[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CTDWWVP5EZRC0MY1DPVYP2":3,"skill-same:01M6CTDWWVP5EZRC0MY1DPVYP2":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":24,"linkOnly":25,"markdownContent":26,"markdownBody":27,"frontMatter":28,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":6,"ownerDescription":38,"updatedAt":39,"install":40,"resources":52},"01M6CTDWWVP5EZRC0MY1DPVYP2","feedback-synthesizer",null,"Turns messy customer feedback into themes with supporting evidence and a ranked pain matrix. Use when consolidating feedback from several sources.","vibbs\u002Fcompany-os","vibbs","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F7379149?v=4","01M6CT6M03CAS1H7RA89F3965B","Vibbs Dod","01M6CT6M4MY60C9FFQ3AAR2RSK",6,"MIT","https:\u002F\u002Fgithub.com\u002Fvibbs\u002Fcompany-os\u002Fblob\u002Fmain\u002Fos\u002Fskills\u002Ffeedback-synthesizer\u002FSKILL.md",[],[19,20,21,22,23],"feedback","feedback synthesizer","customer","use","evidence","2026-11-10 10:12:30",false,"---\nname: feedback-synthesizer\ndescription: Turns messy customer feedback into themes with supporting evidence and a ranked pain matrix. Use when consolidating feedback from several sources.\nruntimes:\n  claude:\n    user-invocable: true\n---\n\n# Feedback Synthesizer\n\n## Reference\n- **ID**: S-PROD-04\n- **Category**: Product\n- **Inputs**: raw feedback (support tickets, CONV- artifacts, interviews, surveys, reviews, Slack messages)\n- **Outputs**: themed feedback report with actionable insights → artifacts\u002Fproduct\u002F\n- **Used by**: Product Agent\n- **Tool scripts**: .\u002Ftools\u002Fartifact\u002Fvalidate.sh\n\n## Purpose\nConsolidates raw, unstructured feedback from multiple channels into a structured report of themes, each backed by evidence and linked to actionable product recommendations.\n\n## Procedure\n1. Collect raw feedback from all available sources (support tickets, interviews, surveys, app reviews, internal notes).\n2. Normalize feedback: strip duplicates, tag source channel, note user segment.\n3. Perform open coding — assign initial labels to each piece of feedback.\n4. Group labels into higher-level themes (e.g., \"onboarding friction\", \"pricing confusion\").\n5. For each theme, count frequency and assess severity (blocker \u002F pain \u002F annoyance).\n6. Rank themes by frequency * severity to surface the highest-impact issues.\n7. For each top theme, provide 2-3 representative quotes as evidence.\n8. Draft actionable recommendations tied to each theme.\n9. Save the themed feedback report to `artifacts\u002Fproduct\u002F`.\n10. Validate the artifact using `.\u002Ftools\u002Fartifact\u002Fvalidate.sh`.\n\n### Small-Data Path\n\nIf fewer than 10 feedback items across all sources:\n- Skip frequency scoring — insufficient sample size for statistical patterns\n- Produce a **Signal Log** format: chronological list with severity ratings and direct action suggestions\n- Do not generate PRD candidates from fewer than 5 items in the same theme\n- Note the data limitation explicitly in the output\n- Recommend: \"Collect more feedback before synthesizing themes. Use customer-conversations skill to generate structured input.\"\n\nResume standard synthesis procedure when 10+ items are available.\n\n### Step 11: Produce PRD Candidates Section\n\nAfter ranking themes (Step 6), for the top 3 themes by frequency × severity score:\n\n1. Draft a PRD candidate entry for each:\n   - **Theme name**: from Step 4\n   - **Problem statement draft**: 2-sentence articulation of the user pain\n   - **Target ICP**: which user segment reported this most\n   - **Evidence sources**: CONV- artifact IDs + support theme artifact IDs\n   - **Priority score**: frequency × severity (1-25 scale)\n   - **Suggested next action**: `\u002Fship` (score >15), validate first with `\u002Fdiscovery-validation` (8-15), monitor (\u003C8)\n\n2. Append a `## PRD Candidates` section to the themed feedback report.