feat: fix skill frontmatter for tessl validation

default/skills/brainstorming/SKILL.md

@@ -1,25 +1,25 @@
 ---
-name: ring:brainstorming
+name: brainstorming
 description: |
   Socratic design refinement - transforms rough ideas into validated designs through
   structured questioning, alternative exploration, and incremental validation.
-
-trigger: |
-  - New feature or product idea (requirements unclear)
-  - User says "plan", "design", or "architect" something
-  - Multiple approaches seem possible
-  - Design hasn't been validated by user
-
-skip_when: |
-  - Design already complete and validated → use ring:writing-plans
-  - Have detailed plan ready to execute → use ring:executing-plans
-  - Just need task breakdown from existing design → use ring:writing-plans
-
-sequence:
-  before: [ring:writing-plans, ring:using-git-worktrees]
-
-related:
-  similar: [ring:writing-plans]
+metadata:
+  related:
+    similar:
+    - ring:writing-plans
+  sequence:
+    before:
+    - ring:writing-plans
+    - ring:using-git-worktrees
+  skip_when: |
+    - Design already complete and validated → use ring:writing-plans
+    - Have detailed plan ready to execute → use ring:executing-plans
+    - Just need task breakdown from existing design → use ring:writing-plans
+  trigger: |
+    - New feature or product idea (requirements unclear)
+    - User says "plan", "design", or "architect" something
+    - Multiple approaches seem possible
+    - Design hasn't been validated by user
 ---
 
 # Brainstorming Ideas Into Designs

default/skills/drawing-diagrams/SKILL.md

@@ -1,9 +1,12 @@
 ---
 name: drawing-diagrams
-description: Generate Mermaid diagrams from context and open them in mermaid.live in the browser. Use when the user asks for a diagram, visualization, flowchart, sequence diagram, ER diagram, or any visual representation of code, architecture, or processes. Produces lightweight, shareable mermaid.live URLs that open in the browser for interactive editing.
+description: Generate Mermaid diagrams from context and open them in mermaid.live in the browser. Use when the user asks for a diagram, visualization, flowchart, sequence diagram, ER diagram, or any visual
+  representation of code, architecture, or processes. Produces lightweight, shareable mermaid.live URLs that open in the browser for interactive editing.
 license: MIT
 compatibility: Requires Python 3 (standard library only) and a browser. Uses `open` on macOS; Linux users need `xdg-open`.
-skip_when: The user needs a rich, branded, or styled HTML visualization (use ring:visual-explainer instead). This skill produces shareable mermaid.live URLs; visual-explainer produces self-contained Lerian-branded HTML files.
+metadata:
+  skip_when: The user needs a rich, branded, or styled HTML visualization (use ring:visual-explainer instead). This skill produces shareable mermaid.live URLs; visual-explainer produces self-contained Lerian-branded
+    HTML files.
 ---
 
 # Mermaid Live Diagram Generator

default/skills/executing-plans/SKILL.md

@@ -1,24 +1,24 @@
 ---
-name: ring:executing-plans
+name: executing-plans
 description: |
   Controlled plan execution with human review checkpoints - loads plan, executes
   in batches, pauses for feedback. Supports one-go (autonomous) or batch modes.
-
-trigger: |
-  - Have a plan file ready to execute
-  - Want human review between task batches
-  - Need structured checkpoints during implementation
-
-skip_when: |
-  - Same session with independent tasks → use ring:subagent-driven-development
-  - No plan exists → use ring:writing-plans first
-  - Plan needs revision → use ring:brainstorming first
-
-sequence:
-  after: [ring:writing-plans, ring:pre-dev-task-breakdown]
-
-related:
-  similar: [ring:subagent-driven-development]
+metadata:
+  related:
+    similar:
+    - ring:subagent-driven-development
+  sequence:
+    after:
+    - ring:writing-plans
+    - ring:pre-dev-task-breakdown
+  skip_when: |
+    - Same session with independent tasks → use ring:subagent-driven-development
+    - No plan exists → use ring:writing-plans first
+    - Plan needs revision → use ring:brainstorming first
+  trigger: |
+    - Have a plan file ready to execute
+    - Want human review between task batches
+    - Need structured checkpoints during implementation
 ---
 
