[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-zoominfo":3,"mdc-ixos91-key":33,"related-repo-openai-zoominfo":1293,"related-org-openai-zoominfo":1402},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":22,"repoUrl":23,"updatedAt":24,"license":25,"forks":26,"topics":27,"repo":28,"sourceUrl":31,"mdContent":32},"zoominfo","connect and query ZoomInfo for sales","Use only when a focused Sales workflow has selected a present and connected ZoomInfo connector, or the user explicitly asks for ZoomInfo company search, contact search, enrichment, intent, similarity, recommendations, or research. Do not use when another enrichment source is selected.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"openai","OpenAI","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fopenai.png",[12,16,19],{"name":13,"slug":14,"type":15},"Research","research","tag",{"name":17,"slug":18,"type":15},"CRM","crm",{"name":20,"slug":21,"type":15},"Sales","sales",427,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Frole-specific-plugins","2026-07-01T07:53:53.405765",null,65,[],{"repoUrl":23,"stars":22,"forks":26,"topics":29,"description":30},[],"Role-specific Codex plugin templates","https:\u002F\u002Fgithub.com\u002Fopenai\u002Frole-specific-plugins\u002Ftree\u002FHEAD\u002Fplugins\u002Fsales\u002Fskills\u002Fzoominfo","---\nname: zoominfo\ndescription: Use only when a focused Sales workflow has selected a present and connected ZoomInfo connector, or the user explicitly asks for ZoomInfo company search, contact search, enrichment, intent, similarity, recommendations, or research. Do not use when another enrichment source is selected.\n---\n\n# ZoomInfo User Guide\n\nUse ZoomInfo for focused Sales Intelligence work after the parent Sales workflow selects it. Keep the parent workflow authoritative for the seller's task; this guide owns ZoomInfo-specific lookup, search, identity, enrichment, credit, and result-quality rules.\n\n## Common Skill Instructions\n\nMANDATORY: If not already in context, read and adhere closely to plugins\u002Fsales\u002Fskills\u002Findex\u002FSKILL.md## Cross-Skill Best Practices.\n\n## ZoomInfo Operation Ranking\n\n1. Explicit user request, named company or person, domain, email, ZoomInfo ID, or stated constraint\n2. The narrowest ZoomInfo lane needed by the active Sales workflow\n3. Canonical company or contact identity resolved from strong identifiers\n4. Search and shortlist before enrichment, research, similarity, or recommendations\n5. The smallest credit-consuming step that materially improves the answer\n6. A result that clearly separates qualified matches, near matches, and gaps\n\nDo not silently relax hard filters, guess identities, or present ZoomInfo as CRM ground truth.\n\n## Key Dependency Categories\n\nThese are particularly important for this workflow; use your best judgment to potentially include other data sources to improve quality.\n\n- ~~Sales Intelligence, specifically a present and connected ZoomInfo connector, for ZoomInfo search, enrichment, intent, similarity, recommendations, and research\n- ~~CRM for account ownership, customer status, opportunity facts, and forecast truth\n- The parent Sales workflow for Calendar, Meeting Transcripts, Email, Internal Messaging, or Knowledge & Files context\n- User-provided names, domains, emails, IDs, ICP constraints, and business context when connector access or identity is incomplete\n\nIf ZoomInfo is missing, unavailable, ambiguous, or limited by the exposed connector surface, state the limitation instead of substituting unsupported claims.\n\n## Connector Boundary\n\nZoomInfo supports several distinct lanes. Choose the narrowest lane that fits the request.\n\n- Discovery: `lookup`, `search_companies`, `search_contacts`, `search_intent`\n- Structured enrichment: `enrich_companies`, `enrich_contacts`, `enrich_intent`\n- Narrative research: `account_research`, `contact_research`\n- Similarity and recommendation: `find_similar_companies`, `find_similar_contacts`, `get_recommended_contacts`\n- Connector feedback only when the user asks for it: `submit_feedback`\n\nDo not blur these lanes:\n\n- Use `search_*` to discover candidates.\n- Use `enrich_*` when the user wants stronger structured fields or a verified detail check.\n- Use `account_research` or `contact_research` when the user wants a narrative brief, meeting prep, or broader situational readout.\n- Use similarity or recommendation actions for \"more like this\", account expansion, or stakeholder discovery, not as a substitute for precise search filters.\n\nDo not present ZoomInfo as CRM ground truth. If a research response includes relationship or engagement context, label it as connector-surfaced context unless it is independently grounded by ~~CRM or the surrounding workflow.\n\n## Default Resolution Pattern\n\nRun these steps in order.\n\n1. Classify the target:\n   - company set\n   - contact set\n   - one known company\n   - one known person\n   - buyer intent topic\n   - lookalike or recommendation request\n2. Normalize hard filters before searching:\n   - geography\n   - management level\n   - department or job family\n   - employee or revenue bands\n   - industry or company type\n   - technology filters\n   - intent topics\n3. Use `lookup` before search or intent flows whenever the connector expects standardized values.\n4. Resolve canonical company or contact identity before enrichment, research, or recommendation actions that depend on IDs.\n5. Verify that returned rows actually satisfy the user's hard constraints before summarizing them as matches.\n6. State what was not found, weakly supported, or connector-limited instead of smoothing gaps away.\n\n## Lookup Discipline\n\nUse `lookup` to retrieve supported values instead of guessing connector-specific categories.\n\n- Use it for `management-levels`, `metro-regions`, `industries`, `employee-count`, `departments`, `job-functions`, `company-types`, `revenue-ranges`, `tech-vendors`, `tech-products`, and `intent-topics` when those constraints matter.\n- Use the standardized identifier returned by `lookup` where the downstream action expects an identifier, not a prettified display label.\n- For technology-stack searches, resolve the vendor first, then resolve products for that exact vendor, then pass the returned product identifiers into search.\n- For intent workflows, retrieve exact supported intent topics first. If the requested concept does not map cleanly to a supported topic, present the closest supported topic only when it is genuinely close; otherwise say the request is not precisely expressible through the current topic taxonomy.\n\nDo not invent lookup values or silently swap in an adjacent category without saying so.\n\n## Identifier Resolution\n\nResolve entities carefully before ID-dependent actions.\n\n### Companies\n\n- Prefer `companyId`, domain, website, or ticker over company name alone.\n- If the user provides only a company name and the next step requires enrichment, research, or a target-company ID, first use `search_companies` to find the canonical company row when identity is not obvious.\n- If multiple plausible companies remain, use domain, headquarters, industry, or the user's surrounding context to disambiguate. If ambiguity still matters, present the candidate set instead of picking one quietly.\n- For company enrichment, prefer `companyId`, `domain`, or `companyWebsite` over vague name-only input when available.\n\n### Contacts\n\n- Prefer `personId`, business email, or an exact full-name-plus-company combination over a name alone.\n- If the user asks for contact research, similar contacts, or another person-ID-dependent workflow from a name, first use `search_contacts` to resolve the target person.\n- If the same name maps to multiple plausible people, keep the candidate list explicit and do not fabricate a single match.\n- For contact enrichment, use the strongest supported identifier available; avoid broad name-only enrichment when a search pass can make the identity less ambiguous.\n\n### Runtime Shape\n\n- Pass connector-returned identifiers in the runtime-compatible primitive shape the action accepts.