\n\n3. Do NOT auto-create PRD artifacts — present candidates for human review only.\n\n4. Inform the user: \"Run `\u002Fship '[theme name]'` to initiate the PRD pipeline for any candidate you'd like to pursue.\"\n\n### Step 12: Produce Pain Matrix (when invoked by GTM Sprint)\n\nWhen the feedback-synthesizer is called during a GTM Sprint (or explicitly requested), produce an additional **Pain Matrix** section after Step 6:\n\n1. **Build the Matrix Table**\n\n   For each theme from Step 4, score:\n\n   | Theme | Frequency | $$ Impact \u002F Occurrence | Urgency (1-5) | Total Score |\n   |-------|-----------|----------------------|---------------|-------------|\n   | {theme} | {count} | {estimated $$ or time cost} | {1=someday, 5=hair-on-fire} | frequency x urgency |\n\n   - **$$ Impact**: Extract from interview quotes. Use time-to-money conversion if needed (e.g., \"wastes 3 hours\u002Fweek\" at $50\u002Fhr = $150\u002Fweek = $7,800\u002Fyear)\n   - **Urgency**: How soon prospects need a solution (1 = nice to have, 5 = actively searching right now)\n\n2. **Quadrant Classification**\n\n   Classify each theme into a quadrant:\n   - **Build Now** (High $$ + High Urgency): immediate opportunity, prioritize in MVP\n   - **Build Next** (High $$ + Low Urgency): strong business case but prospects can wait\n   - **Quick Win** (Low $$ + High Urgency): small pain but prospects want it solved now\n   - **Monitor** (Low $$ + Low Urgency): track but don't prioritize\n\n3. **Quotable Quotes Section**\n\n   For each \"Build Now\" theme, extract 2-3 direct quotes suitable for:\n   - Landing page social proof (above-the-fold pain quotes)\n   - Lead magnet content\n   - Pitch deck problem slides\n   - Sales outreach templates\n\n   Format: `\"[Quote]\" — {Role}, {Company Size}` (anonymize company name)\n\n4. Append the Pain Matrix, Quadrant Classification, and Quotable Quotes as a `## Pain Matrix` section in the feedback report artifact.\n\n## Quality Checklist\n- [ ] Feedback from at least 2 distinct sources is included\n- [ ] Themes are mutually exclusive and collectively exhaustive\n- [ ] Each theme has frequency count and severity rating\n- [ ] Representative quotes are included as evidence\n- [ ] Recommendations are specific and actionable, not vague\n- [ ] User segments are noted where relevant\n- [ ] Pain Matrix includes $$ quantification (when requested)\n- [ ] Quotable quotes are anonymized and landing-page-ready (when requested)\n- [ ] Artifact passes validation\n\n## Cross-References\n- **gtm-sprint** (S-GRO-09) — invokes Pain Matrix output during Day 2 synthesis\n- **customer-conversations** (S-PROD-08) — provides CONV- artifacts as input\n- **landing-page-copy** (S-GRO-02) — consumes quotable quotes for above-the-fold social proof\n- **prd-writer** (S-PROD-02) — PRD candidates from top themes\n","# Feedback Synthesizer\n\n## Reference\n- **ID**: S-PROD-04\n- **Category**: Product\n- **Inputs**: raw feedback (support tickets, CONV- artifacts, interviews, surveys, reviews, Slack messages)\n- **Outputs**: themed feedback report with actionable insights → artifacts\u002Fproduct\u002F\n- **Used by**: Product Agent\n- **Tool scripts**: .\u002Ftools\u002Fartifact\u002Fvalidate.sh\n\n## Purpose\nConsolidates raw, unstructured feedback from multiple channels into a structured report of themes, each backed by evidence and linked to actionable product recommendations.\n\n## Procedure\n1. Collect raw feedback from all available sources (support tickets, interviews, surveys, app reviews, internal notes).\n2. Normalize feedback: strip duplicates, tag source channel, note user segment.\n3. Perform open coding — assign initial labels to each piece of feedback.\n4. Group labels into higher-level themes (e.g., \"onboarding friction\", \"pricing confusion\").\n5. For each theme, count frequency and assess severity (blocker \u002F pain \u002F annoyance).\n6. Rank themes by frequency * severity to surface the highest-impact issues.