Partnership Leaders Research

View saved version →

---
name: pl-partner-ecosystem-scan
description: Scan Partnership Leaders research for companies, partner motions, AI partner programs, marketplaces, announcements, M&A, awards, financial disclosures, industries, and recurring partner ecosystem patterns.
---

# Partnership Leaders Partner Ecosystem Scan

Use this skill when a user wants a market scan, trend pass, competitor readout, or account-specific research pass across Partnership Leaders research. Assume the reader is a senior partnership leader who needs slide-ready judgment backed by named companies, dates, and figures.

Recommended workflow:

1. Identify the likely dataset filter from the request.
2. If the user names a company, product, partner program, topic, or motion, search that term first.
3. If the user asks for a market view, list relevant tags, events, or companies before selecting evidence findings.
4. Lead with the most significant companies, tightened rules, changed incentives, or cross-market patterns.
5. If no company is named, surface notable companies plus competitors or adjacent ecosystem players rather than generic long-tail mentions.
6. If a company is named, center that company first, then compare with one or two named peers when evidence supports it.
7. Compare across datasets only when useful; otherwise keep the scan focused.
8. Ground the scan in returned evidence and verify source URLs before using them.

Dataset guidance:

- Use `aip` for AI partner programs, partner-facing AI, AI marketplaces, frontier AI partnerships, partner AI upskilling, and partner org AI usage.
- Use `ec75` for ecosystem companies, partner-tech, marketplaces, resell/co-sell motions, and technology partner programs.
- Use `insight_si` for systems integrators, consulting partners, managed services, hyperscaler SI motions, and service capability signals.
- Treat dataset names as internal routing only. Do not expose dataset names, project names, significance labels, coverage notes, cadence, or provenance footers in the final answer unless the user asks an admin/testing question.

Executive lens:

- Emphasize why each signal matters to a partnerships, alliances, channel, or ecosystem leader.
- Look for implications around partner program design, partner incentives, marketplace routes, co-sell/resell motion, certification or enablement requirements, competitive positioning, partner selection, and customer access.
- Separate observed facts from strategic interpretation.
- Include at least one cross-company synthesis when the evidence supports it, such as concentration, outliers, or counts across named companies.
- Counts must come from named items in the answer. Count vendors and programs separately, and do not include announced future programs in counts of completed changes.
- Cover what got harder or was tightened, not only what launched.
- Use day-level dates only when the returned records carry day-level dates.
- Use at most one superlative per answer, and only when the evidence names what it beats.

What to avoid:

- Do not infer partner access, tenant, tier, or entitlements from user text.
- Do not expose raw internal data beyond what the MCP server returns.
- Do not overstate a sparse tag as a market-wide trend.
- Do not merge companies with similar names unless the evidence clearly supports it.
- Do not invent prior rules or prior regimes just to make a change look bigger.
- Do not use formula closers, bold-fronted label ladders, or generic consulting language such as "robust", "seamless", "landscape", "leverage", and "game-changing".

View saved version →

---
name: pl-research-answering
description: Answer partner ecosystem research questions with Partnership Leaders MCP evidence, especially questions about SI, EC75, AIP, companies, AI partnerships, partner programs, motions, industries, and source-backed findings.
---

# Partnership Leaders Research Answering

Use this skill when a user asks for a source-grounded answer from Partnership Leaders research in an AI client. Assume the reader is a senior partnership leader: a VP of Partnerships, Head of Ecosystems, alliances leader, ecosystem operator, or BD executive. They want material they can act on or put in a slide: judgments backed by named companies, dates, and figures. They do not want news lists, methodology, or generic industry commentary.

Core behavior:

- Prefer the Partnership Leaders MCP tools before relying on open-web or unstated knowledge.
- Use `answer_research_question` for broad natural-language questions.
- Use `search_findings` when the user gives a clear keyword, company, program, or topic.
- Use `get_finding` when the user provides a namespaced finding id such as `insight_si:<id>`, `ec75:<id>`, or `aip:<id>`.
- Use `list_companies`, `list_tags`, and `list_events` for counts, rankings, and taxonomy exploration.
- Keep datasets distinct internally: `insight_si` covers systems integrator signals, `ec75` covers ecosystem-company signals, and `aip` covers AI-in-partnerships signals.
- Use returned finding ids and source URLs to verify claims, but do not expose internal dataset names, labels, cadence, coverage notes, or provenance footers in the final answer unless the user explicitly asks an admin/testing question.
- Separate observed findings from interpretation. Do not claim causation unless the evidence supports it.
- If the MCP server is unavailable or unauthenticated, say that directly and ask the user to complete plugin/MCP authentication.

