[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69A0JBPPHWJST4HMRCDZMY8":3,"skill-same:01M69A0JBPPHWJST4HMRCDZMY8":59},{"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":27,"linkOnly":28,"markdownContent":29,"markdownBody":30,"frontMatter":31,"refName":36,"commitSha":37,"skillDirectory":38,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":42,"ownerDescription":43,"updatedAt":44,"install":45,"resources":58},"01M69A0JBPPHWJST4HMRCDZMY8","competitive-intelligence",null,"Analyzes opportunity data and activity notes to generate competitive intelligence including win\u002Floss rates by competitor, patterns, and rep-ready battlecard talking points. Use when user asks \"how are we doing against [competitor]\", \"competitive analysis\", \"competitor win rate\", \"battlecard for [competitor]\", \"competitive landscape\", \"why are we losing to [competitor]\", or \"competitor intelligence\".","microsoft\u002Fdataverse-business-skills","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M69A0CN12Y1G6WKSVKNHX60T",54,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fdataverse-business-skills\u002Fblob\u002Fmain\u002Fskills\u002Fcompetitive-intelligence\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[24,25,26],"competitive intelligence","dataverse","analytics","2026-11-10 10:12:30",false,"---\nname: competitive-intelligence\ndescription: Analyzes opportunity data and activity notes to generate competitive intelligence including win\u002Floss rates by competitor, patterns, and rep-ready battlecard talking points. Use when user asks \"how are we doing against [competitor]\", \"competitive analysis\", \"competitor win rate\", \"battlecard for [competitor]\", \"competitive landscape\", \"why are we losing to [competitor]\", or \"competitor intelligence\".\nmetadata:\n  author: Dataverse\n  version: 1.0.0\n  category: sales-analytics\n---\n\n# Competitive Intelligence\n\nCompetitive insights are often locked in deal notes, lost opportunity records, and anecdotal rep knowledge. This skill mines Dataverse to surface structured competitive intelligence: which competitors appear most frequently, where deals are being lost to them, what deal patterns correlate with wins vs losses, and what talking points reps should use. This is the Dataverse-internal equivalent of competitive research — drawing from closed deal history rather than external sources.\n\n## Instructions\n\n### Step 1: Identify Competitor or Analysis Scope\nAccept input from the user:\n- **Specific competitor name** (to analyze one rival)\n- **All competitors** (for a full competitive landscape view)\n- **Time range** (default: last 12 months)\n- **Segment filter** (by owner, territory, deal size, or industry)\n\nCalculate date range for analysis: `createdon >= '[start_date]'`\n\n#### Step 2: Identify Lost Deals with Competitor Information\n\n**Important:** The `opportunity` entity does not have a direct `competitorid` field — the opportunity-to-competitor relationship is many-to-many (`opportunitycompetitors_association`). When an opportunity is closed, Dynamics 365 creates an `opportunityclose` activity record which **does** have a direct `competitorid` lookup. Use `opportunityclose` for structured competitor data on closed deals.\n\n**Query closed-lost opportunityclose records:**\n```\nSELECT oc.opportunityid, oc.competitorid, oc.description, oc.createdon,\n       oc.actualrevenue\nFROM opportunityclose oc\nWHERE oc.statecode = 1\nAND oc.createdon >= '[start_date]'\nORDER BY oc.createdon DESC\n```\n\nThen join to the `opportunity` table by `opportunityid` to get deal details:\n```\nSELECT opportunityid, name, estimatedvalue, actualclosedate, salesstage,\n       description, ownerid, customerid, closeprobability\nFROM opportunity\nWHERE statecode = 2\nAND actualclosedate >= '[start_date]'\nORDER BY actualclosedate DESC\n```\n\n**Note:** If `opportunityclose` is not populated (competitor not selected at close), fall back to text pattern matching in opportunity description fields as described in Step 3.\n\n**Fetch competitor names if competitor table is used:**\n```\nSELECT competitorid, name, websiteurl, overview, strengths, weaknesses,\n       opportunitiescomments, threatscomments\nFROM competitor\n```\n\n#### Step 3: Mine Opportunity Descriptions for Competitor Mentions\nFor opportunities without structured competitor fields, search text fields for competitor names:\n```\nSELECT opportunityid, name, estimatedvalue, statecode, actualclosedate,\n       salesstage, description, currentsituation, customerneed, customerpainpoints\nFROM opportunity\nWHERE statecode IN (1, 2)\nAND actualclosedate >= '[start_date]'\n```\n\nSearch description, currentsituation, and customerpainpoints for known competitor keywords or names provided by the user. Categorize each mention as:\n- Win with competitor present (statecode = 1)\n- Loss to competitor (statecode = 2)\n\n#### Step 4: Pull Competitor Annotations from Activities\nSearch activity notes for competitor mentions:\n```\nSELECT annotationid, notetext, subject, objectid, createdon\nFROM annotation\nWHERE createdon >= '[start_date]'\n```\n\nSearch notetext for competitor name patterns. Extract:\n- Context of mention (evaluation, objection, price comparison)\n- Outcome (linked opportunity won or