\n7. For each top theme, provide 2-3 representative quotes as evidence.\n8. Draft actionable recommendations tied to each theme.\n9. Save the themed feedback report to `artifacts\u002Fproduct\u002F`.\n10. Validate the artifact using `.\u002Ftools\u002Fartifact\u002Fvalidate.sh`.\n\n### Small-Data Path\n\nIf fewer than 10 feedback items across all sources:\n- Skip frequency scoring — insufficient sample size for statistical patterns\n- Produce a **Signal Log** format: chronological list with severity ratings and direct action suggestions\n- Do not generate PRD candidates from fewer than 5 items in the same theme\n- Note the data limitation explicitly in the output\n- Recommend: \"Collect more feedback before synthesizing themes. Use customer-conversations skill to generate structured input.\"\n\nResume standard synthesis procedure when 10+ items are available.\n\n### Step 11: Produce PRD Candidates Section\n\nAfter ranking themes (Step 6), for the top 3 themes by frequency × severity score:\n\n1. Draft a PRD candidate entry for each:\n   - **Theme name**: from Step 4\n   - **Problem statement draft**: 2-sentence articulation of the user pain\n   - **Target ICP**: which user segment reported this most\n   - **Evidence sources**: CONV- artifact IDs + support theme artifact IDs\n   - **Priority score**: frequency × severity (1-25 scale)\n   - **Suggested next action**: `\u002Fship` (score >15), validate first with `\u002Fdiscovery-validation` (8-15), monitor (\u003C8)\n\n2. Append a `## PRD Candidates` section to the themed feedback report.\n\n3. Do NOT auto-create PRD artifacts — present candidates for human review only.\n\n4. Inform the user: \"Run `\u002Fship '[theme name]'` to initiate the PRD pipeline for any candidate you'd like to pursue.\"\n\n### Step 12: Produce Pain Matrix (when invoked by GTM Sprint)\n\nWhen the feedback-synthesizer is called during a GTM Sprint (or explicitly requested), produce an additional **Pain Matrix** section after Step 6:\n\n1. **Build the Matrix Table**\n\n   For each theme from Step 4, score:\n\n   | Theme | Frequency | $$ Impact \u002F Occurrence | Urgency (1-5) | Total Score |\n   |-------|-----------|----------------------|---------------|-------------|\n   | {theme} | {count} | {estimated $$ or time cost} | {1=someday, 5=hair-on-fire} | frequency x urgency |\n\n   - **$$ Impact**: Extract from interview quotes. Use time-to-money conversion if needed (e.g., \"wastes 3 hours\u002Fweek\" at $50\u002Fhr = $150\u002Fweek = $7,800\u002Fyear)\n   - **Urgency**: How soon prospects need a solution (1 = nice to have, 5 = actively searching right now)\n\n2. **Quadrant Classification**\n\n   Classify each theme into a quadrant:\n   - **Build Now** (High $$ + High Urgency): immediate opportunity, prioritize in MVP\n   - **Build Next** (High $$ + Low Urgency): strong business case but prospects can wait\n   - **Quick Win** (Low $$ + High Urgency): small pain but prospects want it solved now\n   - **Monitor** (Low $$ + Low Urgency): track but don't prioritize\n\n3. **Quotable Quotes Section**\n\n   For each \"Build Now\" theme, extract 2-3 direct quotes suitable for:\n   - Landing page social proof (above-the-fold pain quotes)\n   - Lead magnet content\n   - Pitch deck problem slides\n   - Sales outreach templates\n\n   Format: `\"[Quote]\" — {Role}, {Company Size}` (anonymize company name)\n\n4. Append the Pain Matrix, Quadrant Classification, and Quotable Quotes as a `## Pain Matrix` section in the feedback report artifact.