feat: add trigger phrases to skill descriptions for better model matching

Anthropic's skill best practices: "the description field is not a summary —
it's when to trigger." Add explicit "Use when asked to..." phrases to 12 skill
descriptions so Claude's auto-discovery works with natural language requests
like "deploy this" or "check my diff", not just explicit /slash-commands.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

browse/SKILL.md

@@ -6,7 +6,8 @@ description: |
   elements, verify page state, diff before/after actions, take annotated screenshots, check
   responsive layouts, test forms and uploads, handle dialogs, and assert element states.
   ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a
-  user flow, or file a bug with evidence.
+  user flow, or file a bug with evidence. Use when asked to "open in browser", "test the
+  site", "take a screenshot", or "dogfood this".
 allowed-tools:
   - Bash
   - Read

browse/SKILL.md.tmpl

@@ -6,7 +6,8 @@ description: |
   elements, verify page state, diff before/after actions, take annotated screenshots, check
   responsive layouts, test forms and uploads, handle dialogs, and assert element states.
   ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a
-  user flow, or file a bug with evidence.
+  user flow, or file a bug with evidence. Use when asked to "open in browser", "test the
+  site", "take a screenshot", or "dogfood this".
 allowed-tools:
   - Bash
   - Read

design-consultation/SKILL.md

@@ -6,6 +6,7 @@ description: |
   complete design system (aesthetic, typography, color, layout, spacing, motion), and
   generates font+color preview pages. Creates DESIGN.md as your project's design source
   of truth. For existing sites, use /plan-design-review to infer the system instead.
+  Use when asked to "design system", "brand guidelines", or "create DESIGN.md".
 allowed-tools:
   - Bash
   - Read

design-consultation/SKILL.md.tmpl

@@ -6,6 +6,7 @@ description: |
   complete design system (aesthetic, typography, color, layout, spacing, motion), and
   generates font+color preview pages. Creates DESIGN.md as your project's design source
   of truth. For existing sites, use /plan-design-review to infer the system instead.
+  Use when asked to "design system", "brand guidelines", or "create DESIGN.md".
 allowed-tools:
   - Bash
   - Read

design-review/SKILL.md

@@ -6,6 +6,7 @@ description: |
   AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues
   in source code, committing each fix atomically and re-verifying with before/after
   screenshots. For plan-mode design review (before implementation), use /plan-design-review.
+  Use when asked to "audit the design", "visual QA", "check if it looks good", or "design polish".
 allowed-tools:
   - Bash
   - Read

design-review/SKILL.md.tmpl

@@ -6,6 +6,7 @@ description: |
   AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues
   in source code, committing each fix atomically and re-verifying with before/after
   screenshots. For plan-mode design review (before implementation), use /plan-design-review.
+  Use when asked to "audit the design", "visual QA", "check if it looks good", or "design polish".
 allowed-tools:
   - Bash
   - Read

document-release/SKILL.md

@@ -4,7 +4,8 @@ version: 1.0.0
 description: |
   Post-ship documentation update. Reads all project docs, cross-references the
   diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped,
-  polishes CHANGELOG voice, cleans up TODOS, and optionally bumps VERSION.
+  polishes CHANGELOG voice, cleans up TODOS, and optionally bumps VERSION. Use when
+  asked to "update the docs", "sync documentation", or "post-ship docs".
 allowed-tools:
   - Bash
   - Read

document-release/SKILL.md.tmpl

@@ -4,7 +4,8 @@ version: 1.0.0
 description: |
   Post-ship documentation update. Reads all project docs, cross-references the
   diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped,
-  polishes CHANGELOG voice, cleans up TODOS, and optionally bumps VERSION.
+  polishes CHANGELOG voice, cleans up TODOS, and optionally bumps VERSION. Use when
+  asked to "update the docs", "sync documentation", or "post-ship docs".
 allowed-tools:
   - Bash
   - Read

gstack-upgrade/SKILL.md

@@ -3,7 +3,8 @@ name: gstack-upgrade
 version: 1.1.0
 description: |
   Upgrade gstack to the latest version. Detects global vs vendored install,
-  runs the upgrade, and shows what's new.
+  runs the upgrade, and shows what's new. Use when asked to "upgrade gstack",
+  "update gstack", or "get latest version".
 allowed-tools:
   - Bash
   - Read

gstack-upgrade/SKILL.md.tmpl

@@ -3,7 +3,8 @@ name: gstack-upgrade
 version: 1.1.0
 description: |
   Upgrade gstack to the latest version. Detects global vs vendored install,
-  runs the upgrade, and shows what's new.
+  runs the upgrade, and shows what's new. Use when asked to "upgrade gstack",
+  "update gstack", or "get latest version".
 allowed-tools:
   - Bash
   - Read

plan-ceo-review/SKILL.md

@@ -6,6 +6,8 @@ description: |
   challenge premises, expand scope when it creates a better product. Four modes:
   SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick
   expansions), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials).
+  Use when asked to "think bigger", "expand scope", "strategy review", "rethink this",
+  or "is this ambitious enough".
 allowed-tools:
   - Read
   - Grep