lost)\n- Frequency of mention\n\nAlso search phonecall and appointment descriptions:\n```\nSELECT activityid, subject, description, regardingobjectid, statecode\nFROM phonecall\nWHERE createdon >= '[start_date]'\n```\n\n#### Step 5: Calculate Win\u002FLoss Rates by Competitor\n\nFrom Step 2, you now have two lists of opportunityids: `[lost_opportunityids]` (from `opportunityclose` where `competitorid` matches and deal was lost) and `[won_opportunityids]` (from a separate `opportunityclose` query for won deals). Run an additional query to capture won opportunityclose records for this competitor:\n\n```\nSELECT oc.opportunityid, oc.createdon, oc.actualrevenue\nFROM opportunityclose oc\nWHERE oc.competitorid = '[competitorid]'\nAND oc.createdon >= '[start_date]'\n```\n\nCross-reference these opportunityids against `opportunity.statecode` to split into won vs lost buckets. Then aggregate:\n\n**Won opportunities where competitor was present:**\n```\nSELECT COUNT(opportunityid) as won_count, SUM(estimatedvalue) as won_value\nFROM opportunity\nWHERE statecode = 1\nAND actualclosedate >= '[start_date]'\n```\nFilter results programmatically to only those opportunityids found in the won opportunityclose results above.\n\n**Lost opportunities to competitor:**\n```\nSELECT COUNT(opportunityid) as lost_count, SUM(estimatedvalue) as lost_value\nFROM opportunity\nWHERE statecode = 2\nAND actualclosedate >= '[start_date]'\n```\nFilter results programmatically to only those opportunityids in `[lost_opportunityids]` from Step 2.\n\nCalculate:\n- **Win rate** = won_count \u002F (won_count + lost_count) × 100\n- **Average deal size (wins)** vs **average deal size (losses)**\n- **Average sales cycle (wins)** vs **average sales cycle (losses)**\n\n#### Step 6: Identify Deal Patterns\n\nFor won deals with competitor present vs lost deals to competitor, compare:\n\n**Deal size distribution:**\n```\nSELECT COUNT(opportunityid) as count, SUM(estimatedvalue) as total_value\nFROM opportunity\nWHERE statecode = 1\nAND estimatedvalue \u003C 25000\n```\nFilter results programmatically to only those opportunityids in `[won_opportunityids]`. Repeat for medium ($25K-$100K) and enterprise (>$100K) segments; run equivalent queries for `statecode = 2` filtered to `[lost_opportunityids]`.\n\n**Industry distribution:**\n```\nSELECT account.industrycode, COUNT(opportunity.opportunityid) as count\nFROM opportunity\nJOIN account ON opportunity.customerid = account.accountid\nWHERE opportunity.statecode = 2\nAND opportunity.actualclosedate >= '[start_date]'\nGROUP BY account.industrycode\n```\nFilter results programmatically to only those opportunityids in `[lost_opportunityids]` from Step 2.\n\n**Stage at loss:**\n```\nSELECT salesstage, COUNT(opportunityid) as lost_count, SUM(estimatedvalue) as lost_value\nFROM opportunity\nWHERE statecode = 2\nAND actualclosedate >= '[start_date]'\nGROUP BY salesstage\n```\nFilter results programmatically to only those opportunityids in `[lost_opportunityids]` from Step 2.\n\n#### Step 7: Identify Common Objections and Pain Points\nFrom text mining in Step 4, categorize recurring themes from notes and activity descriptions when competitor is mentioned:\n- **Price objections:** Look for \"cheaper\", \"lower cost\", \"price\", \"pricing\"\n- **Feature gaps:** Look for \"missing\", \"doesn't support\", \"can't do\", \"limitation\"\n- **Existing relationship:** Look for \"incumbent\", \"already using\", \"switching cost\", \"prefer\"\n- **Brand recognition:** Look for \"heard of\", \"well-known\", \"trusted\", \"market leader\"\n- **Implementation concerns:** Look for \"complex\", \"timeline\", \"integration\", \"support\"\n\nCount frequency of each theme across deal notes.\n\n#### Step 8: Extract Win Patterns\nFor won deals where this competitor was present, identify common factors:\n\n**Qualification strength in wins:**\n```\nSELECT budgetstatus, decisionmaker, need, purchasetimeframe, purchaseprocess,\n       COUNT(opportunityid) as count\nFROM opportunity\nWHERE statecode = 1\nAND actualclosedate >= '[start_date]'\nGROUP BY budgetstatus, decisionmaker, need, purchasetimeframe, purchaseprocess\n```\nFilter results programmatically to only those opportunityids in `[won_opportunityids]` from Step 5.\n\nNote which BANT patterns appear most often in wins — these inform the competitive playbook.\n\n**Activity volume in wins vs losses:**\nCount total activities per opportunity for wins and losses separately using activitypointer to identify engagement differences.