\n- When the connector surfaces a numeric ZoomInfo identifier and the destination action requires a numeric identifier at runtime, preserve it as numeric rather than rewriting it into prose or guessing a new value.\n- If an action rejects an apparently valid identifier shape, retry only once with the directly corresponding connector-returned primitive when the target is unambiguous. If that still fails, report a connector contract mismatch and continue only with lower-risk available evidence.\n\n## Search Discipline\n\n### Company Search\n\n- Translate the user's ICP into explicit filters before searching.\n- Prefer structured filters for geography, headcount, revenue, company type, funding, growth, and tech usage when the connector supports them.\n- If the user asks for \"US companies\", \"California companies\", or another hard geography requirement, verify that each surfaced result matches the requested region before calling it a qualified match.\n- If search returns close but imperfect rows, separate `Matches` from `Near Matches` rather than hiding the distinction.\n- Do not claim exhaustive market coverage from a bounded result page.\n\n### Contact Search\n\n- Use management level, department, function, company, and title filters together when that improves precision.\n- For role-family requests such as \"VP, Director, or Head of RevOps\", start with the narrowest structured interpretation that is likely to work.\n- If a single broad title query returns sparse, clearly incomplete, or off-target results, split the role family into a small number of targeted searches, merge duplicates, and summarize the deduped shortlist.\n- Prefer directly returned business fields. Do not infer private email addresses, personal phones, or missing professional profiles.\n\n### Intent Search\n\n- Always resolve exact intent topics with `lookup` before `search_intent` or `enrich_intent`.\n- Keep topic meaning visible in the answer so the user can see what was actually searched.\n- If returned intent topics are materially narrower, broader, or adjacent to the user's concept, say so.\n- If the topic lookup or search path cannot support the requested concept faithfully, report that limitation instead of overstating the result.\n\n## Enrichment And Research Sequencing\n\nUse cheap narrowing steps before expensive or less precise actions when practical.\n\n- Use search first when the entity itself is unclear.\n- Use structured enrichment when the user wants firmographic fields, contactability fields, or batch-ready tabular output.\n- Use narrative research when the user wants a briefing, situational awareness, or prepare-for-meeting style synthesis.\n- For top-N discovery requests, do not enrich every raw candidate by default. Narrow first, then enrich only the shortlisted set that materially improves the answer.\n- When a similarity or recommendation workflow returns sparse person or company detail, add a targeted enrichment pass only when the user asked for actionable detail or when the surrounding workflow needs it.\n\n## Similarity And Recommendation Flows\n\n### Similar Companies\n\n- Use `find_similar_companies` when the user asks for competitor-like, lookalike, or adjacent-account discovery.\n- If the reference company is ambiguous, resolve it before the similarity call.\n- If the user wants a usable market list rather than raw similarity results, enrich the final shortlist just enough to supply requested basics such as website, location, employee range, or a concise description.\n\n### Similar Contacts\n\n- Resolve `referencePersonId` with `search_contacts` when the user gives a name.\n- Resolve `targetCompanyId` with `search_companies` when the user wants lookalike contacts inside a specific account.\n- Explain recommendations using returned metadata rather than making up a similarity rationale.\n\n### Recommended Contacts\n\n- Resolve the target company first.\n- Choose the recommendation use case that matches the user intent:\n  - `PROSPECTING`\n  - `DEAL_ACCELERATION`\n  - `RENEWAL_AND_GROWTH`\n- Explain what the use case means in the final readout when it affects interpretation.\n- Treat recommendation scores as ranking signals, not response probabilities or guaranteed success.\n\n## Credit-Aware Behavior\n\nPrefer free or lower-cost discovery steps before credit-consuming enrichment or AI research when the workflow permits it.\n\n- Use `lookup`, `search_companies`, `search_contacts`, and `search_intent` to narrow scope first when appropriate.\n- Use `enrich_companies`, `enrich_contacts`, `enrich_intent`, `account_research`, and `contact_research` when the user has asked for the stronger result those actions provide.\n- For broad batch requests, make the action scope visible in the answer and avoid unnecessary enrichment of obviously weak candidates.\n\nDo not add friction for a small, clearly requested enrichment task. Do be explicit when the connector result may have consumed meaningful credits or when a narrower rerun would be materially cheaper.\n\n## Failure Handling\n\n- If the connector returns no results, say `no clear ZoomInfo match returned` rather than inventing one.\n- If results violate a hard filter, exclude them from the qualified set and mention the mismatch.\n- If a required lookup value is unavailable, say which constraint could not be represented cleanly.\n- If a research response is thin or generic, preserve the useful parts but label coverage as limited.\n- If a recommendation or similarity call yields weak actionability, say what extra enrichment or user context would be needed.\n- If the connector behavior appears inconsistent with its own action contract, describe the inconsistency plainly in the answer when it affects completeness or confidence.\n\n## Output Rules\n\n- Prefer compact tables for candidate lists, enrichment outputs, similar-company lists, and contact recommendations.\n- Prefer clickable connector-returned links when available; never construct guessed links from opaque IDs.\n- Separate:\n  - `Qualified matches`\n  - `Near matches` when useful\n  - `Gaps \u002F connector limitations`\n- Keep sourced facts separate from `Inference:`.\n- Do not guess emails, phone numbers, exact intent, or confidence levels not surfaced by the connector.\n- When the answer depends on connector-reported fields or recommendation metadata, say so directly.\n- If the user's request asked for a ranked list, rank by explicit connector signal or stated criteria, not by invisible model preference.\n\n#### Output Format\n\n    # [ZoomInfo Search \u002F Enrichment \u002F Research]\n\n    ## Qualified Matches\n\n    | Company \u002F Person | Key Match Evidence | Useful Detail | Source |\n    | --- | --- | --- | --- |\n    | [Result] | [Hard filters satisfied] | [Returned field] | [Link or connector source] |\n\n    ## Near Matches\n\n    - [Result + exact mismatch, when useful]\n\n    ## Gaps \u002F Connector Limitations\n\n    - [Missing field, unsupported filter, bounded coverage, ambiguity, or credit-aware next step]\n\n    ---\n\n    {Follow the instructions and output format\u002Fconditions in [Limitations and Improvements](..\u002Findex\u002FSKILL.md#limitations-and-improvements)}\n\n    {Follow the instructions and output format\u002Fconditions in [Next Steps](..