feat: 100 skills milestone — 7 new skills + quality improvements across all 93

New skills added:
- teaching-lesson-plan: structured lesson plans for any subject/audience/setting
- seo-content-brief: complete SEO briefs with intent, competitor gaps, and outline
- media-pitch: story-first journalist pitches with angle development framework
- change-management-plan: stakeholder analysis, comms strategy, adoption metrics
- workshop-facilitation-guide: activity instructions, decision protocols, facilitator moves
- sales-forecasting-model: pipeline model, scenario analysis, assumption log
- tax-planning-checklist: year-end tax planning across income, pension, CGT, reliefs

Quality improvements across all 93 existing skills:
- Standardised description format: "Verb the thing. Use when X. Produces Y."
- Added Required Inputs section to all skills missing it (prompts for missing info)
- Added Quality Checks section to all skills missing it (specific, not generic)
- Fixed broken multiline YAML descriptions
- Removed non-standard frontmatter keys (tool_integration, metadata blocks)

README updated to v6.0.0 with 100-skill count, new skill tables, and article series

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

skills/launch-readiness/SKILL.md

@@ -1,13 +1,20 @@
 ---
 name: launch-readiness
-description: Run a comprehensive pre-launch readiness assessment across all functions
-tool_integration: Notion, Jira, Slack
+description: "Run a comprehensive pre-launch readiness assessment across all functions. Use when asked to assess launch readiness, run a pre-launch review, create a go/no-go recommendation, or check if a product or feature is ready to ship. Produces a function-by-function readiness status, blockers list, risk register, and an explicit Go / Conditional Go / No-Go recommendation."
 ---
+
 # Launch Readiness Skill
 
-## Purpose
 Ensure nothing falls through the cracks before launch by systematically checking readiness across every function — and producing a clear, evidenced go/no-go recommendation.
 
+## Required Inputs
+
+Ask the user for these if not provided:
+- **Launch name and target date**
+- **Launch tier** (Tier 1 = major launch / Tier 2 = significant feature / Tier 3 = incremental update)
+- **Completed checklist items or self-assessment** (even partial is fine — we'll surface gaps)
+- **Team and role names** (to assign owners to blockers)
+
 ## Readiness Checklist by Function
 
 ### Product & Engineering
@@ -15,7 +22,7 @@ Ensure nothing falls through the cracks before launch by systematically checking
 - [ ] Performance benchmarks met
 - [ ] Accessibility standards checked
 - [ ] Edge cases documented and handled
-- [ ] Rollback plan defined
+- [ ] Rollback plan defined and tested
 
 ### Marketing & Comms
 - [ ] Launch messaging approved
@@ -45,11 +52,13 @@ Ensure nothing falls through the cracks before launch by systematically checking
 2. Flag any incomplete items as blockers (must fix) or risks (monitor)
 3. Assess overall readiness and produce go/no-go recommendation with rationale
 4. If no-go, specify exactly what must be completed and by when
+5. **Validate** — Confirm every blocker has a named owner and resolution deadline, and that the rollback plan is tested (not just documented)
 
-## Output Format
+## Output Structure
 
 ### Launch Readiness Assessment: [Feature/Product Name]
 **Launch Date:** [date]
+**Launch Tier:** [1 / 2 / 3]
 **Overall Status:** ✅ Go / ⚠️ Conditional Go / 🛑 No-Go
 
 **Blockers (must resolve before launch):**
@@ -63,3 +72,11 @@ Ensure nothing falls through the cracks before launch by systematically checking
 
 **Recommendation:**
 [Clear go/no-go with rationale — 3-5 sentences]
+
+## Quality Checks
+
+- [ ] Every blocker has a specific owner (not "the team") and a deadline
+- [ ] Rollback plan is explicitly tested, not just written
+- [ ] Analytics events are verified in staging, not just implemented
+- [ ] Go/No-Go decision has a named decision-maker and a cut-off time
+- [ ] At least one post-launch monitoring check is scheduled (e.g., T+2hr, T+24hr)