations, external source integrations |\n| `FIX` | 1 | Under `### Fixed`, corrections |\n| `MAINTENANCE` | 0 | README updates, badge syncs, landing syncs, count updates |\n\nSee `references\u002Fchangelog-parsing-rules.md` for detailed classification rules.\n\n### Step 4: Transform to user value\n\nApply mappings from `references\u002Fcontent-transformation.md`:\n\n- Technical language -> user benefit\n- Extract concrete numbers\n- Credit named sources\n- Cluster related entries\n\nValidate against `references\u002Ftone-guidelines.md` DO\u002FDON'T checklist.\n\n### Step 4b: Interactive Mode (--interactive only)\n\nIf `--interactive` flag is set, insert between steps 4 and 5:\n\n1. Display candidate highlights with scores:\n   ```\n   Highlights (by score):\n   [14] 4 new ASCII diagrams (16 -> 20)     [NEW_CONTENT]\n   [ 9] 30 new quiz questions (227 -> 257)   [NEW_CONTENT]\n   [ 6] Docker sandbox isolation guide        [NEW_CONTENT]\n   [ 1] README updated                        [MAINTENANCE]\n   ```\n\n2. Ask angle:\n   - Auto (highest scored = hook)\n   - User picks specific entry as hook\n   - Custom angle (user provides theme)\n\n3. Ask target audience:\n   - `devs` (technical depth)\n   - `tech-leads` (impact focus)\n   - `general` (accessible language)\n   - `all` (default, balanced)\n\n4. Ask primary highlight:\n   - Auto (top score)\n   - User selects from list\n\n5. Confirm selection and proceed to step 5.\n\n### Step 5: Score and select\n\nCompute score for each entry:\n\n```\nscore = (category_weight * 3)\n      + (has_number * 2)\n      + (named_source * 1)\n      + (new_file * 1)\n      + (min(impact_files, 3))\n      + (breaking * 2)\n```\n\nSelect top 3-4 entries by score. Highest score = hook line.\n\n**If all scores \u003C 3**: Output \"No social content recommended for this version. Use `--force` to generate anyway.\" and exit (unless `--force`).\n\n### Step 6: Generate content\n\nFor each requested format (default: all 4) and language (default: both):\n\n1. Read the corresponding template from `assets\u002F`\n2. Fill template fields using scored and transformed entries\n3. Apply tone-guidelines.md quality checklist\n\n**Links:**\n\n| Format | Link Target |\n|--------|-------------|\n| LinkedIn | Landing site URL |\n| Twitter | GitHub repo URL |\n| Newsletter | Both (landing + GitHub) |\n| Slack | GitHub repo URL |\n\n**URLs:**\n- Landing: `https:\u002F\u002F{DOMAIN}\u002F`\n- GitHub: `https:\u002F\u002Fgithub.com\u002F{OWNER}\u002F{REPO}`\n\n### Step 7: Output\n\nDisplay each generated post in a fenced code block, labeled by format and language:\n\n```\n## LinkedIn (FR)\n\n```text\n[content]\n`` `\n\n## LinkedIn (EN)\n\n```text\n[content]\n`` `\n\n## Twitter\u002FX (FR)\n\n```text\n[content]\n`` `\n\n...\n```\n\nIf `--save` flag: write all outputs to `[project-docs]\u002Fsocial-posts\u002FYYYY-MM-DD-vX.Y.Z.md` (for version) or `[project-docs]\u002Fsocial-posts\u002FYYYY-MM-DD-week.md` (for week). Create `[project-docs]\u002Fsocial-posts\u002F` directory if it doesn't exist.\n\n## Error Handling\n\n| Error | Response |\n|-------|----------|\n| No argument | Display usage block |\n| Invalid argument | Display usage block with examples |\n| Version not found | List 5 most recent versions, suggest `latest` |\n| Week has no entries | Show date of last release, suggest version |\n| All entries MAINTENANCE (score 0) | \"No social content recommended. Use `--force` to override.\" |\n| CHANGELOG.md not found | \"CHANGELOG.md not found in project root.\" |\n\n## Reference Files\n\n- `references\u002Ftone-guidelines.md` - DO\u002FDON'T rules, emoji budget, language register\n- `references\u002Fchangelog-parsing-rules.md` - CHANGELOG format, extraction, scoring algorithm\n- `references\u002Fcontent-transformation.md` - Technical -> user value mappings (30+)\n- `assets\u002Flinkedin-template.md` - ~1300 chars, hook + bullets + CTA + hashtags\n- `assets\u002Ftwitter-template.md` - 280 chars single or 2-3 tweet thread\n- `assets\u002Fnewsletter-template.md` - ~500 words, structured sections\n- `assets\u002Fslack-template.md` - Compact, emoji-rich, Slack formatting\n- `examples\u002Fversion-output.md` - Full example output for v3.20.5\n- `examples\u002Fweek-output.md` - Full example output for week 2026-01-27\n\n## Tips\n\n- Run `\u002Fguide-recap latest` right after `\u002Frelease` to prepare social posts\n- Use `--interactive` the first few times to understand the scoring\n- Use `--format=linkedin --lang=fr` when you only need one specific output\n- `--save` outputs are gitignored via `[project-docs]\u002F` convention\n- Review and personalize before posting (these are drafts, not final copy)\n","# Guide recap\n\nGenerate social media content from CHANGELOG.md entries. Produces 8 outputs by default (4 formats x 2 languages).