Windsurf + Aider targets, MCP server, and demo placement (#33)

Broadens both reach (more tools) and content types (an MCP server), continuing
the multi-platform story.

Windsurf + Aider:
- build-exports.mjs gains two platforms: exports/windsurf/*.md (workspace rules,
  trigger: model_decision) and exports/aider/*.md (conventions for `aider --read`).
  Now 5 platforms (ChatGPT, Gemini, Cursor, Windsurf, Aider).
- install.sh + bin/cli.mjs install both (windsurf -> .windsurf/rules, aider ->
  .aider/skills with a --read hint); generated README index is excluded from copies.
- One-line windsurf-install.sh / aider-install.sh wrappers for parity.

MCP server (new content type):
- mcp/server.mjs — zero-dependency stdio MCP server exposing list_skills,
  search_skills, get_skill. Published as a second bin (pm-claude-skills-mcp).
  Logs to stderr; reads bundled skills/ at startup. mcp/README.md documents
  client config.

Also: README hero "See it in action" demo placement (ready to swap in a GIF;
recording guide in web/docs-assets/README.md), Works-With table + exports +
install docs updated, CHANGELOG Unreleased. package.json files/bin updated.


Claude-Session: https://claude.ai/code/session_016JWn5jRD5tcEFKrubjQ6Px

Co-authored-by: Claude <noreply@anthropic.com>

exports/windsurf/pm-operations/vendor-evaluation/vendor-evaluation.md

@@ -0,0 +1,87 @@
+---
+trigger: model_decision
+description: "Create a structured vendor evaluation framework for any procurement decision. Use when asked to evaluate vendors, compare suppliers, run an RFP scoring process, or assess a software or service provider. Produces a weighted scorecard, evaluation criteria, and recommendation framework."
+---
+
+# Vendor Evaluation Skill
+
+Produces a structured vendor evaluation framework — from defining criteria through to a scored comparison and recommendation.
+
+## Required Inputs
+- **What you are procuring**
+- **Vendors being evaluated** (minimum 2)
+- **Key decision criteria** (if known)
+- **Decision makers**
+- **Budget range**
+- **Timeline to decide**
+
+## Output Structure
+
+### 1. Evaluation Criteria and Weights
+
+| Category | Weight | Rationale |
+|---|---|---|
+| Functional fit | [%] | Does it do what we need? |
+| Commercial terms | [%] | Price, flexibility, payment |
+| Implementation | [%] | How hard to get started? |
+| Support and SLA | [%] | What happens when things go wrong? |
+| Security and compliance | [%] | Meets regulatory requirements? |
+| Vendor stability | [%] | Will this company exist in 3 years? |
+| References | [%] | Who else uses this? |
+
+Weights must total 100%.
+
+### 2. Scoring Rubric
+- 5: Exceeds requirements — clear best-in-class
+- 4: Meets requirements — fully satisfies with minor gaps
+- 3: Partially meets — notable gaps requiring workarounds
+- 2: Significant gaps — would require workarounds
+- 1: Does not meet — cannot satisfy requirement
+
+### 3. Vendor Scorecard
+
+| Criterion | Weight | [Vendor A] | Weighted | [Vendor B] | Weighted | [Vendor C] | Weighted |
+|---|---|---|---|---|---|---|---|
+| Functional fit | [%] | /5 | | /5 | | /5 | |
+| [Continue...] | | | | | | | |
+| **Total** | 100% | | **/5** | | **/5** | | **/5** |
+
+### 4. Key Questions for Every Vendor
+Functional: Walk through [most critical use case]. What can your product not do that customers ask for?
+Commercial: What is included vs add-ons? Contract minimum term and notice period? Price protection at renewal?
+Implementation: Typical implementation for our size? What do you need from our team?
+Support: SLA for critical issues? Support included vs charged extra?
+Security: ISO 27001 / SOC 2 certified? Where is data stored? Breach notification process?
+
+### 5. Reference Check Questions
+- How long using [vendor]? Implementation surprises? Support responsiveness? One thing you wish you had known? Would you choose them again?
+
+### 6. Recommendation
+
+**Recommended vendor:** [Name] | **Score:** [X/5]
+**Rationale:** [Specific strengths that matter for this decision]
+**Key risks:** [Risk and mitigation]
+**Conditions:** [Contract terms to negotiate before signing]
+**Runner-up:** [Vendor and why they lost]
+
+## Quality Checks
+
+- [ ] Evaluation criteria weights total 100%
+- [ ] Scoring rubric is defined before scoring vendors (not post-hoc)
+- [ ] Reference check questions are included
+- [ ] Recommendation includes risks and conditions, not just a winner
+- [ ] Runner-up rationale explains why they lost (enables future conversations)
+- [ ] Contract terms to negotiate are specified
+
+## Anti-Patterns
+
+- [ ] Do not weight all evaluation criteria equally — the scorecard must reflect the relative importance of each criterion
+- [ ] Do not evaluate vendors only on features — security, support, contract terms, and financial stability matter too
+- [ ] Do not produce a recommendation without explaining why the runner-up lost — this enables future vendor conversations
+- [ ] Do not skip contract terms to negotiate — identifying leverage points is part of the procurement decision
+- [ ] Do not recommend a vendor without stating the conditions under which the recommendation would change
+
+## Example Trigger Phrases
+- "Help me evaluate vendors for [procurement]"
+- "Create a vendor scorecard for [software/service]"
+- "Compare [Vendor A] vs [Vendor B] for [use case]"