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/aider/pm-strategy/competitive-intelligence-monitor/competitive-intelligence-monitor.md

@@ -0,0 +1,67 @@
+# Competitive Intelligence Monitor Skill
+
+Turn scattered competitor updates into structured weekly intelligence — not just "what they did" but "what changed since last week and what it means for us."
+
+## Required Inputs
+
+Ask the user for these if not provided:
+- **Competitors to monitor** (list of company names)
+- **Your current roadmap or strategic priorities** (to assess relevance of signals)
+- **Previous brief or last run summary** (for diff mode — what's new vs. last time)
+- **Time period** (this week, this month)
+
+## Signal Categories to Monitor
+- **Product signals:** New features, removals, UX changes, beta programmes
+- **Pricing signals:** Changes to tiers, free limits, enterprise terms
+- **Hiring signals:** Job postings revealing strategic bets
+- **Partnership signals:** Integrations, acquisitions, ecosystem moves
+- **Messaging signals:** Changes in positioning, audience, value proposition
+
+## Process
+
+### First Run (Full Report)
+1. For each competitor provided, scan all five signal categories
+2. Categorise each signal found
+3. Assess: reactive (responding to market) or proactive (setting direction)?
+4. Rate threat level: High / Medium / Low / Watch
+5. Connect each signal to a specific item on the provided roadmap
+6. Recommend response: Accelerate / Deprioritise / Monitor / Investigate
+7. **Validate** — Every High signal must have a specific recommended action and owner. "Monitor" is only acceptable for Low and Watch ratings.
+
+### Subsequent Runs (Diff Only)
+1. Compare current signals against previous run summary
+2. Output ONLY what is new or changed since last run
+3. Flag if a previously Low signal has escalated to High
+4. Keep output under 300 words — brevity is the point
+
+## Output Structure
+
+### Competitive Intelligence Brief — [Date]
+**New Since Last Run:** [n signals]
+
+#### 🔴 High Priority
+**[Competitor]:** [Signal] → [Implication] → [Recommended action + owner]
+
+#### 🟡 Watch
+**[Competitor]:** [Signal] → [Why it matters now]
+
+#### ✅ No Change
+[Competitors with no new signals this week]
+
+**This Week's Strategic Summary:**
+[2 sentences max — what is the overall competitive landscape doing?]
+
+## Anti-Patterns
+
+- [ ] Do not mark a signal as Low priority simply because it is new and unfamiliar — unknown competitive moves often deserve investigation before dismissal
+- [ ] Do not provide "monitor" as the recommended response for a High-priority signal — High signals require a specific action with a named owner
+- [ ] Do not include signals from competitors that are not relevant to the stated roadmap or strategic priorities — noise reduces the brief's usefulness and trains the team to ignore it
+- [ ] Do not produce a diff-mode brief that is longer than the full report — if the diff output exceeds 300 words, it is a full report, not a diff
+
+## Quality Checks
+
+- [ ] Every High-priority signal has a specific response action and owner
+- [ ] Signals are categorised (not just listed as "they did X")
+- [ ] Roadmap connections are specific (not "generally relevant")
+- [ ] Diff mode output is under 300 words
+- [ ] Strategic summary describes the landscape trend, not just repeats individual signals