\u002Findex\u002FSKILL.md#4-next-steps)}\n",{"data":34,"body":35},{"name":4,"description":6},{"type":36,"children":37},"root",[38,47,53,60,65,71,106,111,117,122,146,151,157,162,278,283,334,339,345,350,460,466,477,586,591,597,602,609,669,675,712,718,736,742,748,792,798,821,827,870,876,881,909,915,921,945,951,997,1003,1056,1062,1067,1139,1144,1150,1191,1197,1274,1281],{"type":39,"tag":40,"props":41,"children":43},"element","h1",{"id":42},"zoominfo-user-guide",[44],{"type":45,"value":46},"text","ZoomInfo User Guide",{"type":39,"tag":48,"props":49,"children":50},"p",{},[51],{"type":45,"value":52},"Use ZoomInfo for focused Sales Intelligence work after the parent Sales workflow selects it. Keep the parent workflow authoritative for the seller's task; this guide owns ZoomInfo-specific lookup, search, identity, enrichment, credit, and result-quality rules.",{"type":39,"tag":54,"props":55,"children":57},"h2",{"id":56},"common-skill-instructions",[58],{"type":45,"value":59},"Common Skill Instructions",{"type":39,"tag":48,"props":61,"children":62},{},[63],{"type":45,"value":64},"MANDATORY: If not already in context, read and adhere closely to plugins\u002Fsales\u002Fskills\u002Findex\u002FSKILL.md## Cross-Skill Best Practices.",{"type":39,"tag":54,"props":66,"children":68},{"id":67},"zoominfo-operation-ranking",[69],{"type":45,"value":70},"ZoomInfo Operation Ranking",{"type":39,"tag":72,"props":73,"children":74},"ol",{},[75,81,86,91,96,101],{"type":39,"tag":76,"props":77,"children":78},"li",{},[79],{"type":45,"value":80},"Explicit user request, named company or person, domain, email, ZoomInfo ID, or stated constraint",{"type":39,"tag":76,"props":82,"children":83},{},[84],{"type":45,"value":85},"The narrowest ZoomInfo lane needed by the active Sales workflow",{"type":39,"tag":76,"props":87,"children":88},{},[89],{"type":45,"value":90},"Canonical company or contact identity resolved from strong identifiers",{"type":39,"tag":76,"props":92,"children":93},{},[94],{"type":45,"value":95},"Search and shortlist before enrichment, research, similarity, or recommendations",{"type":39,"tag":76,"props":97,"children":98},{},[99],{"type":45,"value":100},"The smallest credit-consuming step that materially improves the answer",{"type":39,"tag":76,"props":102,"children":103},{},[104],{"type":45,"value":105},"A result that clearly separates qualified matches, near matches, and gaps",{"type":39,"tag":48,"props":107,"children":108},{},[109],{"type":45,"value":110},"Do not silently relax hard filters, guess identities, or present ZoomInfo as CRM ground truth.",{"type":39,"tag":54,"props":112,"children":114},{"id":113},"key-dependency-categories",[115],{"type":45,"value":116},"Key Dependency Categories",{"type":39,"tag":48,"props":118,"children":119},{},[120],{"type":45,"value":121},"These are particularly important for this workflow; use your best judgment to potentially include other data sources to improve quality.",{"type":39,"tag":123,"props":124,"children":125},"ul",{},[126,131,136,141],{"type":39,"tag":76,"props":127,"children":128},{},[129],{"type":45,"value":130},"~~Sales Intelligence, specifically a present and connected ZoomInfo connector, for ZoomInfo search, enrichment, intent, similarity, recommendations, and research",{"type":39,"tag":76,"props":132,"children":133},{},[134],{"type":45,"value":135},"~~CRM for account ownership, customer status, opportunity facts, and forecast truth",{"type":39,"tag":76,"props":137,"children":138},{},[139],{"type":45,"value":140},"The parent Sales workflow for Calendar, Meeting Transcripts, Email, Internal Messaging, or Knowledge & Files context",{"type":39,"tag":76,"props":142,"children":143},{},[144],{"type":45,"value":145},"User-provided names, domains, emails, IDs, ICP constraints, and business context when connector access or identity is incomplete",{"type":39,"tag":48,"props":147,"children":148},{},[149],{"type":45,"value":150},"If ZoomInfo is missing, unavailable, ambiguous, or limited by the exposed connector surface, state the limitation instead of substituting unsupported claims.",{"type":39,"tag":54,"props":152,"children":154},{"id":153},"connector-boundary",[155],{"type":45,"value":156},"Connector Boundary",{"type":39,"tag":48,"props":158,"children":159},{},[160],{"type":45,"value":161},"ZoomInfo supports several distinct lanes. Choose the narrowest lane that fits the request.",{"type":39,"tag":123,"props":163,"children":164},{},[165,199,224,242,267],{"type":39,"tag":76,"props":166,"children":167},{},[168,170,177,179,185,186,192,193],{"type":45,"value":169},"Discovery: ",{"type":39,"tag":171,"props":172,"children":174},"code",{"className":173},[],[175],{"type":45,"value":176},"lookup",{"type":45,"value":178},", ",{"type":39,"tag":171,"props":180,"children":182},{"className":181},[],[183],{"type":45,"value":184},"search_companies",{"type":45,"value":178},{"type":39,"tag":171,"props":187,"children":189},{"className":188},[],[190],{"type":45,"value":191},"search_contacts",{"type":45,"value":178},{"type":39,"tag":171,"props":194,"children":196},{"className":195},[],[197],{"type":45,"value":198},"search_intent",{"type":39,"tag":76,"props":200,"children":201},{},[202,204,210,211,217,218],{"type":45,"value":203},"Structured enrichment: ",{"type":39,"tag":171,"props":205,"children":207},{"className":206},[],[208],{"type":45,"value":209},"enrich_companies",{"type":45,"value":178},{"type":39,"tag":171,"props":212,"children":214},{"className":213},[],[215],{"type":45,"value":216},"enrich_contacts",{"type":45,"value":178},{"type":39,"tag":171,"props":219,"children":221},{"className":220},[],[222],{"type":45,"value":223},"enrich_intent",{"type":39,"tag":76,"props":225,"children":226},{},[227,229,235,236],{"type":45,"value":228},"Narrative research: ",{"type":39,"tag":171,"props":230,"children":232},{"className":231},[],[233],{"type":45,"value":234},"account_research",{"type":45,"value":178},{"type":39,"tag":171,"props":237,"children":239},{"className":238},[],[240],{"type":45,"value":241},"contact_research",{"type":39,"tag":76,"props":243,"children":244},{},[245,247,253,254,260,261],{"type":45,"value":246},"Similarity and recommendation: ",{"type":39,"tag":171,"props":248,"children":250},{"className":249},[],[251],{"type":45,"value":252},"find_similar_companies",{"type":45,"value":178},{"type":39,"tag":171,"props":255,"children":257},{"className":256},[],[258],{"type":45,"value":259},"find_similar_contacts",{"type":45,"value":178},{"type":39,"tag":171,"props":262,"children":264},{"className":263},[],[265],{"type":45,"value":266},"get_recommended_contacts",{"type":39,"tag":76,"props":268,"children":269},{},[270,272],{"type":45,"value":271},"Connector feedback only when the user asks for it: ",{"type":39,"tag":171,"props":273,"children":275},{"className":274},[],[276],{"type":45,"value":277},"submit_feedback",{"type":39,"tag":48,"props":279,"children":280},{},[281],{"type":45,"value":282},"Do not blur these lanes:",{"type":39,"tag":123,"props":284,"children":285},{},[286,299,311,329],{"type":39,"tag":76,"props":287,"children":288},{},[289,291,297],{"type":45,"value":290},"Use ",{"type":39,"tag":171,"props":292,"children":294},{"className":293},[],[295],{"type":45,"value":296},"search_*",{"type":45,"value":298}," to discover candidates.",{"type":39,"tag":76,"props":300,"children":301},{},[302,303,309],{"type":45,"value":290},{"type":39,"tag":171,"props":304,"children":306},{"className":305},[],[307],{"type":45,"value":308},"enrich_*",{"type":45,"value":310}," when the user wants stronger structured fields or a verified detail check.",{"type":39,"tag":76,"props":312,"children":313},{},[314,315,320,322,327],{"type":45,"value":290},{"type":39,"tag":171,"props":316,"children":318},{"className":317},[],[319],{"type":45,"value":234},{"type":45,"value":321}," or ",{"type":39,"tag":171,"props":323,"children":325},{"className":324},[],[326],{"type":45,"value":241},{"type":45,"value":328}," when the user wants a narrative brief, meeting prep, or broader situational readout.",{"type":39,"tag":76,"props":330,"children":331},{},[332],{"type":45,"value":333},"Use similarity or recommendation actions for \"more like this\", account expansion, or stakeholder discovery, not as a substitute for precise search filters.",{"type":39,"tag":48,"props":335,"children":336},{},[337],{"type":45,"value":338},"Do not present ZoomInfo as CRM ground truth. If a research response includes relationship or engagement context, label it as connector-surfaced context unless it is independently grounded by ~~CRM or the surrounding workflow.",{"type":39,"tag":54,"props":340,"children":342},{"id":341},"default-resolution-pattern",[343],{"type":45,"value":344},"Default Resolution Pattern",{"type":39,"tag":48,"props":346,"children":347},{},[348],{"type":45,"value":349},"Run these steps in order.",{"type":39,"tag":72,"props":351,"children":352},{},[353,391,434,445,450,455],{"type":39,"tag":76,"props":354,"children":355},{},[356,358],{"type":45,"value":357},"Classify the