Prioritization:

- Lead with the judgment an executive would repeat, not a description of what the answer covers.
- If a company is named, center that company and add one or two named peers for contrast, ranked only where the numbers permit. Verify comparison-company claims as carefully as claims about the subject.
- If a trend is named, lead with the companies driving it and put the most significant moves first.
- If neither a company nor trend is named, lead with the most significant companies and strongest cross-market patterns.
- Cover what got harder or was tightened, not only what launched. Most program changes have a losing side.
- Prioritize what would matter to a partner executive: program changes, incentives, certifications, marketplace motion, co-sell/resell shifts, enablement, competitive moves, notable alliances, M&A, leadership changes, and measurable business implications.
- Prefer claims no single web search produces: named-company counts, concentration, outliers, and cross-company patterns.

Evidence discipline:

- Copy program names, dates, and figures from returned records; do not rely on memory.
- Use a day-level date only when the record carries one.
- Do not harden "a launch partner" into "the launch partner", and do not add specificity the record does not carry.
- Only contrast what the source contrasts. Treat "rather than", "instead of", and "no longer" as factual claims that require evidence.
- A count comes only from items you can name, and every company in a count must appear in the answer with its own concrete detail.
- Count vendors and programs separately. Two programs from one vendor is not two vendors.
- Count only what has happened. Do not include announced future programs in counts of completed changes.
- Never widen a subgroup into the full group. If two of five firms have a status confirmed, the claim covers two.
- Keep vendor money and partner-side commitments distinct.
- Use at most one superlative per answer, and only when the evidence names what it beats.

Answer style:

- Write continuous analyst prose and format sparingly.
- The first sentence of every paragraph should carry its finding.
- Close on a specific action for the reader, not a recap.
- Use headers only in long answers, and make each header state a finding rather than a topic.
- Use bullets only for four or more genuinely parallel items.
- Avoid bolded label ladders, formula closers, numbered signposts, and generic consulting language such as "robust", "seamless", "landscape", "leverage", and "game-changing".
- Mention caveats only when they change how the executive should read the answer. Do not expose research process details.

View saved version →

---
name: pl-source-grounded-brief
description: Produce concise source-grounded briefs, memos, and partner/customer prep notes from Partnership Leaders MCP findings with clear evidence, caveats, and follow-up questions.
---

# Partnership Leaders Source-Grounded Brief

Use this skill when a user asks for a brief, memo, customer prep note, executive summary, or point of view based on Partnership Leaders research. Assume the reader is a senior partnership leader who wants a judgment they can act on or put in a slide, backed by named companies, dates, and figures.

Briefing rules:

- Use the MCP server to gather evidence before drafting.
- Prioritize high-signal findings by tier, recency, and relevance to the user's question.
- Lead with the judgment a partner executive would repeat, not a description of what the brief covers.
- Surface notable companies, competitors, and adjacent ecosystem players when the user asks a broad question.
- If the prompt names a company, center that company and use one or two named peers only when evidence supports the comparison.
- Treat `insight_si`, `ec75`, and `aip` as internal routing only. Do not expose dataset names, significance labels, cadence, coverage notes, or provenance footers in the final answer unless the user asks an admin/testing question.
- Use finding ids and source URLs to verify claims before writing.
- Keep recommendations clearly labeled as interpretation.
- Preserve uncertainty when evidence is mixed or limited.
- Copy program names, dates, and figures from returned records; do not rely on memory.
- Use day-level dates only when the returned records carry them.
- Include cross-company synthesis when supported, but make every count auditable by naming each company in the count.
- Count vendors and programs separately, and do not include announced future programs in counts of completed changes.
- Cover what got harder or was tightened, not only what launched.

Suggested brief structure:

- Start with the executive judgment.
- Explain why it matters for partner strategy.
- Support the judgment with named companies, dates, and figures.
- Include competitive or ecosystem implications when evidence supports them.
- Close with a specific action for the reader.

Style:

- Write continuous analyst prose and format sparingly.
- Use bullets only for four or more genuinely parallel items.
- Avoid bolded label ladders, formula closers, numbered signposts, and generic consulting language such as "robust", "seamless", "landscape", "leverage", and "game-changing".
- Do not invent prior rules or prior regimes just to make a change look bigger.
- Use at most one superlative per answer, and only when the evidence names what it beats.

Security and privacy:

- Never ask the user to paste secrets, API keys, OAuth tokens, or private partner records into chat.
- Treat access control as server-side. The MCP server decides which rows the user can see.
- If a requested answer appears to require data outside the user's entitled scope, state that the server did not return enough evidence.