\n\n## When to use\n\n- After running `\u002Frelease` to create social announcements\n- Weekly to summarize multiple releases\n- Before posting on LinkedIn, Twitter\u002FX, newsletter, or Slack\n\n## Usage\n\n```\n\u002Fguide-recap latest              # Latest released version\n\u002Fguide-recap v3.20.5             # Specific version\n\u002Fguide-recap week                # Current week (Monday to today)\n\u002Fguide-recap week 2026-01-27     # Specific week (Monday to Sunday)\n```\n\n### Flags\n\n| Flag | Effect | Default |\n|------|--------|---------|\n| `--interactive` | Guide mode: choose angle, audience, highlight | Off (auto-draft) |\n| `--format=X` | Single format: `linkedin`, `twitter`, `newsletter`, `slack` | All 4 formats |\n| `--lang=X` | Single language: `fr`, `en` | Both FR + EN |\n| `--save` | Save output to `[project-docs]\u002Fsocial-posts\u002F` | Display only |\n| `--force` | Generate even if only maintenance entries | Skip low-score |\n\n## Workflow (7 steps)\n\n### Step 1: Parse input\n\nParse `$ARGUMENTS` to determine mode:\n\n| Input | Mode | Target |\n|-------|------|--------|\n| `latest` | Single version | First `## [X.Y.Z]` after `[Unreleased]` |\n| `vX.Y.Z` or `X.Y.Z` | Single version | Exact version match |\n| `week` | Week range | Monday of current week -> today |\n| `week YYYY-MM-DD` | Week range | That Monday -> following Sunday |\n\nIf no argument or invalid argument, display usage and exit.\n\n### Step 2: Extract CHANGELOG entries\n\nRead `CHANGELOG.md` from the project root.\n\n**Single version:**\n1. Find line matching `## [{version}]`\n2. Extract all content until next `## [` line\n3. Parse `### Added`, `### Changed`, `### Fixed` sections\n\n**Week range:**\n1. Collect all `## [X.Y.Z] - YYYY-MM-DD` entries where date falls in range\n2. Parse all sections from all matching versions\n\n**Error: version not found** -> List last 5 versions, suggest `latest`.\n**Error: week has no entries** -> Show date of last release, suggest that version.\n\n### Step 3: Categorize entries\n\nFor each top-level entry (first-level bullet under `###`), assign a category:\n\n| Category | Weight | Detection |\n|----------|--------|-----------|\n| `NEW_CONTENT` | 3 | New files, new sections, new diagrams, new quiz questions |\n| `GROWTH_METRIC` | 2 | Line count growth, item count changes |\n| `RESEARCH` | 1 | Resource evaluations, external source integrations |\n| `FIX` | 1 | Under `### Fixed`, corrections |\n| `MAINTENANCE` | 0 | README updates, badge syncs, landing syncs, count updates |\n\nSee `references\u002Fchangelog-parsing-rules.md` for detailed classification rules.\n\n### Step 4: Transform to user value\n\nApply mappings from `references\u002Fcontent-transformation.md`:\n\n- Technical language -> user benefit\n- Extract concrete numbers\n- Credit named sources\n- Cluster related entries\n\nValidate against `references\u002Ftone-guidelines.md` DO\u002FDON'T checklist.\n\n### Step 4b: Interactive Mode (--interactive only)\n\nIf `--interactive` flag is set, insert between steps 4 and 5:\n\n1. Display candidate highlights with scores:\n   ```\n   Highlights (by score):\n   [14] 4 new ASCII diagrams (16 -> 20)     [NEW_CONTENT]\n   [ 9] 30 new quiz questions (227 -> 257)   [NEW_CONTENT]\n   [ 6] Docker sandbox isolation guide        [NEW_CONTENT]\n   [ 1] README updated                        [MAINTENANCE]\n   ```\n\n2. Ask angle:\n   - Auto (highest scored = hook)\n   - User picks specific entry as hook\n   - Custom angle (user provides theme)\n\n3. Ask target audience:\n   - `devs` (technical depth)\n   - `tech-leads` (impact focus)\n   - `general` (accessible language)\n   - `all` (default, balanced)\n\n4. Ask primary highlight:\n   - Auto (top score)\n   - User selects from list\n\n5. Confirm selection and proceed to step 5.