target:\n",{"type":39,"tag":123,"props":359,"children":360},{},[361,366,371,376,381,386],{"type":39,"tag":76,"props":362,"children":363},{},[364],{"type":45,"value":365},"company set",{"type":39,"tag":76,"props":367,"children":368},{},[369],{"type":45,"value":370},"contact set",{"type":39,"tag":76,"props":372,"children":373},{},[374],{"type":45,"value":375},"one known company",{"type":39,"tag":76,"props":377,"children":378},{},[379],{"type":45,"value":380},"one known person",{"type":39,"tag":76,"props":382,"children":383},{},[384],{"type":45,"value":385},"buyer intent topic",{"type":39,"tag":76,"props":387,"children":388},{},[389],{"type":45,"value":390},"lookalike or recommendation request",{"type":39,"tag":76,"props":392,"children":393},{},[394,396],{"type":45,"value":395},"Normalize hard filters before searching:\n",{"type":39,"tag":123,"props":397,"children":398},{},[399,404,409,414,419,424,429],{"type":39,"tag":76,"props":400,"children":401},{},[402],{"type":45,"value":403},"geography",{"type":39,"tag":76,"props":405,"children":406},{},[407],{"type":45,"value":408},"management level",{"type":39,"tag":76,"props":410,"children":411},{},[412],{"type":45,"value":413},"department or job family",{"type":39,"tag":76,"props":415,"children":416},{},[417],{"type":45,"value":418},"employee or revenue bands",{"type":39,"tag":76,"props":420,"children":421},{},[422],{"type":45,"value":423},"industry or company type",{"type":39,"tag":76,"props":425,"children":426},{},[427],{"type":45,"value":428},"technology filters",{"type":39,"tag":76,"props":430,"children":431},{},[432],{"type":45,"value":433},"intent topics",{"type":39,"tag":76,"props":435,"children":436},{},[437,438,443],{"type":45,"value":290},{"type":39,"tag":171,"props":439,"children":441},{"className":440},[],[442],{"type":45,"value":176},{"type":45,"value":444}," before search or intent flows whenever the connector expects standardized values.",{"type":39,"tag":76,"props":446,"children":447},{},[448],{"type":45,"value":449},"Resolve canonical company or contact identity before enrichment, research, or recommendation actions that depend on IDs.",{"type":39,"tag":76,"props":451,"children":452},{},[453],{"type":45,"value":454},"Verify that returned rows actually satisfy the user's hard constraints before summarizing them as matches.",{"type":39,"tag":76,"props":456,"children":457},{},[458],{"type":45,"value":459},"State what was not found, weakly supported, or connector-limited instead of smoothing gaps away.",{"type":39,"tag":54,"props":461,"children":463},{"id":462},"lookup-discipline",[464],{"type":45,"value":465},"Lookup Discipline",{"type":39,"tag":48,"props":467,"children":468},{},[469,470,475],{"type":45,"value":290},{"type":39,"tag":171,"props":471,"children":473},{"className":472},[],[474],{"type":45,"value":176},{"type":45,"value":476}," to retrieve supported values instead of guessing connector-specific categories.",{"type":39,"tag":123,"props":478,"children":479},{},[480,564,576,581],{"type":39,"tag":76,"props":481,"children":482},{},[483,485,491,492,498,499,505,506,512,513,519,520,526,527,533,534,540,541,547,548,554,556,562],{"type":45,"value":484},"Use it for ",{"type":39,"tag":171,"props":486,"children":488},{"className":487},[],[489],{"type":45,"value":490},"management-levels",{"type":45,"value":178},{"type":39,"tag":171,"props":493,"children":495},{"className":494},[],[496],{"type":45,"value":497},"metro-regions",{"type":45,"value":178},{"type":39,"tag":171,"props":500,"children":502},{"className":501},[],[503],{"type":45,"value":504},"industries",{"type":45,"value":178},{"type":39,"tag":171,"props":507,"children":509},{"className":508},[],[510],{"type":45,"value":511},"employee-count",{"type":45,"value":178},{"type":39,"tag":171,"props":514,"children":516},{"className":515},[],[517],{"type":45,"value":518},"departments",{"type":45,"value":178},{"type":39,"tag":171,"props":521,"children":523},{"className":522},[],[524],{"type":45,"value":525},"job-functions",{"type":45,"value":178},{"type":39,"tag":171,"props":528,"children":530},{"className":529},[],[531],{"type":45,"value":532},"company-types",{"type":45,"value":178},{"type":39,"tag":171,"props":535,"children":537},{"className":536},[],[538],{"type":45,"value":539},"revenue-ranges",{"type":45,"value":178},{"type":39,"tag":171,"props":542,"children":544},{"className":543},[],[545],{"type":45,"value":546},"tech-vendors",{"type":45,"value":178},{"type":39,"tag":171,"props":549,"children":551},{"className":550},[],[552],{"type":45,"value":553},"tech-products",{"type":45,"value":555},", and ",{"type":39,"tag":171,"props":557,"children":559},{"className":558},[],[560],{"type":45,"value":561},"intent-topics",{"type":45,"value":563}," when those constraints matter.",{"type":39,"tag":76,"props":565,"children":566},{},[567,569,574],{"type":45,"value":568},"Use the standardized identifier returned by ",{"type":39,"tag":171,"props":570,"children":572},{"className":571},[],[573],{"type":45,"value":176},{"type":45,"value":575}," where the downstream action expects an identifier, not a prettified display label.",{"type":39,"tag":76,"props":577,"children":578},{},[579],{"type":45,"value":580},"For technology-stack searches, resolve the vendor first, then resolve products for that exact vendor, then pass the returned product identifiers into search.",{"type":39,"tag":76,"props":582,"children":583},{},[584],{"type":45,"value":585},"For intent workflows, retrieve exact supported intent topics first. If the requested concept does not map cleanly to a supported topic, present the closest supported topic only when it is genuinely close; otherwise say the request is not precisely expressible through the current topic taxonomy.",{"type":39,"tag":48,"props":587,"children":588},{},[589],{"type":45,"value":590},"Do not invent lookup values or silently swap in an adjacent category without saying so.",{"type":39,"tag":54,"props":592,"children":594},{"id":593},"identifier-resolution",[595],{"type":45,"value":596},"Identifier Resolution",{"type":39,"tag":48,"props":598,"children":599},{},[600],{"type":45,"value":601},"Resolve entities carefully before ID-dependent actions.",{"type":39,"tag":603,"props":604,"children":606},"h3",{"id":605},"companies",[607],{"type":45,"value":608},"Companies",{"type":39,"tag":123,"props":610,"children":611},{},[612,625,637,642],{"type":39,"tag":76,"props":613,"children":614},{},[615,617,623],{"type":45,"value":616},"Prefer ",{"type":39,"tag":171,"props":618,"children":620},{"className":619},[],[621],{"type":45,"value":622},"companyId",{"type":45,"value":624},", domain, website, or ticker over company name alone.",{"type":39,"tag":76,"props":626,"children":627},{},[628,630,635],{"type":45,"value":629},"If the user provides only a company name and the next step requires enrichment, research, or a target-company ID, first use ",{"type":39,"tag":171,"props":631,"children":633},{"className":632},[],[634],{"type":45,"value":184},{"type":45,"value":636}," to find the canonical company row when identity is not obvious.",{"type":39,"tag":76,"props":638,"children":639},{},[640],{"type":45,"value":641},"If multiple plausible companies remain, use domain, headquarters, industry, or the user's surrounding context to disambiguate. If ambiguity still matters, present the candidate set instead of picking one quietly.",{"type":39,"tag":76,"props":643,"children":644},{},[645,647,652,653,659,661,667],{"type":45,"value":646},"For company enrichment, prefer ",{"type":39,"tag":171,"props":648,"children":650},{"className":649},[],[651],{"type":45,"value":622},{"type":45,"value":178},{"type":39,"tag":171,"props":654,"children":656},{"className":655},[],[657],{"type":45,"value":658},"domain",{"type":45,"value":660},", or ",{"type":39,"tag":171,"props":662,"children":664},{"className":663},[],[665],{"type":45,"value":666},"companyWebsite",{"type":45,"value":668}," over vague name-only input when available.",{"type":39,"tag":603,"props":670,"children":672},{"id":671},"contacts",[673],{"type":45,"value":674},"Contacts",{"type":39,"tag":123,"props":676,"children":677},{},[678,690,702,707],{"type":39,"tag":76,"props":679,"children":680},{},[681,682,688],{"type":45,"value":616},{"type":39,"tag":171,"props":683,"children":685},{"className":684},[],[686],{"type":45,"value":687},"personId",{"type":45,"value":689},", business