\n\n#### Step 9: Generate Competitive Intelligence Report\n\n```\nCOMPETITIVE INTELLIGENCE REPORT\nCompetitor: [Competitor Name]\nPeriod: [Start Date] – [End Date]\nGenerated: [Today's Date]\n═══════════════════════════════════════════════════════════\n\nEXECUTIVE SUMMARY\n───────────────────────────────────────────────────────────\nDeals Analyzed: [n won] wins \u002F [n lost] losses\nWin Rate (competitive): [n]%\nRevenue Won (competitive): $[value]\nRevenue Lost to Competitor: $[value]\n\nCOMPETITIVE PERFORMANCE BY DEAL SIZE\n───────────────────────────────────────────────────────────\nSmall (\u003C$25K):     Win rate [n]%  | [n] won, [n] lost\nMedium ($25K-$100K): Win rate [n]% | [n] won, [n] lost\nEnterprise (>$100K): Win rate [n]% | [n] won, [n] lost\n\nWHERE WE LOSE\n───────────────────────────────────────────────────────────\nMost losses occur at: [Stage] stage ([n]% of losses)\nTop industries lost: [Industry 1] ([n] deals), [Industry 2] ([n] deals)\nAverage deal size lost: $[value] vs average deal size won: $[value]\n\nCOMMON OBJECTIONS (from deal notes)\n───────────────────────────────────────────────────────────\n1. Price\u002FCost concerns — mentioned in [n]% of lost deals\n2. [Feature gap] — mentioned in [n]% of lost deals\n3. [Incumbent relationship] — mentioned in [n]% of lost deals\n\nWIN PATTERNS (what works in competitive deals)\n───────────────────────────────────────────────────────────\n✓ Economic buyer engaged: [n]% of wins vs [n]% of losses\n✓ Budget confirmed before Propose: [n]% of wins vs [n]% of losses\n✓ Higher activity volume: [n] avg activities (wins) vs [n] (losses)\n✓ Shorter sales cycle: [n] avg days (wins) vs [n] avg days (losses)\n\nBATTLECARD: [COMPETITOR NAME]\n───────────────────────────────────────────────────────────\n\nTheir strengths (from deal notes):\n• [Strength extracted from notes]\n• [Strength extracted from notes]\n\nCommon objections and responses:\n• \"They're cheaper\" → [Response based on win patterns]\n• \"[Feature gap]\" → [Response\u002Fworkaround]\n• \"We already know them\" → [Response focused on differentiation]\n\nWhere we win:\n• [Scenario 1 — e.g., enterprise deals with complex integration needs]\n• [Scenario 2 — e.g., accounts with active support issues with competitor]\n• [Scenario 3 — e.g., deals where economic buyer is engaged early]\n\nWhere to be careful:\n• [Risk area 1 — e.g., SMB price-sensitive deals]\n• [Risk area 2 — e.g., industries where competitor has strong presence]\n\nRECOMMENDED ACTIONS\n───────────────────────────────────────────────────────────\n1. [Specific action based on loss patterns]\n2. [Coaching recommendation for reps]\n3. [Process change to improve win rate]\n═══════════════════════════════════════════════════════════\n```\n\n### Output Format\nDeliver a two-part output:\n1. **Intelligence report** — quantitative win\u002Floss analysis with patterns\n2. **Battlecard** — rep-ready talking points, objection responses, and when-to-use guidance\n\n### Example Interaction\n\n**User Input:**\n\"Show me competitive intelligence on Acme Corp for the last 6 months.\"\n\n**Skill Output:**\n```\nCOMPETITIVE INTELLIGENCE REPORT\nCompetitor: Acme Corp | Period: Sep 2025 – Mar 2026\n═══════════════════════════════════════════════════════════\n\nEXECUTIVE SUMMARY\nWin Rate vs Acme Corp: 38% (vs 61% overall win rate)\nRevenue Won: $420,000 | Revenue Lost to Acme: $680,000\n\nCOMPETITIVE PERFORMANCE BY DEAL SIZE\nSmall (\u003C$25K): 55% win rate — strongest segment\nMedium ($25K-$100K): 32% win rate — significant gap\nEnterprise (>$100K): 18% win rate — critical weakness\n\nWHERE WE LOSE\nMost losses at: Propose stage (67% of losses)\nTop industries: Financial Services (5 deals), Healthcare (3 deals)\n\nCOMMON OBJECTIONS\n1. Price — mentioned in 71% of lost deals\n2. Existing integration with their platform — 43% of lost deals\n3. Acme's brand recognition in FSI — 29% of lost deals\n\nWIN PATTERNS\n✓ Economic buyer engaged early: 78% of wins vs 22% of losses\n✓ POC completed before proposal: 64% of wins vs 11% of losses\n\nBATTLECARD: ACME CORP\n\"They're cheaper\" → \"Our TCO over 3 years is [X]% lower due to...\"\n\"We use their platform\" → \"Our API integrates in \u003C2 hours — here's a reference customer...\"\n```\n\n### Dataverse Tables Used\n| Table | Purpose |\n|-------|---------|\n| `opportunity` | Win\u002Floss records and deal details |\n| `opportunityclose` | Structured competitor data on closed deals (has direct `competitorid` lookup) |\n| `competitor` | Structured competitor profiles |\n| `account` | Industry and firmographic context |\n| `activitypointer` | Activity volume comparison |\n| `annotation` | Mining notes for competitive mentions |\n| `phonecall` | Call descriptions for competitor mentions |\n\n### Key Fields Reference\n**opportunity:**\n- `statecode` (STATE) - Open(0), Won(1), Lost(2)\n- `description` (MULTILINE TEXT) - General opportunity notes\n- `currentsituation` (MULTILINE TEXT) - Customer's current environment\n- `actualclosedate` (DATE) - When deal was closed\n- `salesstage` (CHOICE) - Stage at close\n- Note: `opportunity` has no direct `competitorid` field — the relationship is many-to-many via `opportunitycompetitors_association`. Use `opportunityclose.competitorid` for closed deal competitor data.\n\n**opportunityclose:**\n- `opportunityid` (LOOKUP) - Links to the closed opportunity\n- `competitorid` (LOOKUP) - Competitor selected at close (direct lookup, use this for competitive analysis)\n- `description` (MULTILINE TEXT) - Close reason \u002F notes entered at time of close\n- `actualrevenue` (MONEY) - Final deal value at close\n- `statecode` (STATE) - Activity completion state\n- `createdon` (DATETIME) - When the close activity was created\n\n**competitor:**\n- `name` (NVARCHAR) - Competitor name\n- `strengths` (MULTILINE TEXT) - Known strengths\n- `weaknesses` (MULTILINE TEXT) - Known weaknesses\n- `overview` (MULTILINE TEXT) - General description\n- `opportunitiescomments` (MULTILINE TEXT) - Where we win\n- `threatscomments` (MULTILINE TEXT) - Where we lose\n\n### Configurable Parameters\n- Analysis period (default: last 12 months)\n- Minimum deal count threshold for statistical confidence (default: 5 deals)\n- Competitor name keywords for text mining (configurable list)\n- Deal size segmentation thresholds\n\n## Examples\n\n### Example 1: Specific Competitor Analysis\n\n**User says:** \"How are we doing against ACME Corp?