feat: news-summary v4 — 教育+投資分析ブリーフィング skill

CHANGELOG.md

@@ -1,5 +1,25 @@
 # Changelog
 
+## [0.15.2.0] - 2026-04-01 — news-summary v4: 教育+投資分析ブリーフィング
+
+Say `/news-summary` and get a full Japanese stock market briefing written to your Obsidian vault. Layer 1 is the speed-read: market data, causal Mermaid diagrams, sector tables, scenario analysis. Layer 2 is folded education callouts explaining why things move the way they do, with wikilinks to a living glossary. Stock notes and weekly summaries auto-update.
+
+### Added
+
+- **`/news-summary` skill v4.0** — Collects from Nikkei, Kabutan, Shikiho Online, and NYT Japan via Chrome MCP (paid content) with WebFetch/WebSearch fallback. Parallel collection groups cut execution time in half.
+- **Layer design.** Speed-read briefing + folded `> [!info]-` education callouts with causal chain explanations, multi-pathway analysis (経路A/B structure), sector impact tables, and background knowledge with real numbers.
+- **Stock notes** (`Stocks/{code}-{name}.md`). Auto-created/updated with today's news, basic data, and investment analysis. `## 自分のメモ` section is protected.
+- **Living glossary** (`Glossary/{macro,market,geopolitics}/{term}.md`). Deep format: multi-step Mermaid causal diagrams, sector impact tables, scenario tables, background knowledge with DCF calculations and concrete examples.
+- **Weekly summary** with prediction tracking. Friday afternoon sessions auto-verify Monday's scenario predictions against actual results.
+- **Session state file** (`.state.json`). Tracks scenario predictions, watchlist, and key metrics across runs for automatic "what changed since last time" detection.
+- **Chart.js candlestick template** extracted to `templates/candlestick.html` for context efficiency.
+
+### Changed
+
+- **Unified error handling.** Single error policy table at the top of the skill instead of scattered per-step rules. Edit-only for existing files (no Write fallback), retry-once for data sources,推測禁止 for all numbers.
+- **Preamble cleanup.** Removed session timeline logging, auto-learnings-search in preamble, /checkpoint and /health routing references. Added contributor mode detection.
+- **Telemetry gate fix.** `"$_TEL"` → `"${_TEL:-off}"` prevents writing analytics when telemetry is unset.
+
 ## [0.15.1.0] - 2026-04-01 — Design Without Shotgun
 
 You can now run `/design-html` without having to run `/design-shotgun` first. The skill detects what design context exists (CEO plans, design review artifacts, approved mockups) and asks how you want to proceed. Start from a plan, a description, or a provided PNG, not just an approved mockup.

CLAUDE.md

@@ -385,3 +385,21 @@ The active skill lives at `~/.claude/skills/gstack/`. After making changes:
 Or copy the binaries directly:
 - `cp browse/dist/browse ~/.claude/skills/gstack/browse/dist/browse`
 - `cp design/dist/design ~/.claude/skills/gstack/design/dist/design`
+
+## Skill routing
+
+When the user's request matches an available skill, ALWAYS invoke it using the Skill
+tool as your FIRST action. Do NOT answer directly, do NOT use other tools first.
+The skill has specialized workflows that produce better results than ad-hoc answers.
+
+Key routing rules:
+- Product ideas, "is this worth building", brainstorming → invoke office-hours
+- Bugs, errors, "why is this broken", 500 errors → invoke investigate
+- Ship, deploy, push, create PR → invoke ship
+- QA, test the site, find bugs → invoke qa
+- Code review, check my diff → invoke review
+- Update docs after shipping → invoke document-release
+- Weekly retro → invoke retro
+- Design system, brand → invoke design-consultation
+- Visual audit, design polish → invoke design-review
+- Architecture review → invoke plan-eng-review

VERSION

@@ -1 +1 @@
-0.15.1.0
+0.15.2.0

careful/SKILL.md

@@ -17,6 +17,7 @@ hooks:
         - type: command
           command: "bash ${CLAUDE_SKILL_DIR}/bin/check-careful.sh"
           statusMessage: "Checking for destructive commands..."
+sensitive: true
 ---
 <!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
 <!-- Regenerate: bun run gen:skill-docs -->

freeze/SKILL.md

@@ -23,6 +23,7 @@ hooks:
         - type: command
           command: "bash ${CLAUDE_SKILL_DIR}/bin/check-freeze.sh"
           statusMessage: "Checking freeze boundary..."
+sensitive: true
 ---
 <!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
 <!-- Regenerate: bun run gen:skill-docs -->

guard/SKILL.md

@@ -28,6 +28,7 @@ hooks:
         - type: command
           command: "bash ${CLAUDE_SKILL_DIR}/../freeze/bin/check-freeze.sh"
           statusMessage: "Checking freeze boundary..."
+sensitive: true
 ---
 <!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
 <!-- Regenerate: bun run gen:skill-docs -->

land-and-deploy/SKILL.md

@@ -13,6 +13,7 @@ allowed-tools:
   - Write
   - Glob
   - AskUserQuestion
+sensitive: true
 ---
 <!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
 <!-- Regenerate: bun run gen:skill-docs -->