email, or an exact full-name-plus-company combination over a name alone.",{"type":39,"tag":76,"props":691,"children":692},{},[693,695,700],{"type":45,"value":694},"If the user asks for contact research, similar contacts, or another person-ID-dependent workflow from a name, first use ",{"type":39,"tag":171,"props":696,"children":698},{"className":697},[],[699],{"type":45,"value":191},{"type":45,"value":701}," to resolve the target person.",{"type":39,"tag":76,"props":703,"children":704},{},[705],{"type":45,"value":706},"If the same name maps to multiple plausible people, keep the candidate list explicit and do not fabricate a single match.",{"type":39,"tag":76,"props":708,"children":709},{},[710],{"type":45,"value":711},"For contact enrichment, use the strongest supported identifier available; avoid broad name-only enrichment when a search pass can make the identity less ambiguous.",{"type":39,"tag":603,"props":713,"children":715},{"id":714},"runtime-shape",[716],{"type":45,"value":717},"Runtime Shape",{"type":39,"tag":123,"props":719,"children":720},{},[721,726,731],{"type":39,"tag":76,"props":722,"children":723},{},[724],{"type":45,"value":725},"Pass connector-returned identifiers in the runtime-compatible primitive shape the action accepts.",{"type":39,"tag":76,"props":727,"children":728},{},[729],{"type":45,"value":730},"When the connector surfaces a numeric ZoomInfo identifier and the destination action requires a numeric identifier at runtime, preserve it as numeric rather than rewriting it into prose or guessing a new value.",{"type":39,"tag":76,"props":732,"children":733},{},[734],{"type":45,"value":735},"If an action rejects an apparently valid identifier shape, retry only once with the directly corresponding connector-returned primitive when the target is unambiguous. If that still fails, report a connector contract mismatch and continue only with lower-risk available evidence.",{"type":39,"tag":54,"props":737,"children":739},{"id":738},"search-discipline",[740],{"type":45,"value":741},"Search Discipline",{"type":39,"tag":603,"props":743,"children":745},{"id":744},"company-search",[746],{"type":45,"value":747},"Company Search",{"type":39,"tag":123,"props":749,"children":750},{},[751,756,761,766,787],{"type":39,"tag":76,"props":752,"children":753},{},[754],{"type":45,"value":755},"Translate the user's ICP into explicit filters before searching.",{"type":39,"tag":76,"props":757,"children":758},{},[759],{"type":45,"value":760},"Prefer structured filters for geography, headcount, revenue, company type, funding, growth, and tech usage when the connector supports them.",{"type":39,"tag":76,"props":762,"children":763},{},[764],{"type":45,"value":765},"If the user asks for \"US companies\", \"California companies\", or another hard geography requirement, verify that each surfaced result matches the requested region before calling it a qualified match.",{"type":39,"tag":76,"props":767,"children":768},{},[769,771,777,779,785],{"type":45,"value":770},"If search returns close but imperfect rows, separate ",{"type":39,"tag":171,"props":772,"children":774},{"className":773},[],[775],{"type":45,"value":776},"Matches",{"type":45,"value":778}," from ",{"type":39,"tag":171,"props":780,"children":782},{"className":781},[],[783],{"type":45,"value":784},"Near Matches",{"type":45,"value":786}," rather than hiding the distinction.",{"type":39,"tag":76,"props":788,"children":789},{},[790],{"type":45,"value":791},"Do not claim exhaustive market coverage from a bounded result page.",{"type":39,"tag":603,"props":793,"children":795},{"id":794},"contact-search",[796],{"type":45,"value":797},"Contact Search",{"type":39,"tag":123,"props":799,"children":800},{},[801,806,811,816],{"type":39,"tag":76,"props":802,"children":803},{},[804],{"type":45,"value":805},"Use management level, department, function, company, and title filters together when that improves precision.",{"type":39,"tag":76,"props":807,"children":808},{},[809],{"type":45,"value":810},"For role-family requests such as \"VP, Director, or Head of RevOps\", start with the narrowest structured interpretation that is likely to work.",{"type":39,"tag":76,"props":812,"children":813},{},[814],{"type":45,"value":815},"If a single broad title query returns sparse, clearly incomplete, or off-target results, split the role family into a small number of targeted searches, merge duplicates, and summarize the deduped shortlist.",{"type":39,"tag":76,"props":817,"children":818},{},[819],{"type":45,"value":820},"Prefer directly returned business fields. Do not infer private email addresses, personal phones, or missing professional profiles.",{"type":39,"tag":603,"props":822,"children":824},{"id":823},"intent-search",[825],{"type":45,"value":826},"Intent Search",{"type":39,"tag":123,"props":828,"children":829},{},[830,855,860,865],{"type":39,"tag":76,"props":831,"children":832},{},[833,835,840,842,847,848,853],{"type":45,"value":834},"Always resolve exact intent topics with ",{"type":39,"tag":171,"props":836,"children":838},{"className":837},[],[839],{"type":45,"value":176},{"type":45,"value":841}," before ",{"type":39,"tag":171,"props":843,"children":845},{"className":844},[],[846],{"type":45,"value":198},{"type":45,"value":321},{"type":39,"tag":171,"props":849,"children":851},{"className":850},[],[852],{"type":45,"value":223},{"type":45,"value":854},".",{"type":39,"tag":76,"props":856,"children":857},{},[858],{"type":45,"value":859},"Keep topic meaning visible in the answer so the user can see what was actually searched.",{"type":39,"tag":76,"props":861,"children":862},{},[863],{"type":45,"value":864},"If returned intent topics are materially narrower, broader, or adjacent to the user's concept, say so.",{"type":39,"tag":76,"props":866,"children":867},{},[868],{"type":45,"value":869},"If the topic lookup or search path cannot support the requested concept faithfully, report that limitation instead of overstating the result.",{"type":39,"tag":54,"props":871,"children":873},{"id":872},"enrichment-and-research-sequencing",[874],{"type":45,"value":875},"Enrichment And Research Sequencing",{"type":39,"tag":48,"props":877,"children":878},{},[879],{"type":45,"value":880},"Use cheap narrowing steps before expensive or less precise actions when practical.",{"type":39,"tag":123,"props":882,"children":883},{},[884,889,894,899,904],{"type":39,"tag":76,"props":885,"children":886},{},[887],{"type":45,"value":888},"Use search first when the entity itself is unclear.",{"type":39,"tag":76,"props":890,"children":891},{},[892],{"type":45,"value":893},"Use structured enrichment when the user wants firmographic fields, contactability fields, or batch-ready tabular output.",{"type":39,"tag":76,"props":895,"children":896},{},[897],{"type":45,"value":898},"Use narrative research when the user wants a briefing, situational awareness, or prepare-for-meeting style synthesis.",{"type":39,"tag":76,"props":900,"children":901},{},[902],{"type":45,"value":903},"For top-N discovery requests, do not enrich every raw candidate by default. Narrow first, then enrich only the shortlisted set that materially improves the answer.",{"type":39,"tag":76,"props":905,"children":906},{},[907],{"type":45,"value":908},"When a similarity or recommendation workflow returns sparse person or company detail, add a targeted enrichment pass only when the user asked for actionable detail or when the surrounding workflow needs it.",{"type":39,"tag":54,"props":910,"children":912},{"id":911},"similarity-and-recommendation-flows",[913],{"type":45,"value":914},"Similarity And Recommendation Flows",{"type":39,"tag":603,"props":916,"children":918},{"id":917},"similar-companies",[919],{"type":45,"value":920},"Similar Companies",{"type":39,"tag":123,"props":922,"children":923},{},[924,935,940],{"type":39,"tag":76,"props":925,"children":926},{},[927,928,933],{"type":45,"value":290},{"type":39,"tag":171,"props":929,"children":931},{"className":930},[],[932],{"type":45,"value":252},{"type":45,"value":934}," when