[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M718NA8DMBM58M4TRTA4K9D6":3,"skill-same:01M718NA8DMBM58M4TRTA4K9D6":72},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":6,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":6,"updatedAt":57,"install":58,"resources":71},"01M718NA8DMBM58M4TRTA4K9D6","synthesize-research",null,"Synthesize user research from interviews, surveys, and feedback into structured insights. Use when you have a pile of interview notes, survey responses, or support tickets to make sense of, need to extract themes and rank findings by frequency and impact, or want to turn raw feedback into roadmap recommendations.","anthropics\u002Fknowledge-work-plugins","anthropics","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F76263028?v=4","01M697XGDPXJAVQ8391V2BCYTE","Anthropic","01M7188MPC48111TN566QNQE3X",35656,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fproduct-management\u002Fskills\u002Fsynthesize-research\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"synthesize research","research","synthesize","use","feedback","interview","make","interviews","recommendations","support","notes","you","when","roadmap","impact","themes","question","insights","survey","user research","2026-11-10 10:12:30",false,"---\nname: synthesize-research\ndescription: Synthesize user research from interviews, surveys, and feedback into structured insights. Use when you have a pile of interview notes, survey responses, or support tickets to make sense of, need to extract themes and rank findings by frequency and impact, or want to turn raw feedback into roadmap recommendations.\nargument-hint: \"\u003Cresearch topic or question>\"\n---\n\n# Synthesize Research\n\n> If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](..\u002F..\u002FCONNECTORS.md).\n\nSynthesize user research from multiple sources into structured insights and recommendations.\n\n## Usage\n\n```\n\u002Fsynthesize-research $ARGUMENTS\n```\n\n## Workflow\n\n### 1. Gather Research Inputs\n\nAccept research from any combination of:\n- **Pasted text**: Interview notes, transcripts, survey responses, feedback\n- **Uploaded files**: Research documents, spreadsheets, recordings summaries\n- **~~knowledge base** (if connected): Search for research documents, interview notes, survey results\n- **~~user feedback** (if connected): Pull recent support tickets, feature requests, bug reports\n- **~~product analytics** (if connected): Pull usage data, funnel metrics, behavioral data\n- **~~meeting transcription** (if connected): Pull interview recordings, meeting summaries, and discussion notes\n\nAsk the user what they have:\n- What type of research? (interviews, surveys, usability tests, analytics, support tickets, sales call notes)\n- How many sources \u002F participants?\n- Is there a specific question or hypothesis they are investigating?\n- What decisions will this research inform?\n\n### 2. Process the Research\n\nFor each source, extract:\n- **Key observations**: What did users say, do, or experience?\n- **Quotes**: Verbatim quotes that illustrate important points\n- **Behaviors**: What users actually did (vs what they said they do)\n- **Pain points**: Frustrations, workarounds, and unmet needs\n- **Positive signals**: What works well, moments of delight\n- **Context**: User segment, use case, experience level\n\n### 3. Identify Themes and Patterns\n\nApply thematic analysis — see **Research Synthesis Methodology** below for detailed guidance on thematic analysis, affinity mapping, and triangulation techniques.\n\nGroup observations into themes, count frequency across participants, and assess impact severity. Note contradictions and surprises.\n\nCreate a priority matrix:\n- **High frequency + High impact**: Top priority findings\n- **Low frequency + High impact**: Important for specific segments\n- **High frequency + Low impact**: Quality-of-life improvements\n- **Low frequency + Low impact**: Note but deprioritize\n\n### 4. Generate the Synthesis\n\nProduce a structured research synthesis:\n\n#### Research Overview\n- Methodology: what types of research, how many participants\u002Fsources\n- Research question(s): what we set out to learn\n- Timeframe: when the research was conducted\n\n#### Key Findings\nFor each major finding (aim for 5-8):\n- **Finding statement**: One clear sentence describing the insight\n- **Evidence**: Supporting quotes, data points, or observations (with source attribution)\n- **Frequency**: How many participants\u002Fsources support this finding\n- **Impact**: How significantly this affects the user experience or business\n- **Confidence level**: High (strong evidence), Medium (suggestive), Low (early signal)\n\nOrder findings by priority (frequency x impact).