\n\n### Step 5: Score and select\n\nCompute score for each entry:\n\n```\nscore = (category_weight * 3)\n      + (has_number * 2)\n      + (named_source * 1)\n      + (new_file * 1)\n      + (min(impact_files, 3))\n      + (breaking * 2)\n```\n\nSelect top 3-4 entries by score. Highest score = hook line.\n\n**If all scores \u003C 3**: Output \"No social content recommended for this version. Use `--force` to generate anyway.\" and exit (unless `--force`).\n\n### Step 6: Generate content\n\nFor each requested format (default: all 4) and language (default: both):\n\n1. Read the corresponding template from `assets\u002F`\n2. Fill template fields using scored and transformed entries\n3. Apply tone-guidelines.md quality checklist\n\n**Links:**\n\n| Format | Link Target |\n|--------|-------------|\n| LinkedIn | Landing site URL |\n| Twitter | GitHub repo URL |\n| Newsletter | Both (landing + GitHub) |\n| Slack | GitHub repo URL |\n\n**URLs:**\n- Landing: `https:\u002F\u002F{DOMAIN}\u002F`\n- GitHub: `https:\u002F\u002Fgithub.com\u002F{OWNER}\u002F{REPO}`\n\n### Step 7: Output\n\nDisplay each generated post in a fenced code block, labeled by format and language:\n\n```\n## LinkedIn (FR)\n\n```text\n[content]\n`` `\n\n## LinkedIn (EN)\n\n```text\n[content]\n`` `\n\n## Twitter\u002FX (FR)\n\n```text\n[content]\n`` `\n\n...\n```\n\nIf `--save` flag: write all outputs to `[project-docs]\u002Fsocial-posts\u002FYYYY-MM-DD-vX.Y.Z.md` (for version) or `[project-docs]\u002Fsocial-posts\u002FYYYY-MM-DD-week.md` (for week). Create `[project-docs]\u002Fsocial-posts\u002F` directory if it doesn't exist.\n\n## Error Handling\n\n| Error | Response |\n|-------|----------|\n| No argument | Display usage block |\n| Invalid argument | Display usage block with examples |\n| Version not found | List 5 most recent versions, suggest `latest` |\n| Week has no entries | Show date of last release, suggest version |\n| All entries MAINTENANCE (score 0) | \"No social content recommended. Use `--force` to override.\" |\n| CHANGELOG.md not found | \"CHANGELOG.md not found in project root.\" |\n\n## Reference Files\n\n- `references\u002Ftone-guidelines.md` - DO\u002FDON'T rules, emoji budget, language register\n- `references\u002Fchangelog-parsing-rules.md` - CHANGELOG format, extraction, scoring algorithm\n- `references\u002Fcontent-transformation.md` - Technical -> user value mappings (30+)\n- `assets\u002Flinkedin-template.md` - ~1300 chars, hook + bullets + CTA + hashtags\n- `assets\u002Ftwitter-template.md` - 280 chars single or 2-3 tweet thread\n- `assets\u002Fnewsletter-template.md` - ~500 words, structured sections\n- `assets\u002Fslack-template.md` - Compact, emoji-rich, Slack formatting\n- `examples\u002Fversion-output.md` - Full example output for v3.20.5\n- `examples\u002Fweek-output.md` - Full example output for week 2026-01-27\n\n## Tips\n\n- Run `\u002Fguide-recap latest` right after `\u002Frelease` to prepare social posts\n- Use `--interactive` the first few times to understand the scoring\n- Use `--format=linkedin --lang=fr` when you only need one specific output\n- `--save` outputs are gitignored via `[project-docs]\u002F` convention\n- Review and personalize before posting (these are drafts, not final copy)\n",{"name":5,"effort":24,"description":7,"allowed-tools":25,"argument-hint":26},"low","Read Bash","\u003Clatest|vX.Y.Z|week [YYYY-MM-DD]> [--interactive] [--format=linkedin|twitter|newsletter|slack] [--lang=fr|en] [--save]","main","f2cc95bc769ca4c3a398965b767dfb41cdf8d698","reference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fguide-recap",2,"https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace","https:\u002F\u002Fgithub.com\u002F313DEVGRP","https:\u002F\u002Fwww.a-rms.net","2026-10-18 12:48:10",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add 313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace --skill guide-recap",{"tool":41,"command":42},"bunx","bunx skills add 313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace --skill guide-recap",{"tool":44,"command":45},"pnpm","pnpm dlx skills add 313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace --skill guide-recap","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fguide-recap\u002FSKILL.md",true,[49,55,59,63,67,73,77,81,85],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"assets\u002Flinkedin-template.md","ASSET","资产文件",2443,"https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fguide-recap\u002Fassets\u002Flinkedin-template.