the user asks for competitor-like, lookalike, or adjacent-account discovery.",{"type":39,"tag":76,"props":936,"children":937},{},[938],{"type":45,"value":939},"If the reference company is ambiguous, resolve it before the similarity call.",{"type":39,"tag":76,"props":941,"children":942},{},[943],{"type":45,"value":944},"If the user wants a usable market list rather than raw similarity results, enrich the final shortlist just enough to supply requested basics such as website, location, employee range, or a concise description.",{"type":39,"tag":603,"props":946,"children":948},{"id":947},"similar-contacts",[949],{"type":45,"value":950},"Similar Contacts",{"type":39,"tag":123,"props":952,"children":953},{},[954,974,992],{"type":39,"tag":76,"props":955,"children":956},{},[957,959,965,967,972],{"type":45,"value":958},"Resolve ",{"type":39,"tag":171,"props":960,"children":962},{"className":961},[],[963],{"type":45,"value":964},"referencePersonId",{"type":45,"value":966}," with ",{"type":39,"tag":171,"props":968,"children":970},{"className":969},[],[971],{"type":45,"value":191},{"type":45,"value":973}," when the user gives a name.",{"type":39,"tag":76,"props":975,"children":976},{},[977,978,984,985,990],{"type":45,"value":958},{"type":39,"tag":171,"props":979,"children":981},{"className":980},[],[982],{"type":45,"value":983},"targetCompanyId",{"type":45,"value":966},{"type":39,"tag":171,"props":986,"children":988},{"className":987},[],[989],{"type":45,"value":184},{"type":45,"value":991}," when the user wants lookalike contacts inside a specific account.",{"type":39,"tag":76,"props":993,"children":994},{},[995],{"type":45,"value":996},"Explain recommendations using returned metadata rather than making up a similarity rationale.",{"type":39,"tag":603,"props":998,"children":1000},{"id":999},"recommended-contacts",[1001],{"type":45,"value":1002},"Recommended Contacts",{"type":39,"tag":123,"props":1004,"children":1005},{},[1006,1011,1046,1051],{"type":39,"tag":76,"props":1007,"children":1008},{},[1009],{"type":45,"value":1010},"Resolve the target company first.",{"type":39,"tag":76,"props":1012,"children":1013},{},[1014,1016],{"type":45,"value":1015},"Choose the recommendation use case that matches the user intent:\n",{"type":39,"tag":123,"props":1017,"children":1018},{},[1019,1028,1037],{"type":39,"tag":76,"props":1020,"children":1021},{},[1022],{"type":39,"tag":171,"props":1023,"children":1025},{"className":1024},[],[1026],{"type":45,"value":1027},"PROSPECTING",{"type":39,"tag":76,"props":1029,"children":1030},{},[1031],{"type":39,"tag":171,"props":1032,"children":1034},{"className":1033},[],[1035],{"type":45,"value":1036},"DEAL_ACCELERATION",{"type":39,"tag":76,"props":1038,"children":1039},{},[1040],{"type":39,"tag":171,"props":1041,"children":1043},{"className":1042},[],[1044],{"type":45,"value":1045},"RENEWAL_AND_GROWTH",{"type":39,"tag":76,"props":1047,"children":1048},{},[1049],{"type":45,"value":1050},"Explain what the use case means in the final readout when it affects interpretation.",{"type":39,"tag":76,"props":1052,"children":1053},{},[1054],{"type":45,"value":1055},"Treat recommendation scores as ranking signals, not response probabilities or guaranteed success.",{"type":39,"tag":54,"props":1057,"children":1059},{"id":1058},"credit-aware-behavior",[1060],{"type":45,"value":1061},"Credit-Aware Behavior",{"type":39,"tag":48,"props":1063,"children":1064},{},[1065],{"type":45,"value":1066},"Prefer free or lower-cost discovery steps before credit-consuming enrichment or AI research when the workflow permits it.",{"type":39,"tag":123,"props":1068,"children":1069},{},[1070,1099,1134],{"type":39,"tag":76,"props":1071,"children":1072},{},[1073,1074,1079,1080,1085,1086,1091,1092,1097],{"type":45,"value":290},{"type":39,"tag":171,"props":1075,"children":1077},{"className":1076},[],[1078],{"type":45,"value":176},{"type":45,"value":178},{"type":39,"tag":171,"props":1081,"children":1083},{"className":1082},[],[1084],{"type":45,"value":184},{"type":45,"value":178},{"type":39,"tag":171,"props":1087,"children":1089},{"className":1088},[],[1090],{"type":45,"value":191},{"type":45,"value":555},{"type":39,"tag":171,"props":1093,"children":1095},{"className":1094},[],[1096],{"type":45,"value":198},{"type":45,"value":1098}," to narrow scope first when appropriate.",{"type":39,"tag":76,"props":1100,"children":1101},{},[1102,1103,1108,1109,1114,1115,1120,1121,1126,1127,1132],{"type":45,"value":290},{"type":39,"tag":171,"props":1104,"children":1106},{"className":1105},[],[1107],{"type":45,"value":209},{"type":45,"value":178},{"type":39,"tag":171,"props":1110,"children":1112},{"className":1111},[],[1113],{"type":45,"value":216},{"type":45,"value":178},{"type":39,"tag":171,"props":1116,"children":1118},{"className":1117},[],[1119],{"type":45,"value":223},{"type":45,"value":178},{"type":39,"tag":171,"props":1122,"children":1124},{"className":1123},[],[1125],{"type":45,"value":234},{"type":45,"value":555},{"type":39,"tag":171,"props":1128,"children":1130},{"className":1129},[],[1131],{"type":45,"value":241},{"type":45,"value":1133}," when the user has asked for the stronger result those actions provide.",{"type":39,"tag":76,"props":1135,"children":1136},{},[1137],{"type":45,"value":1138},"For broad batch requests, make the action scope visible in the answer and avoid unnecessary enrichment of obviously weak candidates.",{"type":39,"tag":48,"props":1140,"children":1141},{},[1142],{"type":45,"value":1143},"Do not add friction for a small, clearly requested enrichment task. Do be explicit when the connector result may have consumed meaningful credits or when a narrower rerun would be materially cheaper.",{"type":39,"tag":54,"props":1145,"children":1147},{"id":1146},"failure-handling",[1148],{"type":45,"value":1149},"Failure Handling",{"type":39,"tag":123,"props":1151,"children":1152},{},[1153,1166,1171,1176,1181,1186],{"type":39,"tag":76,"props":1154,"children":1155},{},[1156,1158,1164],{"type":45,"value":1157},"If the connector returns no results, say ",{"type":39,"tag":171,"props":1159,"children":1161},{"className":1160},[],[1162],{"type":45,"value":1163},"no clear ZoomInfo match returned",{"type":45,"value":1165}," rather than inventing one.",{"type":39,"tag":76,"props":1167,"children":1168},{},[1169],{"type":45,"value":1170},"If results violate a hard filter, exclude them from the qualified set and mention the mismatch.",{"type":39,"tag":76,"props":1172,"children":1173},{},[1174],{"type":45,"value":1175},"If a required lookup value is unavailable, say which constraint could not be represented cleanly.",{"type":39,"tag":76,"props":1177,"children":1178},{},[1179],{"type":45,"value":1180},"If a research response is thin or generic, preserve the useful parts but label coverage as limited.",{"type":39,"tag":76,"props":1182,"children":1183},{},[1184],{"type":45,"value":1185},"If a recommendation or similarity call yields weak actionability, say what extra enrichment or user context would be needed.",{"type":39,"tag":76,"props":1187,"children":1188},{},[1189],{"type":45,"value":1190},"If the connector behavior appears inconsistent with its own action contract, describe the inconsistency plainly in the answer when it affects completeness or confidence.",{"type":39,"tag":54,"props":1192,"children":1194},{"id":1193},"output-rules",[1195],{"type":45,"value":1196},"Output Rules",{"type":39,"tag":123,"props":1198,"children":1199},{},[1200,1205,1210,1247,1259,1264,1269],{"type":39,"tag":76,"props":1201,"children":1202},{},[1203],{"type":45,"value":1204},"Prefer compact tables for candidate lists, enrichment outputs, similar-company lists, and contact recommendations.",{"type":39,"tag":76,"props":1206,"children":1207},{},[1208],{"type":45,"value":1209},"Prefer clickable connector-returned links when available; never construct guessed links from opaque IDs.",{"type":39,"tag":76,"props":1211,"children":1212},{},[1213,1215],{"type":45,"value":1214},"Separate:\n",{"type":39,"tag":123,"props":1216,"children":1217},{},[1218,1227,1238],{"type":39,"tag":76,"props":1219,"children":1220},{},[1221],{"type":39,"tag":171,"props":1222,"children":1224},{"className":1223},[],[1225],{"type":45,"value":1226},"Qualified