\n\n#### User Segments \u002F Personas\nIf the research reveals distinct user segments:\n- Segment name and description\n- Key characteristics and behaviors\n- Unique needs and pain points\n- Size estimate if data is available\n\n#### Opportunity Areas\nBased on the findings, identify opportunity areas:\n- What user needs are unmet or underserved\n- Where do current solutions fall short\n- What new capabilities would unlock value\n- Prioritized by potential impact\n\n#### Recommendations\nSpecific, actionable recommendations:\n- What to build, change, or investigate further\n- Tied back to specific findings\n- Prioritized by impact and feasibility\n\n#### Open Questions\nWhat the research did not answer:\n- Gaps in understanding\n- Areas needing further investigation\n- Suggested follow-up research methods\n\n### 5. Review and Extend\n\nAfter generating the synthesis:\n- Ask if any findings need more detail or different framing\n- Offer to generate specific artifacts: persona documents, opportunity maps, research presentations\n- Offer to create follow-up research plans for open questions\n- Offer to draft product implications (how findings should influence the roadmap)\n\n## Research Synthesis Methodology\n\n### Thematic Analysis\nThe core method for synthesizing qualitative research:\n\n1. **Familiarization**: Read through all the data. Get a feel for the overall landscape before coding anything.\n2. **Initial coding**: Go through the data systematically. Tag each observation, quote, or data point with descriptive codes. Be generous with codes — it is easier to merge than to split later.\n3. **Theme development**: Group related codes into candidate themes. A theme captures something important about the data in relation to the research question.\n4. **Theme review**: Check themes against the data. Does each theme have sufficient evidence? Are themes distinct from each other? Do they tell a coherent story?\n5. **Theme refinement**: Define and name each theme clearly. Write a 1-2 sentence description of what each theme captures.\n6. **Report**: Write up the themes as findings with supporting evidence.\n\n### Affinity Mapping\nA collaborative method for grouping observations:\n\n1. **Capture observations**: Write each distinct observation, quote, or data point as a separate note\n2. **Cluster**: Group related notes together based on similarity. Do not pre-define categories — let them emerge from the data.\n3. **Label clusters**: Give each cluster a descriptive name that captures the common thread\n4. **Organize clusters**: Arrange clusters into higher-level groups if patterns emerge\n5. **Identify themes**: The clusters and their relationships reveal the key themes\n\n**Tips for affinity mapping**:\n- One observation per note. Do not combine multiple insights.\n- Move notes between clusters freely. The first grouping is rarely the best.\n- If a cluster gets too large, it probably contains multiple themes. Split it.\n- Outliers are interesting. Do not force every observation into a cluster.\n- The process of grouping is as valuable as the output. It builds shared understanding.\n\n### Triangulation\nStrengthen findings by combining multiple data sources:\n\n- **Methodological triangulation**: Same question, different methods (interviews + survey + analytics)\n- **Source triangulation**: Same method, different participants or segments\n- **Temporal triangulation**: Same observation at different points in time\n\nA finding supported by multiple sources and methods is much stronger than one supported by a single source. When sources disagree, that is interesting — it may reveal different user segments or contexts.\n\n## Interview Note Analysis\n\n### Extracting Insights from Interview Notes\nFor each interview, identify:\n\n**Observations**: What did the participant describe doing, experiencing, or feeling?\n- Distinguish between behaviors (what they do) and attitudes (what they think\u002Ffeel)\n- Note context: when, where, with whom, how often\n- Flag workarounds — these are unmet needs in disguise\n\n**Direct quotes**: Verbatim statements that powerfully illustrate a point\n- Good quotes are specific and vivid, not generic\n- Attribute to participant type, not name: \"Enterprise admin, 200-person team\" not \"Sarah\"\n- A quote is evidence, not a finding. The finding is your interpretation of what the quote means.\n\n**Behaviors vs stated preferences**: What people DO often differs from what they SAY they want\n- Behavioral observations are stronger evidence than stated preferences\n- If a participant says \"I want feature X\" but their workflow shows they never use similar features, note the contradiction\n- Look for revealed preferences through actual behavior\n\n**Signals of intensity**: How much does this matter to the participant?\n- Emotional language: frustration, excitement, resignation\n- Frequency: how often do they encounter this issue\n- Workarounds: how much effort do they expend working around the problem\n- Impact: what is the consequence when things go wrong\n\n### Cross-Interview Analysis\nAfter processing individual interviews:\n- Look for patterns: which observations appear across multiple participants?\n- Note frequency: how many participants mentioned each theme?\n- Identify segments: do different types of users have different patterns?\n- Surface contradictions: where do participants disagree? This often reveals meaningful segments.\n- Find surprises: what challenged your prior assumptions?\n\n## Survey Data Interpretation\n\n### Quantitative Survey Analysis\n- **Response rate**: How representative is the sample? Low response rates may introduce bias.\n- **Distribution**: Look at the shape of responses, not just averages. A bimodal distribution (lots of 1s and 5s) tells a different story than a normal distribution (lots of 3s).\n- **Segmentation**: Break down responses by user segment. Aggregates can mask important differences.