\"\n\n**Actions:**\n1. Search opportunityclose records for competitorid matching ACME\n2. Query won and lost deals with ACME as competitor\n3. Calculate win\u002Floss rates and deal value analysis\n4. Mine activity notes for competitive mentions\n5. Generate battlecard talking points\n\n**Result:**\n```\nCOMPETITIVE ANALYSIS: ACME CORP (Last 12 Months)\n\nHEAD-TO-HEAD RECORD:\nWins: 8 deals ($420K) | Losses: 12 deals ($680K)\nWin Rate: 40% (vs 55% overall win rate)\n\nWHERE WE LOSE:\n- Price objection in 67% of losses\n- Mid-market segment: 25% win rate\n\nWHERE WE WIN:\n- Enterprise deals: 62% win rate\n- When technical eval involved: 71% win rate\n\nBATTLECARD:\n\"They're cheaper\" → \"Our TCO over 3 years is 23% lower...\"\n\"We use their platform\" → \"Our API integrates in \u003C2 hours...\"\n```\n\n### Example 2: Full Competitive Landscape\n\n**User says:** \"Show me the competitive landscape for Q4\"\n\n**Actions:**\n1. Query all opportunityclose records with competitor data for Q4\n2. Group by competitor name\n3. Calculate win rates and deal values per competitor\n4. Rank by frequency and threat level\n\n**Result:**\n```\nQ4 COMPETITIVE LANDSCAPE\n\n| Competitor | Encounters | Win Rate | Avg Deal |\n|------------|------------|----------|----------|\n| ACME Corp  | 20 deals   | 40%      | $55K     |\n| Globex     | 14 deals   | 57%      | $72K     |\n| Initech    | 8 deals    | 75%      | $45K     |\n\nTOP THREAT: ACME Corp (high volume, low win rate)\nSTRONG AGAINST: Initech (technical differentiation)\n```\n\n### Example 3: Loss Pattern Analysis\n\n**User says:** \"Why are we losing to Globex?\"\n\n**Actions:**\n1. Query lost opportunities with Globex as competitor\n2. Analyze opportunity descriptions and close notes\n3. Extract common patterns and objections\n4. Generate actionable insights\n\n**Result:**\n```\nGLOBEX LOSS ANALYSIS (8 losses, $340K)\n\nCOMMON PATTERNS:\n- 75% lost at Proposal stage (late loss)\n- Avg sales cycle: 45 days (vs our 38 day avg)\n- 5\u002F8 losses in Financial Services vertical\n\nTOP OBJECTIONS (from notes):\n1. \"Existing Globex relationship\" (3 deals)\n2. \"Integration concerns\" (3 deals)\n3. \"Reference requests unfulfilled\" (2 deals)\n\nRECOMMENDATION:\n- Engage technical resources earlier in Financial Services\n- Build reference library for banking customers\n```\n\n## Troubleshooting\n\n### Error: No competitor data found\n**Cause:** Competitors not being recorded at deal close, or competitor table empty\n**Solution:**\n- Check if opportunityclose records have competitorid populated\n- Fall back to text mining in opportunity descriptions\n- Recommend enabling competitor tracking in close workflow\n\n### Error: Insufficient data for analysis\n**Cause:** Too few deals with specific competitor to draw conclusions\n**Solution:**\n- Expand time range beyond default 12 months\n- Combine with related competitors for aggregate view\n- Note statistical limitations in output\n\n### Error: Win rate appears inaccurate\n**Cause:** opportunityclose only captures explicit competitor selection; many deals may not have competitor recorded\n**Solution:**\n- Cross-reference with text mining results\n- Note coverage percentage in output\n- Recommend better competitor capture at deal close","# Competitive Intelligence\n\nCompetitive insights are often locked in deal notes, lost opportunity records, and anecdotal rep knowledge. This skill mines Dataverse to surface structured competitive intelligence: which competitors appear most frequently, where deals are being lost to them, what deal patterns correlate with wins vs losses, and what talking points reps should use. This is the Dataverse-internal equivalent of competitive research — drawing from closed deal history rather than external sources.\n\n## Instructions\n\n### Step 1: Identify Competitor or Analysis Scope\nAccept input from the user:\n- **Specific competitor name** (to analyze one rival)\n- **All competitors** (for a full competitive landscape view)\n- **Time range** (default: last 12 months)\n- **Segment filter** (by owner, territory, deal size, or industry)\n\nCalculate date range for analysis: `createdon >= '[start_date]'`\n\n#### Step 2: Identify Lost Deals with Competitor Information\n\n**Important:** The `opportunity` entity does not have a direct `competitorid` field — the opportunity-to-competitor relationship is many-to-many (`opportunitycompetitors_association`). When an opportunity is closed, Dynamics 365 creates an `opportunityclose` activity record which **does** have a direct `competitorid` lookup. Use `opportunityclose` for structured competitor data on closed deals.