matches",{"type":39,"tag":76,"props":1228,"children":1229},{},[1230,1236],{"type":39,"tag":171,"props":1231,"children":1233},{"className":1232},[],[1234],{"type":45,"value":1235},"Near matches",{"type":45,"value":1237}," when useful",{"type":39,"tag":76,"props":1239,"children":1240},{},[1241],{"type":39,"tag":171,"props":1242,"children":1244},{"className":1243},[],[1245],{"type":45,"value":1246},"Gaps \u002F connector limitations",{"type":39,"tag":76,"props":1248,"children":1249},{},[1250,1252,1258],{"type":45,"value":1251},"Keep sourced facts separate from ",{"type":39,"tag":171,"props":1253,"children":1255},{"className":1254},[],[1256],{"type":45,"value":1257},"Inference:",{"type":45,"value":854},{"type":39,"tag":76,"props":1260,"children":1261},{},[1262],{"type":45,"value":1263},"Do not guess emails, phone numbers, exact intent, or confidence levels not surfaced by the connector.",{"type":39,"tag":76,"props":1265,"children":1266},{},[1267],{"type":45,"value":1268},"When the answer depends on connector-reported fields or recommendation metadata, say so directly.",{"type":39,"tag":76,"props":1270,"children":1271},{},[1272],{"type":45,"value":1273},"If the user's request asked for a ranked list, rank by explicit connector signal or stated criteria, not by invisible model preference.",{"type":39,"tag":1275,"props":1276,"children":1278},"h4",{"id":1277},"output-format",[1279],{"type":45,"value":1280},"Output Format",{"type":39,"tag":1282,"props":1283,"children":1287},"pre",{"className":1284,"code":1286,"language":45},[1285],"language-text","# [ZoomInfo Search \u002F Enrichment \u002F Research]\n\n## Qualified Matches\n\n| Company \u002F Person | Key Match Evidence | Useful Detail | Source |\n| --- | --- | --- | --- |\n| [Result] | [Hard filters satisfied] | [Returned field] | [Link or connector source] |\n\n## Near Matches\n\n- [Result + exact mismatch, when useful]\n\n## Gaps \u002F Connector Limitations\n\n- [Missing field, unsupported filter, bounded coverage, ambiguity, or credit-aware next step]\n\n---\n\n{Follow the instructions and output format\u002Fconditions in [Limitations and Improvements](..\u002Findex\u002FSKILL.md#limitations-and-improvements)}\n\n{Follow the instructions and output format\u002Fconditions in [Next Steps](..\u002Findex\u002FSKILL.md#4-next-steps)}\n",[1288],{"type":39,"tag":171,"props":1289,"children":1291},{"__ignoreMap":1290},"",[1292],{"type":45,"value":1286},{"items":1294,"total":1401},[1295,1308,1324,1337,1353,1369,1386],{"slug":1296,"name":1296,"fn":1297,"description":1298,"org":1299,"tags":1300,"stars":22,"repoUrl":23,"updatedAt":1307},"analyze-account-signals","analyze account signals for sales intelligence","Use when the user wants to know what changed with one account, monitor an owner portfolio or watchlist, or rank accounts needing attention from recent evidence. Produce an evidence-backed account brief or bounded watchlist summary with recommended actions.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1301,1304,1305,1306],{"name":1302,"slug":1303,"type":15},"Analytics","analytics",{"name":17,"slug":18,"type":15},{"name":13,"slug":14,"type":15},{"name":20,"slug":21,"type":15},"2026-07-01T07:54:11.79288",{"slug":1309,"name":1309,"fn":1310,"description":1311,"org":1312,"tags":1313,"stars":22,"repoUrl":23,"updatedAt":1323},"analyze-data-quality","assess data quality for analysis","Assess whether structured data, query results, dashboards, or analytical evidence are trustworthy enough to use. Use when the task is to check data quality, reconcile conflicting sources or metric definitions, or decide whether evidence is safe to cite.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1314,1317,1320],{"name":1315,"slug":1316,"type":15},"Audit","audit",{"name":1318,"slug":1319,"type":15},"Data Engineering","data-engineering",{"name":1321,"slug":1322,"type":15},"Data Quality","data-quality","2026-07-01T07:55:01.146961",{"slug":1325,"name":1325,"fn":1326,"description":1327,"org":1328,"tags":1329,"stars":22,"repoUrl":23,"updatedAt":1336},"answers-ask-user-input","request missing context from users","Use when a small amount of missing context would materially improve the answer and tappable options plus a free-text answer can gather it efficiently.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1330,1333],{"name":1331,"slug":1332,"type":15},"Communications","communications",{"name":1334,"slug":1335,"type":15},"Productivity","productivity","2026-07-14T05:43:36.096323",{"slug":1338,"name":1338,"fn":1339,"description":1340,"org":1341,"tags":1342,"stars":22,"repoUrl":23,"updatedAt":1352},"apollo","prospect and enrich leads with Apollo","Use only when a focused Sales workflow has selected a present and connected Apollo connector, or the user explicitly asks for Apollo prospecting, enrichment, Company Details, records, sequences, or outbound planning. Apply Apollo v2-specific behavior only after verifying app version 2.0.0 or later.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1343,1345,1348,1351],{"name":1344,"slug":1338,"type":15},"Apollo",{"name":1346,"slug":1347,"type":15},"Lead Enrichment","lead-enrichment",{"name":1349,"slug":1350,"type":15},"Prospecting","prospecting",{"name":20,"slug":21,"type":15},"2026-07-14T05:43:34.800076",{"slug":1316,"name":1316,"fn":1354,"description":1355,"org":1356,"tags":1357,"stars":22,"repoUrl":23,"updatedAt":1368},"audit product flows and user journeys","Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1358,1359,1362,1365],{"name":1315,"slug":1316,"type":15},{"name":1360,"slug":1361,"type":15},"Design","design",{"name":1363,"slug":1364,"type":15},"Product Management","product-management",{"name":1366,"slug":1367,"type":15},"UX Design","ux-design","2026-07-01T07:54:30.613428",{"slug":1370,"name":1370,"fn":1371,"description":1372,"org":1373,"tags":1374,"stars":22,"repoUrl":23,"updatedAt":1385},"build-business-case","build customer-led business cases and ROI","Review commercial proposals and build customer-led business cases, ROI or value models, pricing or investment rationales, executive summaries, and customer-ready value stories tied to a customer, workflow, initiative, or decision.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1375,1378,1381,1384],{"name":1376,"slug":1377,"type":15},"Content Creation","content-creation",{"name":1379,"slug":1380,"type":15},"Finance","finance",{"name":1382,"slug":1383,"type":15},"Financial Modeling","financial-modeling",{"name":20,"slug":21,"type":15},"2026-07-01T07:54:02.779003",{"slug":1387,"name":1387,"fn":1388,"description":1389,"org":1390,"tags":1391,"stars":22,"repoUrl":23,"updatedAt":1400},"build-competitive-brief","build competitive briefs and battlecards","Use when the user wants a competitor or vendor comparison, market-landscape analysis, battlecard, objection package, positioning brief, or account-specific competitive view. Produce an evidence-backed comparison, guidance, and brief, using supplied materials, connected research, and public evidence when appropriate.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1392,1395,1398,1399],{"name":1393,"slug":1394,"type":15},"Competitive Intelligence","competitive-intelligence",{"name":1396,"slug":1397,"type":15},"Marketing","marketing",{"name":13,"slug":14,"type":15},{"name":20,"slug":21,"type":15},"2026-07-01T07:54:13.073252",43,{"items":1403,"total":1604},[1404,1425,1448,1465,1481,1500,1517,1531,1547,1561,1573,1588],{"slug":1405,"name":1405,"fn":1406,"description":1407,"org":1408,"tags":1409,"stars":1422,"repoUrl":1423,"updatedAt":1424},"prior-auth-packet-builder","build healthcare prior authorization packets","Build a concise prior authorization packet from local case files and payer policy docs.