\n\n## Quality Checklist\n- [ ] Feedback from at least 2 distinct sources is included\n- [ ] Themes are mutually exclusive and collectively exhaustive\n- [ ] Each theme has frequency count and severity rating\n- [ ] Representative quotes are included as evidence\n- [ ] Recommendations are specific and actionable, not vague\n- [ ] User segments are noted where relevant\n- [ ] Pain Matrix includes $$ quantification (when requested)\n- [ ] Quotable quotes are anonymized and landing-page-ready (when requested)\n- [ ] Artifact passes validation\n\n## Cross-References\n- **gtm-sprint** (S-GRO-09) — invokes Pain Matrix output during Day 2 synthesis\n- **customer-conversations** (S-PROD-08) — provides CONV- artifacts as input\n- **landing-page-copy** (S-GRO-02) — consumes quotable quotes for above-the-fold social proof\n- **prd-writer** (S-PROD-02) — PRD candidates from top themes\n",{"name":5,"runtimes":29,"description":7},{"claude":30},{"user-invocable":31},true,"main","e842fb6d0e04360c47db78bc2e2e2987314d64d4","os\u002Fskills\u002Ffeedback-synthesizer",2,"https:\u002F\u002Fgithub.com\u002Fvibbs\u002Fcompany-os","https:\u002F\u002Fgithub.com\u002Fvibbs","Principal Engineer · Applied AI · building ArcAI @ GrowthArc","2026-10-21 02:08:08",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":31},[42,45,48],{"tool":43,"command":44},"npx","npx skills add vibbs\u002Fcompany-os --skill feedback-synthesizer",{"tool":46,"command":47},"bunx","bunx skills add vibbs\u002Fcompany-os --skill feedback-synthesizer",{"tool":49,"command":50},"pnpm","pnpm dlx skills add vibbs\u002Fcompany-os --skill feedback-synthesizer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fvibbs\u002Fcompany-os\u002Fblob\u002Fmain\u002Fos\u002Fskills\u002Ffeedback-synthesizer\u002FSKILL.md",[],[54,63,71,81,97,115],{"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":24},"01M6CTHBW1E64ECYGD105N4S5E","typo-field","Fixture skill with a misspelled top-level field.","https:\u002F\u002Fgithub.com\u002Fvibbs\u002Fcompany-os\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Ftypo-field\u002FSKILL.md",[],[61,62],"typo field","fixture skill",{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":24},"01M6CTHABTV8FKVDHFMMKPAV51","spaced-comments","Fixture skill with comments and spaces after block keys.","https:\u002F\u002Fgithub.com\u002Fvibbs\u002Fcompany-os\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fspaced-comments\u002FSKILL.md",[],[70,62],"spaced comments",{"skillNo":72,"name":73,"nameZh":6,"description":74,"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":24},"01M6CTH8MHC14KB65ZDHYBJW1N","crlf-comments","Fixture skill with Windows line endings.","https:\u002F\u002Fgithub.com\u002Fvibbs\u002Fcompany-os\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fcrlf-comments\u002FSKILL.md",[],[78,79,80,62],"crlf comments","CRLF","windows",{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":24},"01M6CTH6TBKTDP9G8QB1Z2K0TY","claude-fields","Fixture skill using top-level fields Claude Code documents.","https:\u002F\u002Fgithub.com\u002Fvibbs\u002Fcompany-os\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fclaude-fields\u002FSKILL.md",[],[88,89,90,91,92,93,62,94,95,96],"claude fields","explore","documents","src","grep","read","Bash","code","testing",{"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":108,"publishedAt":24},"01M6CTH46BGKXH80RWS876Y2CW","workflow-router","Maps an objective to the artifacts, stages and agents it needs. Use when deciding what happens next or which agents to involve.","https:\u002F\u002Fgithub.com\u002Fvibbs\u002Fcompany-os\u002Fblob\u002Fmain\u002Fos\u002Fskills\u002Fworkflow-router\u002FSKILL.md",[103],{"categoryNo":104,"categoryName":105,"taxonomyType":106,"taxonomyTypeDesc":107},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[109,110,111,112,113,22,114],"workflow","router","workflow router","next","maps","artifacts",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":24},"01M6CTH27653SRVP2FMEQN3J5B","weekly-review","Summarizes your week: what shipped, AI spend, support themes, security health and next priorities. Use at the end of each week.","https:\u002F\u002Fgithub.com\u002Fvibbs\u002Fcompany-os\u002Fblob\u002Fmain\u002Fos\u002Fskills\u002Fweekly-review\u002FSKILL.md",[],[122,123,124,112,22,125,126,127,128],"weekly review","review","priorities","health","save","support","security"]