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"assets\u002Fnewsletter-template.md",2930,"https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fguide-recap\u002Fassets\u002Fnewsletter-template.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"assets\u002Fslack-template.md",2006,"https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fguide-recap\u002Fassets\u002Fslack-template.md",{"path":64,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":65,"sourceHtmlUrl":66},"assets\u002Ftwitter-template.md",2179,"https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fguide-recap\u002Fassets\u002Ftwitter-template.md",{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"examples\u002Fversion-output.md","REFERENCE","参考文档",5451,"https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fguide-recap\u002Fexamples\u002Fversion-output.md",{"path":74,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":75,"sourceHtmlUrl":76},"examples\u002Fweek-output.md",7941,"https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fguide-recap\u002Fexamples\u002Fweek-output.md",{"path":78,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fchangelog-parsing-rules.md",4878,"https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fguide-recap\u002Freferences\u002Fchangelog-parsing-rules.md",{"path":82,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fcontent-transformation.md",4401,"https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fguide-recap\u002Freferences\u002Fcontent-transformation.md",{"path":86,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Ftone-guidelines.md",2965,"https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fguide-recap\u002Freferences\u002Ftone-guidelines.md",[90,97,104,111,118,125],{"skillNo":91,"name":92,"nameZh":6,"description":93,"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},"01M7F343WNVHZWWYJDD77QEJ7J","voice-refine","Transform verbose voice input into structured, token-efficient Claude prompts. Use when cleaning up voice memos, dictation output, or speech-to-text transcriptions that contain filler words, repetitions, and unstructured thoughts.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fvoice-refine\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M7F3417SNXASFTDA1B2X4XYZ","validate-changes","Evaluate staged changes using LLM-as-a-Judge before committing","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fvalidate-changes\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":19},"01M7F33YN9QK88H2B81PVHMNG1","update-threat-db","Delegate threat-intelligence research and updates to AgentSec, then validate the guide and landing mirrors.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fupdate-threat-db\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":19},"01M7F33SXQ57G2FVFK094T4584","token-audit","Audit Claude Code configuration to measure fixed-context token overhead and produce a prioritized action plan. Use when hitting rate limits, experiencing early context compression, or after adding significant config files.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Ftoken-audit\u002Fskill.md",[],[],{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":19},"01M7F33NAWXFPHW59CF52EAGGK","talk-stage6-revision","Produces revision sheets with quick navigation by act, a master concept-to-URL table, Q&A cheat-sheet with 6-10 anticipated questions, glossary, and external resources list. Use when preparing for a talk with Q&A, creating shareable reference material for attendees, or building a safety-net glossary for live delivery.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Ftalk-pipeline\u002Fstage-6-revision\u002FSKILL.md",[],[],{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":19},"01M7F33G9V96HVZKAGZ84J4EBR","talk-stage5-script","Produces a complete 5-act pitch with speaker notes, a slide-by-slide specification, and a ready-to-paste Kimi prompt for AI slide generation. Requires validated angle and title from Stage 4. Use when you have a confirmed talk angle and need the full script, slide spec, and AI-generated presentation prompt.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Ftalk-pipeline\u002Fstage-5-script\u002FSKILL.md",[],[]]