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1410,1413,1416,1419],{"name":1411,"slug":1412,"type":15},"Documents","documents",{"name":1414,"slug":1415,"type":15},"Healthcare","healthcare",{"name":1417,"slug":1418,"type":15},"Insurance","insurance",{"name":1420,"slug":1421,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-04-16T05:11:39.180399",{"slug":1426,"name":1426,"fn":1427,"description":1428,"org":1429,"tags":1430,"stars":1445,"repoUrl":1446,"updatedAt":1447},"aspnet-core","build ASP.NET Core web applications","Build, review, refactor, or architect ASP.NET Core web applications using current official guidance for .NET web development. Use when working on Blazor Web Apps, Razor Pages, MVC, Minimal APIs, controller-based Web APIs, SignalR, gRPC, middleware, dependency injection, configuration, authentication, authorization, testing, performance, deployment, or ASP.NET Core upgrades.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1431,1434,1436,1439,1442],{"name":1432,"slug":1433,"type":15},".NET","dotnet",{"name":1435,"slug":1426,"type":15},"ASP.NET Core",{"name":1437,"slug":1438,"type":15},"Blazor","blazor",{"name":1440,"slug":1441,"type":15},"C#","csharp",{"name":1443,"slug":1444,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":1449,"name":1449,"fn":1450,"description":1451,"org":1452,"tags":1453,"stars":1445,"repoUrl":1446,"updatedAt":1464},"chatgpt-apps","build ChatGPT Apps SDK applications","Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or CSP or domain settings, or produce a docs-aligned project scaffold. Prefer a docs-first workflow by invoking the openai-docs skill or OpenAI developer docs MCP tools before generating code.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1454,1457,1460,1463],{"name":1455,"slug":1456,"type":15},"Apps SDK","apps-sdk",{"name":1458,"slug":1459,"type":15},"ChatGPT","chatgpt",{"name":1461,"slug":1462,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":1466,"name":1466,"fn":1467,"description":1468,"org":1469,"tags":1470,"stars":1445,"repoUrl":1446,"updatedAt":1480},"cli-creator","build CLIs from API docs","Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read\u002Fwrite commands, return stable JSON, manage auth, and pair with a companion skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1471,1474,1477],{"name":1472,"slug":1473,"type":15},"API Development","api-development",{"name":1475,"slug":1476,"type":15},"CLI","cli",{"name":1478,"slug":1479,"type":15},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":1482,"name":1482,"fn":1483,"description":1484,"org":1485,"tags":1486,"stars":1445,"repoUrl":1446,"updatedAt":1499},"cloudflare-deploy","deploy projects to Cloudflare","Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1487,1490,1493,1496],{"name":1488,"slug":1489,"type":15},"Cloudflare","cloudflare",{"name":1491,"slug":1492,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":1494,"slug":1495,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":1497,"slug":1498,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":1501,"name":1501,"fn":1502,"description":1503,"org":1504,"tags":1505,"stars":1445,"repoUrl":1446,"updatedAt":1516},"define-goal","define and set measurable project goals","Help the user define a concrete, measurable goal before starting work, especially when they ask to use the goal tool, create a goal, set an objective, clarify success criteria, or turn a fuzzy intention into a quantitative outcome. Use this skill for goal creation and goal refinement only; it does not manage durable snapshots, decision logs, or long-running execution artifacts.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1506,1507,1510,1513],{"name":1334,"slug":1335,"type":15},{"name":1508,"slug":1509,"type":15},"Project Management","project-management",{"name":1511,"slug":1512,"type":15},"Strategy","strategy",{"name":1514,"slug":1515,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":1518,"name":1518,"fn":1519,"description":1520,"org":1521,"tags":1522,"stars":1445,"repoUrl":1446,"updatedAt":1530},"figma","translate Figma designs into code","Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1523,1524,1526,1529],{"name":1360,"slug":1361,"type":15},{"name":1525,"slug":1518,"type":15},"Figma",{"name":1527,"slug":1528,"type":15},"Frontend","frontend",{"name":1461,"slug":1462,"type":15},"2026-04-12T05:06:47.939943",{"slug":1532,"name":1532,"fn":1533,"description":1534,"org":1535,"tags":1536,"stars":1445,"repoUrl":1446,"updatedAt":1546},"figma-code-connect-components","connect Figma designs to code components","Connects Figma design components to code components using Code Connect mapping tools. Use when user says \"code connect\", \"connect this component to code\", \"map this component\", \"link component to code\", \"create code connect mapping\", or wants to establish mappings between Figma designs and code implementations. For canvas writes via `use_figma`, use `figma-use`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1537,1538,1541,1542,1543],{"name":1360,"slug":1361,"type":15},{"name":1539,"slug":1540,"type":15},"Design System","design-system",{"name":1525,"slug":1518,"type":15},{"name":1527,"slug":1528,"type":15},{"name":1544,"slug":1545,"type":15},"UI Components","ui-components","2026-05-10T05:59:52.971881",{"slug":1548,"name":1548,"fn":1549,"description":1550,"org":1551,"tags":1552,"stars":1445,"repoUrl":1446,"updatedAt":1560},"figma-create-design-system-rules","generate design system rules from Figma","Generates custom design system rules for the user's codebase. Use when user says \"create design system rules\", \"generate rules for my project\", \"set up design rules\", \"customize design system guidelines\", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server connection.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1553,1554,1555,1558,1559],{"name":1360,"slug":1361,"type":15},{"name":1539,"slug":1540,"type":15},{"name":1556,"slug":1557,"type":15},"Documentation","documentation",{"name":1525,"slug":1518,"type":15},{"name":1527,"slug":1528,"type":15},"2026-05-16T06:07:47.821474",{"slug":1562,"name":1562,"fn":1563,"description":1564,"org":1565,"tags":1566,"stars":1445,"repoUrl":1446,"updatedAt":1572},"figma-implement-design","translate Figma designs into application code","Translates Figma designs into production-ready application code with 1:1 visual fidelity. Use when implementing UI code from Figma files, when user mentions \"implement design\", \"generate code\", \"implement component\", provides Figma URLs, or asks to build components matching Figma specs. For Figma canvas writes via `use_figma`, use `figma-use`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1567,1568,1569,1570,1571],{"name":1360,"slug":1361,"type":15},{"name":1525,"slug":1518,"type":15},{"name":1527,"slug":1528,"type":15},{"name":1544,"slug":1545,"type":15},{"name":1443,"slug":1444,"type":15},"2026-05-16T06:07:40.583615",{"slug":1574,"name":1574,"fn":1575,"description":1576,"org":1577,"tags":1578,"stars":1445,"repoUrl":1446,"updatedAt":1587},"hatch-pet","create animated pets for Codex","Create, repair, validate, visually QA, and package Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual references. Use when a user wants a lightweight-worker Codex pet workflow, a non-pixel custom pet style, a prospect or company mascot pet, or a full 8x9 animated pet atlas with transparent unused cells, QA contact sheets, and pet.json packaging. This skill composes the installed $imagegen system skill for visual generation and uses bundled scripts for deterministic spritesheet assembly.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1579,1582,1583,1586],{"name":1580,"slug":1581,"type":15},"Animation","animation",{"name":1478,"slug":1479,"type":15},{"name":1584,"slug":1585,"type":15},"Creative","creative",{"name":1360,"slug":1361,"type":15},"2026-05-02T05:31:48.48485",{"slug":1589,"name":1589,"fn":1590,"description":1591,"org":1592,"tags":1593,"stars":1445,"repoUrl":1446,"updatedAt":1603},"imagegen","generate and edit raster images","Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG\u002Fvector\u002Fcode-native assets, extending an established icon or logo system, or building the visual directly in HTML\u002FCSS\u002Fcanvas.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1594,1595,1596,1599,1602],{"name":1584,"slug":1585,"type":15},{"name":1360,"slug":1361,"type":15},{"name":1597,"slug":1598,"type":15},"Image Generation","image-generation",{"name":1600,"slug":1601,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",675]