\n\n**Query closed-lost opportunityclose records:**\n```\nSELECT oc.opportunityid, oc.competitorid, oc.description, oc.createdon,\n       oc.actualrevenue\nFROM opportunityclose oc\nWHERE oc.statecode = 1\nAND oc.createdon >= '[start_date]'\nORDER BY oc.createdon DESC\n```\n\nThen join to the `opportunity` table by `opportunityid` to get deal details:\n```\nSELECT opportunityid, name, estimatedvalue, actualclosedate, salesstage,\n       description, ownerid, customerid, closeprobability\nFROM opportunity\nWHERE statecode = 2\nAND actualclosedate >= '[start_date]'\nORDER BY actualclosedate DESC\n```\n\n**Note:** If `opportunityclose` is not populated (competitor not selected at close), fall back to text pattern matching in opportunity description fields as described in Step 3.\n\n**Fetch competitor names if competitor table is used:**\n```\nSELECT competitorid, name, websiteurl, overview, strengths, weaknesses,\n       opportunitiescomments, threatscomments\nFROM competitor\n```\n\n#### Step 3: Mine Opportunity Descriptions for Competitor Mentions\nFor opportunities without structured competitor fields, search text fields for competitor names:\n```\nSELECT opportunityid, name, estimatedvalue, statecode, actualclosedate,\n       salesstage, description, currentsituation, customerneed, customerpainpoints\nFROM opportunity\nWHERE statecode IN (1, 2)\nAND actualclosedate >= '[start_date]'\n```\n\nSearch description, currentsituation, and customerpainpoints for known competitor keywords or names provided by the user. Categorize each mention as:\n- Win with competitor present (statecode = 1)\n- Loss to competitor (statecode = 2)\n\n#### Step 4: Pull Competitor Annotations from Activities\nSearch activity notes for competitor mentions:\n```\nSELECT annotationid, notetext, subject, objectid, createdon\nFROM annotation\nWHERE createdon >= '[start_date]'\n```\n\nSearch notetext for competitor name patterns. Extract:\n- Context of mention (evaluation, objection, price comparison)\n- Outcome (linked opportunity won or lost)\n- Frequency of mention\n\nAlso search phonecall and appointment descriptions:\n```\nSELECT activityid, subject, description, regardingobjectid, statecode\nFROM phonecall\nWHERE createdon >= '[start_date]'\n```\n\n#### Step 5: Calculate Win\u002FLoss Rates by Competitor\n\nFrom Step 2, you now have two lists of opportunityids: `[lost_opportunityids]` (from `opportunityclose` where `competitorid` matches and deal was lost) and `[won_opportunityids]` (from a separate `opportunityclose` query for won deals). Run an additional query to capture won opportunityclose records for this competitor:\n\n```\nSELECT oc.opportunityid, oc.createdon, oc.actualrevenue\nFROM opportunityclose oc\nWHERE oc.competitorid = '[competitorid]'\nAND oc.createdon >= '[start_date]'\n```\n\nCross-reference these opportunityids against `opportunity.statecode` to split into won vs lost buckets. Then aggregate:\n\n**Won opportunities where competitor was present:**\n```\nSELECT COUNT(opportunityid) as won_count, SUM(estimatedvalue) as won_value\nFROM opportunity\nWHERE statecode = 1\nAND actualclosedate >= '[start_date]'\n```\nFilter results programmatically to only those opportunityids found in the won opportunityclose results above.\n\n**Lost opportunities to competitor:**\n```\nSELECT COUNT(opportunityid) as lost_count, SUM(estimatedvalue) as lost_value\nFROM opportunity\nWHERE statecode = 2\nAND actualclosedate >= '[start_date]'\n```\nFilter results programmatically to only those opportunityids in `[lost_opportunityids]` from Step 2.\n\nCalculate:\n- **Win rate** = won_count \u002F (won_count + lost_count) × 100\n- **Average deal size (wins)** vs **average deal size (losses)**\n- **Average sales cycle (wins)** vs **average sales cycle (losses)**\n\n#### Step 6: Identify Deal Patterns\n\nFor won deals with competitor present vs lost deals to competitor, compare:\n\n**Deal size distribution:**\n```\nSELECT COUNT(opportunityid) as count, SUM(estimatedvalue) as total_value\nFROM opportunity\nWHERE statecode = 1\nAND estimatedvalue \u003C 25000\n```\nFilter results programmatically to only those opportunityids in `[won_opportunityids]`. Repeat for medium ($25K-$100K) and enterprise (>$100K) segments; run equivalent queries for `statecode = 2` filtered to `[lost_opportunityids]`.\n\n**Industry distribution:**\n```\nSELECT account.industrycode, COUNT(opportunity.opportunityid) as count\nFROM opportunity\nJOIN account ON opportunity.customerid = account.accountid\nWHERE opportunity.statecode = 2\nAND opportunity.actualclosedate >= '[start_date]'\nGROUP BY account.industrycode\n```\nFilter results programmatically to only those opportunityids in `[lost_opportunityids]` from Step 2.\n\n**Stage at loss:**\n```\nSELECT salesstage, COUNT(opportunityid) as lost_count, SUM(estimatedvalue) as lost_value\nFROM opportunity\nWHERE statecode = 2\nAND actualclosedate >= '[start_date]'\nGROUP BY salesstage\n```\nFilter results programmatically to only those opportunityids in `[lost_opportunityids]` from Step 2.\n\n#### Step 7: Identify Common Objections and Pain Points\nFrom text mining in Step 4, categorize recurring themes from notes and activity descriptions when competitor is mentioned:\n- **Price objections:** Look for \"cheaper\", \"lower cost\", \"price\", \"pricing\"\n- **Feature gaps:** Look for \"missing\", \"doesn't support\", \"can't do\", \"limitation\"\n- **Existing relationship:** Look for \"incumbent\", \"already using\", \"switching cost\", \"prefer\"\n- **Brand recognition:** Look for \"heard of\", \"well-known\", \"trusted\", \"market leader\"\n- **Implementation concerns:** Look for \"complex\", \"timeline\", \"integration\", \"support\"\n\nCount frequency of each theme across deal notes.