\n- **Statistical significance**: For small samples, be cautious about drawing conclusions from small differences.\n- **Benchmark comparison**: How do scores compare to industry benchmarks or previous surveys?\n\n### Open-Ended Survey Response Analysis\n- Treat open-ended responses like mini interview notes\n- Code each response with themes\n- Count frequency of themes across responses\n- Pull representative quotes for each theme\n- Look for themes that appear in open-ended responses but not in structured questions — these are things you did not think to ask about\n\n### Common Survey Analysis Mistakes\n- Reporting averages without distributions. A 3.5 average could mean everyone is lukewarm or half love it and half hate it.\n- Ignoring non-response bias. The people who did not respond may be systematically different.\n- Over-interpreting small differences. A 0.1 point change in NPS is noise, not signal.\n- Treating Likert scales as interval data. The difference between \"Strongly Agree\" and \"Agree\" is not necessarily the same as between \"Agree\" and \"Neutral.\"\n- Confusing correlation with causation in cross-tabulations.\n\n## Combining Qualitative and Quantitative Insights\n\n### The Qual-Quant Feedback Loop\n- **Qualitative first**: Interviews and observation reveal WHAT is happening and WHY. They generate hypotheses.\n- **Quantitative validation**: Surveys and analytics reveal HOW MUCH and HOW MANY. They test hypotheses at scale.\n- **Qualitative deep-dive**: Return to qualitative methods to understand unexpected quantitative findings.\n\n### Integration Strategies\n- Use quantitative data to prioritize qualitative findings. A theme from interviews is more important if usage data shows it affects many users.\n- Use qualitative data to explain quantitative anomalies. A drop in retention is a number; interviews reveal it is because of a confusing onboarding change.\n- Present combined evidence: \"47% of surveyed users report difficulty with X (survey), and interviews reveal this is because Y (qualitative finding).\"\n\n### When Sources Disagree\n- Quantitative and qualitative sources may tell different stories. This is signal, not error.\n- Check if the disagreement is due to different populations being measured\n- Check if stated preferences (survey) differ from actual behavior (analytics)\n- Check if the quantitative question captured what you think it captured\n- Report the disagreement honestly and investigate further rather than choosing one source\n\n## Persona Development from Research\n\n### Building Evidence-Based Personas\nPersonas should emerge from research data, not imagination:\n\n1. **Identify behavioral patterns**: Look for clusters of similar behaviors, goals, and contexts across participants\n2. **Define distinguishing variables**: What dimensions differentiate one cluster from another? (e.g., company size, technical skill, usage frequency, primary use case)\n3. **Create persona profiles**: For each behavioral cluster:\n   - Name and brief description\n   - Key behaviors and goals\n   - Pain points and needs\n   - Context (role, company, tools used)\n   - Representative quotes\n4. **Validate with data**: Can you size each persona segment using quantitative data?\n\n### Persona Template\n```\n[Persona Name] — [One-line description]\n\nWho they are:\n- Role, company type\u002Fsize, experience level\n- How they found\u002Fstarted using the product\n\nWhat they are trying to accomplish:\n- Primary goals and jobs to be done\n- How they measure success\n\nHow they use the product:\n- Frequency and depth of usage\n- Key workflows and features used\n- Tools they use alongside this product\n\nKey pain points:\n- Top 3 frustrations or unmet needs\n- Workarounds they have developed\n\nWhat they value:\n- What matters most in a solution\n- What would make them switch or churn\n\nRepresentative quotes:\n- 2-3 verbatim quotes that capture this persona's perspective\n```\n\n### Common Persona Mistakes\n- Demographic personas: defining by age\u002Fgender\u002Flocation instead of behavior. Behavior predicts product needs better than demographics.\n- Too many personas: 3-5 is the sweet spot. More than that and they are not actionable.\n- Fictional personas: made up based on assumptions rather than research data.\n- Static personas: never updated as the product and market evolve.\n- Personas without implications: a persona that does not change any product decisions is not useful.\n\n## Opportunity Sizing\n\n### Estimating Opportunity Size\nFor each research finding or opportunity area, estimate:\n\n- **Addressable users**: How many users could benefit from addressing this? Use product analytics, survey data, or market data to estimate.\n- **Frequency**: How often do affected users encounter this issue? (Daily, weekly, monthly, one-time)\n- **Severity**: How much does this issue impact users when it occurs? (Blocker, significant friction, minor annoyance)\n- **Willingness to pay**: Would addressing this drive upgrades, retention, or new customer acquisition?\n\n### Opportunity Scoring\nScore opportunities on a simple matrix:\n\n- **Impact**: (Users affected) x (Frequency) x (Severity) = impact score\n- **Evidence strength**: How confident are we in the finding? (Multiple sources > single source, behavioral data > stated preferences)\n- **Strategic alignment**: Does this opportunity align with company strategy and product vision?