plan-ceo-review/SKILL.md.tmpl

@@ -6,6 +6,8 @@ description: |
   challenge premises, expand scope when it creates a better product. Four modes:
   SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick
   expansions), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials).
+  Use when asked to "think bigger", "expand scope", "strategy review", "rethink this",
+  or "is this ambitious enough".
 allowed-tools:
   - Read
   - Grep

plan-design-review/SKILL.md

@@ -5,7 +5,8 @@ description: |
   Designer's eye plan review — interactive, like CEO and Eng review.
   Rates each design dimension 0-10, explains what would make it a 10,
   then fixes the plan to get there. Works in plan mode. For live site
-  visual audits, use /design-review.
+  visual audits, use /design-review. Use when asked to "review the design plan"
+  or "design critique".
 allowed-tools:
   - Read
   - Edit

plan-design-review/SKILL.md.tmpl

@@ -5,7 +5,8 @@ description: |
   Designer's eye plan review — interactive, like CEO and Eng review.
   Rates each design dimension 0-10, explains what would make it a 10,
   then fixes the plan to get there. Works in plan mode. For live site
-  visual audits, use /design-review.
+  visual audits, use /design-review. Use when asked to "review the design plan"
+  or "design critique".
 allowed-tools:
   - Read
   - Edit

plan-eng-review/SKILL.md

@@ -4,7 +4,8 @@ version: 1.0.0
 description: |
   Eng manager-mode plan review. Lock in the execution plan — architecture,
   data flow, diagrams, edge cases, test coverage, performance. Walks through
-  issues interactively with opinionated recommendations.
+  issues interactively with opinionated recommendations. Use when asked to
+  "review the architecture", "engineering review", or "lock in the plan".
 allowed-tools:
   - Read
   - Write

plan-eng-review/SKILL.md.tmpl

@@ -4,7 +4,8 @@ version: 1.0.0
 description: |
   Eng manager-mode plan review. Lock in the execution plan — architecture,
   data flow, diagrams, edge cases, test coverage, performance. Walks through
-  issues interactively with opinionated recommendations.
+  issues interactively with opinionated recommendations. Use when asked to
+  "review the architecture", "engineering review", or "lock in the plan".
 allowed-tools:
   - Read
   - Write

retro/SKILL.md

@@ -5,6 +5,7 @@ description: |
   Weekly engineering retrospective. Analyzes commit history, work patterns,
   and code quality metrics with persistent history and trend tracking.
   Team-aware: breaks down per-person contributions with praise and growth areas.
+  Use when asked to "weekly retro", "what did we ship", or "engineering retrospective".
 allowed-tools:
   - Bash
   - Read

retro/SKILL.md.tmpl

@@ -5,6 +5,7 @@ description: |
   Weekly engineering retrospective. Analyzes commit history, work patterns,
   and code quality metrics with persistent history and trend tracking.
   Team-aware: breaks down per-person contributions with praise and growth areas.
+  Use when asked to "weekly retro", "what did we ship", or "engineering retrospective".
 allowed-tools:
   - Bash
   - Read

review/SKILL.md

@@ -3,7 +3,8 @@ name: review
 version: 1.0.0
 description: |
   Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust
-  boundary violations, conditional side effects, and other structural issues.
+  boundary violations, conditional side effects, and other structural issues. Use when
+  asked to "review this PR", "code review", "pre-landing review", or "check my diff".
 allowed-tools:
   - Bash
   - Read

review/SKILL.md.tmpl

@@ -3,7 +3,8 @@ name: review
 version: 1.0.0
 description: |
   Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust
-  boundary violations, conditional side effects, and other structural issues.
+  boundary violations, conditional side effects, and other structural issues. Use when
+  asked to "review this PR", "code review", "pre-landing review", or "check my diff".
 allowed-tools:
   - Bash
   - Read

setup-browser-cookies/SKILL.md

@@ -4,7 +4,8 @@ version: 1.0.0
 description: |
   Import cookies from your real browser (Comet, Chrome, Arc, Brave, Edge) into the
   headless browse session. Opens an interactive picker UI where you select which
-  cookie domains to import. Use before QA testing authenticated pages.
+  cookie domains to import. Use before QA testing authenticated pages. Use when asked
+  to "import cookies", "login to the site", or "authenticate the browser".
 allowed-tools:
   - Bash
   - Read

setup-browser-cookies/SKILL.md.tmpl

@@ -4,7 +4,8 @@ version: 1.0.0
 description: |
   Import cookies from your real browser (Comet, Chrome, Arc, Brave, Edge) into the
   headless browse session. Opens an interactive picker UI where you select which
-  cookie domains to import. Use before QA testing authenticated pages.
+  cookie domains to import. Use before QA testing authenticated pages. Use when asked
+  to "import cookies", "login to the site", or "authenticate the browser".
 allowed-tools:
   - Bash
   - Read

ship/SKILL.md

@@ -2,7 +2,7 @@
 name: ship
 version: 1.0.0
 description: |
-  Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR.
+  Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", or "merge and push".
 allowed-tools:
   - Bash
   - Read

ship/SKILL.md.tmpl

@@ -2,7 +2,7 @@
 name: ship
 version: 1.0.0
 description: |
-  Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR.
+  Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", or "merge and push".
 allowed-tools:
   - Bash
   - Read