\n\n#### Step 8: Extract Win Patterns\nFor won deals where this competitor was present, identify common factors:\n\n**Qualification strength in wins:**\n```\nSELECT budgetstatus, decisionmaker, need, purchasetimeframe, purchaseprocess,\n       COUNT(opportunityid) as count\nFROM opportunity\nWHERE statecode = 1\nAND actualclosedate >= '[start_date]'\nGROUP BY budgetstatus, decisionmaker, need, purchasetimeframe, purchaseprocess\n```\nFilter results programmatically to only those opportunityids in `[won_opportunityids]` from Step 5.\n\nNote which BANT patterns appear most often in wins — these inform the competitive playbook.\n\n**Activity volume in wins vs losses:**\nCount total activities per opportunity for wins and losses separately using activitypointer to identify engagement differences.\n\n#### Step 9: Generate Competitive Intelligence Report\n\n```\nCOMPETITIVE INTELLIGENCE REPORT\nCompetitor: [Competitor Name]\nPeriod: [Start Date] – [End Date]\nGenerated: [Today's Date]\n═══════════════════════════════════════════════════════════\n\nEXECUTIVE SUMMARY\n───────────────────────────────────────────────────────────\nDeals Analyzed: [n won] wins \u002F [n lost] losses\nWin Rate (competitive): [n]%\nRevenue Won (competitive): $[value]\nRevenue Lost to Competitor: $[value]\n\nCOMPETITIVE PERFORMANCE BY DEAL SIZE\n───────────────────────────────────────────────────────────\nSmall (\u003C$25K):     Win rate [n]%  | [n] won, [n] lost\nMedium ($25K-$100K): Win rate [n]% | [n] won, [n] lost\nEnterprise (>$100K): Win rate [n]% | [n] won, [n] lost\n\nWHERE WE LOSE\n───────────────────────────────────────────────────────────\nMost losses occur at: [Stage] stage ([n]% of losses)\nTop industries lost: [Industry 1] ([n] deals), [Industry 2] ([n] deals)\nAverage deal size lost: $[value] vs average deal size won: $[value]\n\nCOMMON OBJECTIONS (from deal notes)\n───────────────────────────────────────────────────────────\n1. Price\u002FCost concerns — mentioned in [n]% of lost deals\n2. [Feature gap] — mentioned in [n]% of lost deals\n3. [Incumbent relationship] — mentioned in [n]% of lost deals\n\nWIN PATTERNS (what works in competitive deals)\n───────────────────────────────────────────────────────────\n✓ Economic buyer engaged: [n]% of wins vs [n]% of losses\n✓ Budget confirmed before Propose: [n]% of wins vs [n]% of losses\n✓ Higher activity volume: [n] avg activities (wins) vs [n] (losses)\n✓ Shorter sales cycle: [n] avg days (wins) vs [n] avg days (losses)\n\nBATTLECARD: [COMPETITOR NAME]\n───────────────────────────────────────────────────────────\n\nTheir strengths (from deal notes):\n• [Strength extracted from notes]\n• [Strength extracted from notes]\n\nCommon objections and responses:\n• \"They're cheaper\" → [Response based on win patterns]\n• \"[Feature gap]\" → [Response\u002Fworkaround]\n• \"We already know them\" → [Response focused on differentiation]\n\nWhere we win:\n• [Scenario 1 — e.g., enterprise deals with complex integration needs]\n• [Scenario 2 — e.g., accounts with active support issues with competitor]\n• [Scenario 3 — e.g., deals where economic buyer is engaged early]\n\nWhere to be careful:\n• [Risk area 1 — e.g., SMB price-sensitive deals]\n• [Risk area 2 — e.g., industries where competitor has strong presence]\n\nRECOMMENDED ACTIONS\n───────────────────────────────────────────────────────────\n1. [Specific action based on loss patterns]\n2. [Coaching recommendation for reps]\n3. [Process change to improve win rate]\n═══════════════════════════════════════════════════════════\n```\n\n### Output Format\nDeliver a two-part output:\n1. **Intelligence report** — quantitative win\u002Floss analysis with patterns\n2. **Battlecard** — rep-ready talking points, objection responses, and when-to-use guidance\n\n### Example Interaction\n\n**User Input:**\n\"Show me competitive intelligence on Acme Corp for the last 6 months.\"\n\n**Skill Output:**\n```\nCOMPETITIVE INTELLIGENCE REPORT\nCompetitor: Acme Corp | Period: Sep 2025 – Mar 2026\n═══════════════════════════════════════════════════════════\n\nEXECUTIVE SUMMARY\nWin Rate vs Acme Corp: 38% (vs 61% overall win rate)\nRevenue Won: $420,000 | Revenue Lost to Acme: $680,000\n\nCOMPETITIVE PERFORMANCE BY DEAL SIZE\nSmall (\u003C$25K): 55% win rate — strongest segment\nMedium ($25K-$100K): 32% win rate — significant gap\nEnterprise (>$100K): 18% win rate — critical weakness\n\nWHERE WE LOSE\nMost losses at: Propose stage (67% of losses)\nTop industries: Financial Services (5 deals), Healthcare (3 deals)\n\nCOMMON OBJECTIONS\n1. Price — mentioned in 71% of lost deals\n2. Existing integration with their platform — 43% of lost deals\n3. Acme's brand recognition in FSI — 29% of lost deals\n\nWIN PATTERNS\n✓ Economic buyer engaged early: 78% of wins vs 22% of losses\n✓ POC completed before proposal: 64% of wins vs 11% of losses\n\nBATTLECARD: ACME CORP\n\"They're cheaper\" → \"Our TCO over 3 years is [X]% lower due to...\"\n\"We use their platform\" → \"Our API integrates in \u003C2 hours — here's a reference customer...