\n- **Feasibility**: Can we realistically address this? (Technical feasibility, resource availability, time to impact)\n\n### Presenting Opportunity Sizing\n- Be transparent about assumptions and confidence levels\n- Show the math: \"Based on support ticket volume, approximately 2,000 users per month encounter this issue. Interview data suggests 60% of them consider it a significant blocker.\"\n- Use ranges rather than false precision: \"This affects 1,500-2,500 users monthly\" not \"This affects 2,137 users monthly\"\n- Compare opportunities against each other to create a relative ranking, not just absolute scores\n\n## Output Format\n\nUse clear headers and structured formatting. Each finding should stand on its own — a reader should be able to read any single finding and understand it without reading the rest.\n\n## Tips\n\n- Let the data speak. Do not force findings into a predetermined narrative.\n- Distinguish between what users say and what they do. Behavioral data is stronger than stated preferences.\n- Quotes are powerful evidence. Include them generously, with attribution to participant type (not name).\n- Be explicit about confidence levels. A finding from 2 interviews is a hypothesis, not a conclusion.\n- Contradictions in the data are interesting, not inconvenient. They often reveal distinct user segments.\n- Recommendations should be specific enough to act on. \"Improve onboarding\" is not actionable. \"Add a progress indicator to the setup flow\" is.\n- Resist the temptation to synthesize too many themes. 5-8 strong findings are better than 20 weak ones.\n","# Synthesize Research\n\n> If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](..\u002F..\u002FCONNECTORS.md).\n\nSynthesize user research from multiple sources into structured insights and recommendations.\n\n## Usage\n\n```\n\u002Fsynthesize-research $ARGUMENTS\n```\n\n## Workflow\n\n### 1. Gather Research Inputs\n\nAccept research from any combination of:\n- **Pasted text**: Interview notes, transcripts, survey responses, feedback\n- **Uploaded files**: Research documents, spreadsheets, recordings summaries\n- **~~knowledge base** (if connected): Search for research documents, interview notes, survey results\n- **~~user feedback** (if connected): Pull recent support tickets, feature requests, bug reports\n- **~~product analytics** (if connected): Pull usage data, funnel metrics, behavioral data\n- **~~meeting transcription** (if connected): Pull interview recordings, meeting summaries, and discussion notes\n\nAsk the user what they have:\n- What type of research? (interviews, surveys, usability tests, analytics, support tickets, sales call notes)\n- How many sources \u002F participants?\n- Is there a specific question or hypothesis they are investigating?\n- What decisions will this research inform?\n\n### 2. Process the Research\n\nFor each source, extract:\n- **Key observations**: What did users say, do, or experience?\n- **Quotes**: Verbatim quotes that illustrate important points\n- **Behaviors**: What users actually did (vs what they said they do)\n- **Pain points**: Frustrations, workarounds, and unmet needs\n- **Positive signals**: What works well, moments of delight\n- **Context**: User segment, use case, experience level\n\n### 3. Identify Themes and Patterns\n\nApply thematic analysis — see **Research Synthesis Methodology** below for detailed guidance on thematic analysis, affinity mapping, and triangulation techniques.\n\nGroup observations into themes, count frequency across participants, and assess impact severity. Note contradictions and surprises.\n\nCreate a priority matrix:\n- **High frequency + High impact**: Top priority findings\n- **Low frequency + High impact**: Important for specific segments\n- **High frequency + Low impact**: Quality-of-life improvements\n- **Low frequency + Low impact**: Note but deprioritize\n\n### 4. Generate the Synthesis\n\nProduce a structured research synthesis:\n\n#### Research Overview\n- Methodology: what types of research, how many participants\u002Fsources\n- Research question(s): what we set out to learn\n- Timeframe: when the research was conducted\n\n#### Key Findings\nFor each major finding (aim for 5-8):\n- **Finding statement**: One clear sentence describing the insight\n- **Evidence**: Supporting quotes, data points, or observations (with source attribution)\n- **Frequency**: How many participants\u002Fsources support this finding\n- **Impact**: How significantly this affects the user experience or business\n- **Confidence level**: High (strong evidence), Medium (suggestive), Low (early signal)\n\nOrder findings by priority (frequency x impact).