 # Executing Plans

default/skills/exploring-codebase/SKILL.md

@@ -1,32 +1,35 @@
 ---
-name: ring:exploring-codebase
+name: exploring-codebase
 description: |
   Autonomous two-phase codebase exploration - first discovers natural perspectives
   (layers, components, boundaries), then dispatches adaptive deep-dive explorers
   based on what was discovered. Synthesizes findings into actionable insights.
-
-trigger: |
-  - Need to understand how a feature/system works across the codebase
-  - Starting work on unfamiliar codebase or component
-  - Planning changes that span multiple layers/components
-  - User asks "how does X work?" for non-trivial X
-  - Need architecture understanding before implementation
-
-skip_when: |
-  - Pure reference lookup (function signature, type definition)
-  - Checking if specific file exists (yes/no question)
-  - Reading error message from known file location
-
-  WARNING: These are NOT valid skip reasons:
-  - "I already know the architecture" → Prior knowledge is incomplete
-  - "Simple question about location" → Location without context is incomplete
-  - "Production emergency, no time" → High stakes demand MORE rigor
-  - "Colleague told me structure" → High-level ≠ implementation details
-
-related:
-  similar: [dispatching-parallel-agents, systematic-debugging]
-  sequence_after: [brainstorming]
-  sequence_before: [ring:writing-plans, ring:executing-plans]
+metadata:
+  related:
+    similar:
+    - dispatching-parallel-agents
+    - systematic-debugging
+    sequence_after:
+    - brainstorming
+    sequence_before:
+    - ring:writing-plans
+    - ring:executing-plans
+  skip_when: |
+    - Pure reference lookup (function signature, type definition)
+    - Checking if specific file exists (yes/no question)
+    - Reading error message from known file location
+
+    WARNING: These are NOT valid skip reasons:
+    - "I already know the architecture" → Prior knowledge is incomplete
+    - "Simple question about location" → Location without context is incomplete
+    - "Production emergency, no time" → High stakes demand MORE rigor
+    - "Colleague told me structure" → High-level ≠ implementation details
+  trigger: |
+    - Need to understand how a feature/system works across the codebase
+    - Starting work on unfamiliar codebase or component
+    - Planning changes that span multiple layers/components
+    - User asks "how does X work?" for non-trivial X
+    - Need architecture understanding before implementation
 ---
 
 # Autonomous Two-Phase Codebase Exploration

default/skills/gandalf-webhook/SKILL.md

@@ -1,11 +1,9 @@
 ---
-name: ring:gandalf-webhook
+name: gandalf-webhook
 description: Send tasks to Gandalf (AI team member) via webhook and get responses back. Publish to Alfarrábio, send Slack notifications, ask for business context, and more.
-user_invocable: true
-allowed-tools:
-  - Bash
-  - Read
-  - Write
+allowed-tools: Bash, Read, Write
+metadata:
+  user_invocable: true
 ---
 
 # Gandalf Webhook

default/skills/git-commit/SKILL.md

@@ -1,13 +1,9 @@
 ---
-name: ring:git-commit
+name: git-commit
 description: Smart commit organization with atomic grouping, conventional commits, and trailer management
-user_invocable: false
-allowed-tools:
-  - Bash
-  - Read
-  - Glob
-  - Grep
-  - AskUserQuestion
+allowed-tools: Bash, Read, Glob, Grep, AskUserQuestion
+metadata:
+  user_invocable: false
 ---
 
 Analyze changes, group them into coherent atomic commits, and create signed commits following repository conventions. This skill transforms a messy working directory into a clean, logical commit history.