\"\n```\n\n### Dataverse Tables Used\n| Table | Purpose |\n|-------|---------|\n| `opportunity` | Win\u002Floss records and deal details |\n| `opportunityclose` | Structured competitor data on closed deals (has direct `competitorid` lookup) |\n| `competitor` | Structured competitor profiles |\n| `account` | Industry and firmographic context |\n| `activitypointer` | Activity volume comparison |\n| `annotation` | Mining notes for competitive mentions |\n| `phonecall` | Call descriptions for competitor mentions |\n\n### Key Fields Reference\n**opportunity:**\n- `statecode` (STATE) - Open(0), Won(1), Lost(2)\n- `description` (MULTILINE TEXT) - General opportunity notes\n- `currentsituation` (MULTILINE TEXT) - Customer's current environment\n- `actualclosedate` (DATE) - When deal was closed\n- `salesstage` (CHOICE) - Stage at close\n- Note: `opportunity` has no direct `competitorid` field — the relationship is many-to-many via `opportunitycompetitors_association`. Use `opportunityclose.competitorid` for closed deal competitor data.\n\n**opportunityclose:**\n- `opportunityid` (LOOKUP) - Links to the closed opportunity\n- `competitorid` (LOOKUP) - Competitor selected at close (direct lookup, use this for competitive analysis)\n- `description` (MULTILINE TEXT) - Close reason \u002F notes entered at time of close\n- `actualrevenue` (MONEY) - Final deal value at close\n- `statecode` (STATE) - Activity completion state\n- `createdon` (DATETIME) - When the close activity was created\n\n**competitor:**\n- `name` (NVARCHAR) - Competitor name\n- `strengths` (MULTILINE TEXT) - Known strengths\n- `weaknesses` (MULTILINE TEXT) - Known weaknesses\n- `overview` (MULTILINE TEXT) - General description\n- `opportunitiescomments` (MULTILINE TEXT) - Where we win\n- `threatscomments` (MULTILINE TEXT) - Where we lose\n\n### Configurable Parameters\n- Analysis period (default: last 12 months)\n- Minimum deal count threshold for statistical confidence (default: 5 deals)\n- Competitor name keywords for text mining (configurable list)\n- Deal size segmentation thresholds\n\n## Examples\n\n### Example 1: Specific Competitor Analysis\n\n**User says:** \"How are we doing against ACME Corp?\"\n\n**Actions:**\n1. Search opportunityclose records for competitorid matching ACME\n2. Query won and lost deals with ACME as competitor\n3. Calculate win\u002Floss rates and deal value analysis\n4. Mine activity notes for competitive mentions\n5. Generate battlecard talking points\n\n**Result:**\n```\nCOMPETITIVE ANALYSIS: ACME CORP (Last 12 Months)\n\nHEAD-TO-HEAD RECORD:\nWins: 8 deals ($420K) | Losses: 12 deals ($680K)\nWin Rate: 40% (vs 55% overall win rate)\n\nWHERE WE LOSE:\n- Price objection in 67% of losses\n- Mid-market segment: 25% win rate\n\nWHERE WE WIN:\n- Enterprise deals: 62% win rate\n- When technical eval involved: 71% win rate\n\nBATTLECARD:\n\"They're cheaper\" → \"Our TCO over 3 years is 23% lower...\"\n\"We use their platform\" → \"Our API integrates in \u003C2 hours...\"\n```\n\n### Example 2: Full Competitive Landscape\n\n**User says:** \"Show me the competitive landscape for Q4\"\n\n**Actions:**\n1. Query all opportunityclose records with competitor data for Q4\n2. Group by competitor name\n3. Calculate win rates and deal values per competitor\n4. Rank by frequency and threat level\n\n**Result:**\n```\nQ4 COMPETITIVE LANDSCAPE\n\n| Competitor | Encounters | Win Rate | Avg Deal |\n|------------|------------|----------|----------|\n| ACME Corp  | 20 deals   | 40%      | $55K     |\n| Globex     | 14 deals   | 57%      | $72K     |\n| Initech    | 8 deals    | 75%      | $45K     |\n\nTOP THREAT: ACME Corp (high volume, low win rate)\nSTRONG AGAINST: Initech (technical differentiation)\n```\n\n### Example 3: Loss Pattern Analysis\n\n**User says:** \"Why are we losing to Globex?\"\n\n**Actions:**\n1. Query lost opportunities with Globex as competitor\n2. Analyze opportunity descriptions and close notes\n3. Extract common patterns and objections\n4. Generate actionable insights\n\n**Result:**\n```\nGLOBEX LOSS ANALYSIS (8 losses, $340K)\n\nCOMMON PATTERNS:\n- 75% lost at Proposal stage (late loss)\n- Avg sales cycle: 45 days (vs our 38 day avg)\n- 5\u002F8 losses in Financial Services vertical\n\nTOP OBJECTIONS (from notes):\n1. \"Existing Globex relationship\" (3 deals)\n2. \"Integration concerns\" (3 deals)\n3. \"Reference requests unfulfilled\" (2 deals)\n\nRECOMMENDATION:\n- Engage technical resources earlier in Financial Services\n- Build reference library for banking customers\n```\n\n## Troubleshooting\n\n### Error: No competitor data found\n**Cause:** Competitors not being recorded at deal close, or competitor table empty\n**Solution:**\n- Check if opportunityclose records have competitorid populated\n- Fall back to text mining in opportunity descriptions\n- Recommend enabling competitor tracking in close workflow\n\n### Error: Insufficient data for analysis\n**Cause:** Too few deals with specific competitor to draw conclusions\n**Solution:**\n- Expand time range beyond default 12 months\n- Combine with related competitors for aggregate view\n- Note statistical limitations in output\n\n### Error: Win rate appears inaccurate\n**Cause:** opportunityclose only captures explicit competitor selection; many deals may not have competitor