\n\n#### User Segments \u002F Personas\nIf the research reveals distinct user segments:\n- Segment name and description\n- Key characteristics and behaviors\n- Unique needs and pain points\n- Size estimate if data is available\n\n#### Opportunity Areas\nBased on the findings, identify opportunity areas:\n- What user needs are unmet or underserved\n- Where do current solutions fall short\n- What new capabilities would unlock value\n- Prioritized by potential impact\n\n#### Recommendations\nSpecific, actionable recommendations:\n- What to build, change, or investigate further\n- Tied back to specific findings\n- Prioritized by impact and feasibility\n\n#### Open Questions\nWhat the research did not answer:\n- Gaps in understanding\n- Areas needing further investigation\n- Suggested follow-up research methods\n\n### 5. Review and Extend\n\nAfter generating the synthesis:\n- Ask if any findings need more detail or different framing\n- Offer to generate specific artifacts: persona documents, opportunity maps, research presentations\n- Offer to create follow-up research plans for open questions\n- Offer to draft product implications (how findings should influence the roadmap)\n\n## Research Synthesis Methodology\n\n### Thematic Analysis\nThe core method for synthesizing qualitative research:\n\n1. **Familiarization**: Read through all the data. Get a feel for the overall landscape before coding anything.\n2. **Initial coding**: Go through the data systematically. Tag each observation, quote, or data point with descriptive codes. Be generous with codes — it is easier to merge than to split later.\n3. **Theme development**: Group related codes into candidate themes. A theme captures something important about the data in relation to the research question.\n4. **Theme review**: Check themes against the data. Does each theme have sufficient evidence? Are themes distinct from each other? Do they tell a coherent story?\n5. **Theme refinement**: Define and name each theme clearly. Write a 1-2 sentence description of what each theme captures.\n6. **Report**: Write up the themes as findings with supporting evidence.\n\n### Affinity Mapping\nA collaborative method for grouping observations:\n\n1. **Capture observations**: Write each distinct observation, quote, or data point as a separate note\n2. **Cluster**: Group related notes together based on similarity. Do not pre-define categories — let them emerge from the data.\n3. **Label clusters**: Give each cluster a descriptive name that captures the common thread\n4. **Organize clusters**: Arrange clusters into higher-level groups if patterns emerge\n5. **Identify themes**: The clusters and their relationships reveal the key themes\n\n**Tips for affinity mapping**:\n- One observation per note. Do not combine multiple insights.\n- Move notes between clusters freely. The first grouping is rarely the best.\n- If a cluster gets too large, it probably contains multiple themes. Split it.\n- Outliers are interesting. Do not force every observation into a cluster.\n- The process of grouping is as valuable as the output. It builds shared understanding.\n\n### Triangulation\nStrengthen findings by combining multiple data sources:\n\n- **Methodological triangulation**: Same question, different methods (interviews + survey + analytics)\n- **Source triangulation**: Same method, different participants or segments\n- **Temporal triangulation**: Same observation at different points in time\n\nA finding supported by multiple sources and methods is much stronger than one supported by a single source. When sources disagree, that is interesting — it may reveal different user segments or contexts.\n\n## Interview Note Analysis\n\n### Extracting Insights from Interview Notes\nFor each interview, identify:\n\n**Observations**: What did the participant describe doing, experiencing, or feeling?\n- Distinguish between behaviors (what they do) and attitudes (what they think\u002Ffeel)\n- Note context: when, where, with whom, how often\n- Flag workarounds — these are unmet needs in disguise\n\n**Direct quotes**: Verbatim statements that powerfully illustrate a point\n- Good quotes are specific and vivid, not generic\n- Attribute to participant type, not name: \"Enterprise admin, 200-person team\" not \"Sarah\"\n- A quote is evidence, not a finding. The finding is your interpretation of what the quote means.\n\n**Behaviors vs stated preferences**: What people DO often differs from what they SAY they want\n- Behavioral observations are stronger evidence than stated preferences\n- If a participant says \"I want feature X\" but their workflow shows they never use similar features, note the contradiction\n- Look for revealed preferences through actual behavior\n\n**Signals of intensity**: How much does this matter to the participant?\n- Emotional language: frustration, excitement, resignation\n- Frequency: how often do they encounter this issue\n- Workarounds: how much effort do they expend working around the problem\n- Impact: what is the consequence when things go wrong\n\n### Cross-Interview Analysis\nAfter processing individual interviews:\n- Look for patterns: which observations appear across multiple participants?\n- Note frequency: how many participants mentioned each theme?\n- Identify segments: do different types of users have different patterns?\n- Surface contradictions: where do participants disagree? This often reveals meaningful segments.\n- Find surprises: what challenged your prior assumptions?\n\n## Survey Data Interpretation\n\n### Quantitative Survey Analysis\n- **Response rate**: How representative is the sample? Low response rates may introduce bias.\n- **Distribution**: Look at the shape of responses, not just averages. A bimodal distribution (lots of 1s and 5s) tells a different story than a normal distribution (lots of 3s).