default/skills/interviewing-user/SKILL.md

@@ -1,29 +1,30 @@
 ---
-name: ring:interviewing-user
+name: interviewing-user
 description: |
   Proactive requirements gathering - systematically interviews the user to uncover
   ambiguities, preferences, and constraints BEFORE implementation begins.
-
-trigger: |
-  - User invokes /ring:interview-me command
-  - Claude detects significant ambiguity in requirements
-  - Multiple valid implementation paths exist with no clear winner
-  - User says "interview me", "ask me questions", "clarify with me"
-  - Task involves architecture decisions without clear direction
-
-skip_when: |
-  - Requirements are already crystal clear
-  - User has provided detailed specifications
-  - Following an existing plan with explicit instructions
-  - Doubt can be resolved via doubt-triggered-questions (single question)
-
-sequence:
-  before: [brainstorming, ring:writing-plans]
-  after: []
-
-related:
-  similar: [brainstorming]
-  uses: [doubt-triggered-questions]
+metadata:
+  related:
+    similar:
+    - brainstorming
+    uses:
+    - doubt-triggered-questions
+  sequence:
+    before:
+    - brainstorming
+    - ring:writing-plans
+    after: []
+  skip_when: |
+    - Requirements are already crystal clear
+    - User has provided detailed specifications
+    - Following an existing plan with explicit instructions
+    - Doubt can be resolved via doubt-triggered-questions (single question)
+  trigger: |
+    - User invokes /ring:interview-me command
+    - Claude detects significant ambiguity in requirements
+    - Multiple valid implementation paths exist with no clear winner
+    - User says "interview me", "ask me questions", "clarify with me"
+    - Task involves architecture decisions without clear direction
 ---
 
 # Interviewing User for Requirements

default/skills/linting-codebase/SKILL.md

@@ -1,18 +1,17 @@
 ---
-name: ring:linting-codebase
+name: linting-codebase
 description: |
   Parallel lint fixing pattern - runs lint checks, groups issues into independent
   streams, and dispatches AI agents to fix all issues until the codebase is clean.
-
-trigger: |
-  - User runs /ring:lint command
-  - Codebase has lint issues that need fixing
-  - Multiple lint errors across different files/components
-
-skip_when: |
-  - Single lint error → fix directly without agent dispatch
-  - Lint already passes → nothing to do
-  - User only wants to see lint output, not fix
+metadata:
+  skip_when: |-
+    - Single lint error → fix directly without agent dispatch
+    - Lint already passes → nothing to do
+    - User only wants to see lint output, not fix
+  trigger: |
+    - User runs /ring:lint command
+    - Codebase has lint issues that need fixing
+    - Multiple lint errors across different files/components
 ---
 
 # Linting Codebase

default/skills/production-readiness-audit/SKILL.md

@@ -1,10 +1,15 @@
 ---
-name: ring:production-readiness-audit
-title: Production Readiness Audit
-category: operations
-tier: advanced
-description: Comprehensive Ring-standards-aligned 44-dimension production readiness audit. Detects project stack, loads Ring standards via WebFetch, and runs in batches of 10 explorers appending incrementally to a single report file. Categories - Structure (pagination, errors, routes, bootstrap, runtime, core deps, naming, domain modeling, nil-safety, api-versioning, resource-leaks), Security (auth, IDOR, SQL, validation, secret-scanning, data-encryption, multi-tenant, rate-limiting, cors), Operations (telemetry, health, config, connections, logging, resilience, graceful-degradation), Quality (idempotency, docs, debt, testing, dependencies, performance, concurrency, migrations, linting, caching), Infrastructure (containers, hardening, cicd, async, makefile, license). Produces scored report (0-430, max 440 with multi-tenant) with severity ratings and standards cross-reference.
+name: production-readiness-audit
+description: Comprehensive Ring-standards-aligned 44-dimension production readiness audit. Detects project stack, loads Ring standards via WebFetch, and runs in batches of 10 explorers appending incrementally
+  to a single report file. Categories - Structure (pagination, errors, routes, bootstrap, runtime, core deps, naming, domain modeling, nil-safety, api-versioning, resource-leaks), Security (auth, IDOR,
+  SQL, validation, secret-scanning, data-encryption, multi-tenant, rate-limiting, cors), Operations (telemetry, health, config, connections, logging, resilience, graceful-degradation), Quality (idempotency,
+  docs, debt, testing, dependencies, performance, concurrency, migrations, linting, caching), Infrastructure (containers, hardening, cicd, async, makefile, license). Produces scored report (0-430, max 440
+  with multi-tenant) with severity ratings and standards cross-reference.
 allowed-tools: Task, Read, Glob, Grep, Write, TodoWrite, WebFetch
+metadata:
+  category: operations
+  tier: advanced
+  title: Production Readiness Audit
 ---
 
 # Production Readiness Audit