recorded\n**Solution:**\n- Cross-reference with text mining results\n- Note coverage percentage in output\n- Recommend better competitor capture at deal close",{"name":5,"metadata":32,"description":7},{"author":33,"version":34,"category":35},"Dataverse","1.0.0","sales-analytics","main","10016dd09acfa5f4dfce84de4e34ef294961faaf","skills\u002Fcompetitive-intelligence",9,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fdataverse-business-skills","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-03-10 22:57:33",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add microsoft\u002Fdataverse-business-skills --skill competitive-intelligence",{"tool":51,"command":52},"bunx","bunx skills add microsoft\u002Fdataverse-business-skills --skill competitive-intelligence",{"tool":54,"command":55},"pnpm","pnpm dlx skills add microsoft\u002Fdataverse-business-skills --skill competitive-intelligence","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fdataverse-business-skills\u002Fblob\u002Fmain\u002Fskills\u002Fcompetitive-intelligence\u002FSKILL.md",true,[],[60,68,77,85,93,101],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":27},"01M69A19ETGAKEDJSRGPZ6QGTZ","win-loss-pattern-analyzer","Analyzes closed opportunities to identify patterns between won and lost deals. Compares sales cycles, activities, stakeholder engagement, and deal characteristics for actionable playbook insights. Use when user asks \"why are we losing deals\", \"win loss analysis\", \"what makes deals win\", \"analyze lost opportunities\", \"sales pattern analysis\", \"compare won vs lost deals\", or \"improve win rate\".","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fdataverse-business-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwin-loss-pattern-analyzer\u002FSKILL.md",[],[67,26,25],"win loss pattern analyzer",{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":27},"01M69A17A9PBCXTW6BX84RQPVD","pipeline-health-analyzer","Reviews opportunities in the sales pipeline to identify stuck deals, missing next steps, weak qualification, and unbalanced stages. Use when user asks \"how is my pipeline looking\", \"analyze pipeline health\", \"which deals are stuck\", \"pipeline review\", \"find at-risk deals\", \"identify stalled opportunities\", or \"audit my open deals\".","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fdataverse-business-skills\u002Fblob\u002Fmain\u002Fskills\u002Fpipeline-health-analyzer\u002FSKILL.md",[],[75,26,25,76],"pipeline health analyzer","review",{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":27},"01M69A15PGJM0FQRNMWMHHVQTC","next-best-action-engine","Analyzes an opportunity's current state and engagement history, compares against won deals, and recommends the most effective next action with reasoning. Use when user asks \"what should I do next on this deal\", \"next steps for this opportunity\", \"how do I move this deal forward\", \"what's the best action for this opp\", \"deal coaching\", or \"opportunity next action\".","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fdataverse-business-skills\u002Fblob\u002Fmain\u002Fskills\u002Fnext-best-action-engine\u002FSKILL.md",[],[84,25],"next best action engine",{"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":27},"01M69A13E5XFQH0FFSQV14N77Q","log-call-transcripts","Analyzes sales call transcripts to extract key information and automatically logs the call as a Phone Call activity in Dataverse. Use when user says \"log this call\", \"process this transcript\", \"save this call to CRM\", \"create a phone call record from this transcript\", uploads a call recording transcript, or pastes meeting\u002Fcall notes to be logged.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fdataverse-business-skills\u002Fblob\u002Fmain\u002Fskills\u002Flog-call-transcripts\u002FSKILL.md",[],[92,25],"log call transcripts",{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":27},"01M69A123D52BE37H1PSJZCG5Y","lead-qualification-playbook","Guides sales reps through structured lead qualification using BANT+ methodology. Evaluates leads, suggests discovery questions, scores quality, and recommends next steps. Use when user says \"qualify this lead\", \"help me qualify\", \"BANT analysis\", \"score this lead\", \"should I convert this lead\", \"lead qualification questions\", or \"assess lead quality\".","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fdataverse-business-skills\u002Fblob\u002Fmain\u002Fskills\u002Flead-qualification-playbook\u002FSKILL.md",[],[100,25],"lead qualification playbook",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":27},"01M69A10JBPT5T3B7XN33XK3TX","handoff-brief-generator","Creates comprehensive handoff documentation for sales reps going on vacation or transitioning deals. Generates structured briefs with deal status, activities, next steps, contacts, and risks. Use when user says \"I'm going on vacation\", \"create handoff brief\", \"coverage brief for my deals\", \"vacation handoff\", \"out of office brief\", \"transition my deals\", or \"backup documentation\".","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fdataverse-business-skills\u002Fblob\u002Fmain\u002Fskills\u002Fhandoff-brief-generator\u002FSKILL.md",[],[108,109,110,111,25],"handoff brief generator","handoff","documentation","status"]