\n- **Segmentation**: Break down responses by user segment. Aggregates can mask important differences.\n- **Statistical significance**: For small samples, be cautious about drawing conclusions from small differences.\n- **Benchmark comparison**: How do scores compare to industry benchmarks or previous surveys?\n\n### Open-Ended Survey Response Analysis\n- Treat open-ended responses like mini interview notes\n- Code each response with themes\n- Count frequency of themes across responses\n- Pull representative quotes for each theme\n- Look for themes that appear in open-ended responses but not in structured questions — these are things you did not think to ask about\n\n### Common Survey Analysis Mistakes\n- Reporting averages without distributions. A 3.5 average could mean everyone is lukewarm or half love it and half hate it.\n- Ignoring non-response bias. The people who did not respond may be systematically different.\n- Over-interpreting small differences. A 0.1 point change in NPS is noise, not signal.\n- Treating Likert scales as interval data. The difference between \"Strongly Agree\" and \"Agree\" is not necessarily the same as between \"Agree\" and \"Neutral.\"\n- Confusing correlation with causation in cross-tabulations.\n\n## Combining Qualitative and Quantitative Insights\n\n### The Qual-Quant Feedback Loop\n- **Qualitative first**: Interviews and observation reveal WHAT is happening and WHY. They generate hypotheses.\n- **Quantitative validation**: Surveys and analytics reveal HOW MUCH and HOW MANY. They test hypotheses at scale.\n- **Qualitative deep-dive**: Return to qualitative methods to understand unexpected quantitative findings.\n\n### Integration Strategies\n- Use quantitative data to prioritize qualitative findings. A theme from interviews is more important if usage data shows it affects many users.\n- Use qualitative data to explain quantitative anomalies. A drop in retention is a number; interviews reveal it is because of a confusing onboarding change.\n- Present combined evidence: \"47% of surveyed users report difficulty with X (survey), and interviews reveal this is because Y (qualitative finding).\"\n\n### When Sources Disagree\n- Quantitative and qualitative sources may tell different stories. This is signal, not error.\n- Check if the disagreement is due to different populations being measured\n- Check if stated preferences (survey) differ from actual behavior (analytics)\n- Check if the quantitative question captured what you think it captured\n- Report the disagreement honestly and investigate further rather than choosing one source\n\n## Persona Development from Research\n\n### Building Evidence-Based Personas\nPersonas should emerge from research data, not imagination:\n\n1. **Identify behavioral patterns**: Look for clusters of similar behaviors, goals, and contexts across participants\n2. **Define distinguishing variables**: What dimensions differentiate one cluster from another? (e.g., company size, technical skill, usage frequency, primary use case)\n3. **Create persona profiles**: For each behavioral cluster:\n   - Name and brief description\n   - Key behaviors and goals\n   - Pain points and needs\n   - Context (role, company, tools used)\n   - Representative quotes\n4. **Validate with data**: Can you size each persona segment using quantitative data?\n\n### Persona Template\n```\n[Persona Name] — [One-line description]\n\nWho they are:\n- Role, company type\u002Fsize, experience level\n- How they found\u002Fstarted using the product\n\nWhat they are trying to accomplish:\n- Primary goals and jobs to be done\n- How they measure success\n\nHow they use the product:\n- Frequency and depth of usage\n- Key workflows and features used\n- Tools they use alongside this product\n\nKey pain points:\n- Top 3 frustrations or unmet needs\n- Workarounds they have developed\n\nWhat they value:\n- What matters most in a solution\n- What would make them switch or churn\n\nRepresentative quotes:\n- 2-3 verbatim quotes that capture this persona's perspective\n```\n\n### Common Persona Mistakes\n- Demographic personas: defining by age\u002Fgender\u002Flocation instead of behavior. Behavior predicts product needs better than demographics.\n- Too many personas: 3-5 is the sweet spot. More than that and they are not actionable.\n- Fictional personas: made up based on assumptions rather than research data.\n- Static personas: never updated as the product and market evolve.\n- Personas without implications: a persona that does not change any product decisions is not useful.\n\n## Opportunity Sizing\n\n### Estimating Opportunity Size\nFor each research finding or opportunity area, estimate:\n\n- **Addressable users**: How many users could benefit from addressing this? Use product analytics, survey data, or market data to estimate.\n- **Frequency**: How often do affected users encounter this issue? (Daily, weekly, monthly, one-time)\n- **Severity**: How much does this issue impact users when it occurs? (Blocker, significant friction, minor annoyance)\n- **Willingness to pay**: Would addressing this drive upgrades, retention, or new customer acquisition?\n\n### Opportunity Scoring\nScore opportunities on a simple matrix:\n\n- **Impact**: (Users affected) x (Frequency) x (Severity) = impact score\n- **Evidence strength**: How confident are we in the finding? (Multiple sources > single source, behavioral data > stated preferences)\n- **Strategic alignment**: Does this opportunity align with company strategy and product vision?\n- **Feasibility**: Can we realistically address this? (Technical feasibility, resource availability, time to impact)\n\n### Presenting Opportunity Sizing\n- Be transparent about assumptions and confidence levels\n- Show the math: \"Based on support ticket volume, approximately 2,000 users per month encounter this issue. Interview data suggests 60% of them consider it a significant blocker.\"\n- Use ranges rather than false precision: \"This affects 1,500-2,500 users monthly\" not \"This affects 2,137 users monthly\"\n- Compare opportunities against each other to create a relative ranking, not just absolute scores\n\n## Output Format\n\nUse clear headers and structured formatting. Each finding should stand on its own — a reader should be able to read any single finding and understand it without reading the rest.\n\n## Tips\n\n- Let the data speak. Do not force findings into a predetermined narrative.\n- Distinguish between what users say and what they do. Behavioral data is stronger than stated preferences.\n- Quotes are powerful evidence. Include them generously, with attribution to participant type (not name).\n- Be explicit about confidence levels. A finding from 2 interviews is a hypothesis, not a conclusion.\n- Contradictions in the data are interesting, not inconvenient. They often reveal distinct user segments.\n- Recommendations should be specific enough to act on. \"Improve onboarding\" is not actionable. \"Add a progress indicator to the setup flow\" is.\n- Resist the temptation to synthesize too many themes. 5-8 strong findings are better than 20 weak ones.\n",{"name":5,"description":7,"argument-hint":49},"\u003Cresearch topic or question>","main","e605d8ddbfb688da57dfaaceebd93f12a64ef1d3","product-management\u002Fskills\u002Fsynthesize-research",3945,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins","https:\u002F\u002Fgithub.com\u002Fanthropics","https:\u002F\u002Fanthropic.com","2026-11-13 23:29:50",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add anthropics\u002Fknowledge-work-plugins --skill synthesize-research",{"tool":64,"command":65},"bunx","bunx skills add anthropics\u002Fknowledge-work-plugins --skill synthesize-research",{"tool":67,"command":68},"pnpm","pnpm dlx skills add anthropics\u002Fknowledge-work-plugins --skill synthesize-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fproduct-management\u002Fskills\u002Fsynthesize-research\u002FSKILL.md",true,[],[73,98,123,145,174,200],{"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":44},"01M718Y97HCGW12Q53PSJDY03W","ticket-deflector","Reads a forwarded customer email or ticket, pulls order and refund status from a payments connector (PayPal, Square, or Stripe) or Shopify, account history from the CRM, and open tickets from a support desk (Zoho Desk), drafts a tone-matched reply in the owner's writing voice, and can issue a refund through the payments connector with explicit owner approval. With Shopify connected it also runs a proactive order-triage mode that surfaces orders needing attention — unfulfilled past the promised window, payment problems, pending refunds, stuck shipments — and drafts the next action for each before the customer has to ask. Use when the user says \"draft a response,\" \"answer this customer,\" \"where's my order,\" \"I want a refund,\" \"check my orders,\" or \"anything about to blow up.\"","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fsmall-business\u002Fskills\u002Fticket-deflector\u002FSKILL.md",[],[80,81,82,83,84,85,86,36,87,88,89,90,91,92,93,94,33,95,96,97],"ticket","ticket deflector","mode","up","payments","open","writing","workflow","ask","Connector","text","mail","window","next","customer","crm","past","read",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":44},"01M718Y55HFAN5705ME5VEDZ9K","tax-season-organizer","Prepares tax-season materials for the owner's accountant, not tax advice. US federal tax; a non-US business gets its closed-books packet instead. Two modes: (1) quarterly estimated tax from YTD net income in the ledger (MYOB, NetSuite, QuickBooks, Xero, or Zoho Books); (2) year-end 1099 prep, scanning the ledger, PayPal, and Stripe for contractors paid over USD 600 into a 1099-NEC list with missing W-9 flags.\nAny tax request routes first to \u002Ftax-prep, which confirms the books are closed and reconciled before running this skill. Use this skill directly only when the owner says the period's books are already closed: \"books are closed, now do the 1099s,\" \"run the quarterly estimate off the closed numbers,\" or \"just the contractor W-9 list.\"","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fsmall-business\u002Fskills\u002Ftax-season-organizer\u002FSKILL.md",[],[105,106,107,108,109,110,111,112,113,114,36,115,116,117,118,119,97,120,121,122],"tax season organizer","tax","us federal","which","netsuite","paid","end","usd","only","now","books","xero","scanning","run","request","flags","list","stripe",{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":44},"01M718Y13VVPHDD9NTDBVFJ2AZ","tax-prep","Prepares tax materials as a two-link chain — month-end-prep confirms the books are closed and reconciled first, then tax-season-organizer calculates the quarterly estimated payment or builds the year-end 1099-NEC list and accountant packet from those closed numbers. Requires a ledger (MYOB, NetSuite, QuickBooks, Xero, or Zoho Books); uses Gusto, PayPal, and Stripe when connected, else CSV upload. US federal tax math; a non-US business gets the closed-books packet. Prep material for a CPA, never tax advice, nothing filed. Trigger on \"quarterly taxes,\" \"estimated tax payment,\" \"how much should I set aside,\" \"1099s,\" \"1099-NEC,\" \"W-9s,\" \"year-end tax prep,\" \"get my books ready for my accountant,\" any phrasing that suggests a tax deadline is coming, or a question about net profit or YTD income that sounds like worry about a tax bill. An owner who says the period's books are already closed routes to tax-season-organizer directly.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fsmall-business\u002Fskills\u002Ftax-prep\u002FSKILL.md",[],[130,106,131,132,107,133,134,109,135,136,137,138,139,140,141,111,142,40,143,144],"tax prep","prep","SET","as","ready","never","zoho books","get","chain","profit","for","trigger","material","paypal","business",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":156,"publishedAt":44},"01M718XWTWQZ01GYSG9T8RW8TW","speed-to-lead","Makes sure no inbound lead goes unanswered. Watches web forms, the shared inbox, and the CRM for new inquiries, qualifies each one against the owner's criteria, drafts a reply in the owner's voice with real meeting times for the owner to approve and send, routes anything hot to a human right away, and logs the whole thing to the CRM. Never sends on its own. Built to run on a schedule so overnight inquiries are drafted and sorted by morning, and works from forwarded or pasted inquiries when no connector is available. Use this whenever the owner is worried about inbound leads or response time — including phrasings like \"leads are going cold,\" \"did anyone answer that inquiry,\" \"I keep missing form submissions,\" \"nothing falls through the cracks,\" \"handle my inbound,\" \"respond to this lead,\" or \"we lose people because nobody gets back fast enough.\" Reach for it for a single unanswered inquiry as readily as for a standing setup.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fsmall-business\u002Fskills\u002Fspeed-to-lead\u002FSKILL.md",[151],{"categoryNo":152,"categoryName":153,"taxonomyType":154,"taxonomyTypeDesc":155},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[157,158,159,160,161,162,135,163,164,165,166,167,168,169,36,170,171,89,172,173],"speed to lead","lead","speed","shared","back","cold","time","inbox","send","respond","new","web forms","people","schedule","logs","sure","human",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":183,"publishedAt":44},"01M718XQYMN1KY3TPS33967FK0","social-content-engine","Runs the owner's content operation as a standing thing rather than a one-off: keeps a rolling posting calendar, learns the owner's voice, generates on-brand Canva graphics, writes captions that sound like them, repurposes one asset into every channel format, and stages posts for approval instead of publishing on its own. Pulls product photos and prices from Shopify when connected; with no connectors, drafts the calendar and asset briefs for manual posting. Use this whenever the owner talks about posting, content, or social — including \"I need to post more,\" \"we've gone quiet on Instagram,\" \"what should we post this month,\" \"make the content,\" \"give me a month of posts,\" \"write this in my voice,\" \"repurpose this,\" or \"set up our content calendar.\" Reach for it for a single post as readily as for a full quarter. One handoff: a finished, approved campaign brief goes to canva-creator; this skill owns the standing operation.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fsmall-business\u002Fskills\u002Fsocial-content-engine\u002FSKILL.md",[180],{"categoryNo":181,"categoryName":182,"taxonomyType":154,"taxonomyTypeDesc":155},"01JBSEEDCAT000000000000036","内容创作者",[184,185,186,187,188,189,132,190,191,192,193,83,194,36,195,196,197,97,198,199],"social","social content engine","engine","content engine","social content","content","brief","posts","Captions","prices","campaign","me","product","calendar","write","drafts",{"skillNo":201,"name":202,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":206,"publishedAt":44},"01M718XMPJVH0EVRVP998BVZPC","smb-router","The front door to the Small Business plugin. Listens to what the owner needs right now — vague or specific — and routes them to the best skill or slash command for the moment. Also serves as a guide: explains what's available, suggests what to try next, and adapts recommendations based on stored business context. Trigger whenever the owner asks \"what can you do,\" \"help me with my business,\" \"what should I focus on,\" \"I don't know where to start,\" or any open-ended business request that doesn't clearly match a single skill.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Fblob\u002Fmain\u002Fsmall-business\u002Fskills\u002Fsmb-router\u002FSKILL.md",[],[207,208,209,133,210,140,141,211,85,212,114,144,35,213,214,215,216,195,217,93],"router","smb","smb router","do","front","single","vague","can","with","plugin","focus"]