feat(dashboard): add dashboard skill for milestone/issue overview

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

agents/code-reviewer/AGENT.md

@@ -21,7 +21,8 @@ Review one PR completely:
 2. Analyze the code changes
 3. Check for quality, bugs, tests, documentation
 4. Post concise review comment (issues with file:line, no fluff)
-5. Return verdict (approved or needs-work)
+5. If approved: merge with rebase and delete branch
+6. Return verdict (approved or needs-work)
 
 ## When Invoked
 
@@ -32,6 +33,7 @@ You receive:
 
 You produce:
 - Concise review comment on PR (issues with file:line, no thanking/fluff)
+- If approved: merged PR and deleted branch
 - Verdict for orchestrator
 
 ## Process
@@ -182,7 +184,20 @@ Implementation looks solid. No blocking issues found.
 - Consider adding rate limiting
 ```
 
-### 5. Output Result
+### 5. If Approved: Merge and Clean Up
+
+**Only if verdict is approved**, merge the PR and delete the branch:
+
+```bash
+tea pulls merge <PR_NUMBER> --style rebase
+tea pulls clean <PR_NUMBER>
+```
+
+This rebases the PR onto main and deletes the source branch.
+
+**If merge fails:** Still output the result with verdict "approved" but note the merge failure in the summary.
+
+### 6. Output Result
 
 **CRITICAL**: Your final output must be exactly this format:
 
@@ -194,7 +209,7 @@ summary: <1-2 sentences>
 ```
 
 **Verdict values:**
-- `approved` - PR is ready to merge
+- `approved` - PR is ready to merge (and was merged if step 5 succeeded)
 - `needs-work` - PR has issues that must be fixed
 
 **Important:**

settings.json

@@ -29,5 +29,6 @@
   },
   "enabledPlugins": {
     "gopls-lsp@claude-plugins-official": true
-  }
+  },
+  "model": "opus"
 }

skills/create-capability/SKILL.md

@@ -95,9 +95,9 @@ Create new capabilities following latest Anthropic best practices (progressive d
 
    | Model | Use For | Cost vs Haiku |
    |-------|---------|---------------|
-   | `haiku` | Most skills and agents (DEFAULT) | Baseline |
-   | `sonnet` | When Haiku would struggle (<80% success rate) | 12x more expensive |
-   | `opus` | Deep reasoning, architectural analysis | 60x more expensive |
+   | `claude-haiku-4-5` | Most skills and agents (DEFAULT) | Baseline |
+   | `claude-sonnet-4-5` | When Haiku would struggle (<80% success rate) | 12x more expensive |
+   | `claude-opus-4-5` | Deep reasoning, architectural analysis | 60x more expensive |
 
    **Ask for justification if not Haiku:**
    - "This looks like a simple workflow. Should we try Haiku first?"

skills/dashboard/SKILL.md

@@ -0,0 +1,47 @@
+---
+name: dashboard
+description: >
+  Display milestones with unblocked issues at a glance.
+  Use when you want to see project progress and which issues are ready to work on.
+  Invoke with /dashboard [milestone-name-filter]
+model: claude-haiku-4-5
+user-invocable: true
+context: fork
+allowed-tools:
+  - Bash(~/.claude/skills/dashboard/scripts/generate-dashboard.sh*)
+---
+
+# Dashboard
+
+@~/.claude/skills/gitea/SKILL.md
+
+Display all milestones and their unblocked issues. Issues are considered unblocked if they have no open blockers in their dependency list.
+
+## Workflow
+
+1. **Run the dashboard script** with the milestone filter argument (if provided):
+   ```bash
+   ~/.claude/skills/dashboard/scripts/generate-dashboard.sh "$1"
+   ```
+
+2. **Display the output** to the user
+
+The script automatically:
+- Fetches all milestones from the repository
+- For each milestone, gets all open issues
+- For each issue, checks dependencies with `tea issues deps list`
+- Categorizes issues as unblocked (no open dependencies) or blocked (has open dependencies)
+- Displays results grouped by milestone in this format:
+
+```
+## Milestone: Release 1.0
+
+✓ Unblocked (3):
+  #42 Implement feature X
+  #43 Fix bug in Y
+  #45 Add tests for Z
+
+⊘ Blocked (2):
+  #40 Feature A (blocked by #39)
+  #41 Feature B (blocked by #38, #37)
+```

skills/dashboard/scripts/generate-dashboard.sh

@@ -0,0 +1,83 @@
+#!/bin/bash
+set -euo pipefail
+
+# Generate dashboard showing milestones with unblocked/blocked issues
+# Usage: ./generate-dashboard.sh [milestone-filter]
+
+MILESTONE_FILTER="${1:-}"
+
+# Get all milestones
+milestones_json=$(tea milestones -o json)
+
+# Parse milestone names
+milestone_names=$(echo "$milestones_json" | jq -r '.[].title')
+
+# Process each milestone
+while IFS= read -r milestone; do
+  # Skip if filter provided and doesn't match
+  if [[ -n "$MILESTONE_FILTER" && ! "$milestone" =~ $MILESTONE_FILTER ]]; then
+    continue
+  fi
+
+  echo "## Milestone: $milestone"
+  echo ""
+
+  # Get open issues for this milestone
+  issues_json=$(tea issues --milestones "$milestone" --state open -o json 2>/dev/null || echo "[]")
+
+  # Skip empty milestones or invalid JSON
+  issue_count=$(echo "$issues_json" | jq -e 'length' 2>/dev/null || echo "0")
+  if [[ "$issue_count" -eq 0 ]]; then
+    echo "No open issues"
+    echo ""
+    continue
+  fi
+
+  # Arrays for categorizing issues
+  declare -a unblocked=()
+  declare -a blocked=()
+
+  # Process each issue
+  while IFS=$'\t' read -r number title; do
+    # Check dependencies (tea returns plain text "Issue #N has no dependencies" when empty)
+    deps_output=$(tea issues deps list "$number" -o json 2>/dev/null || echo "")
+
+    # If output contains "has no dependencies", treat as empty array
+    if [[ "$deps_output" == *"has no dependencies"* ]]; then
+      deps_json="[]"
+    else
+      deps_json="$deps_output"
+    fi
+
+    # Count open dependencies
+    open_deps=$(echo "$deps_json" | jq -r '[.[] | select(.state == "open")] | length' 2>/dev/null || echo "0")
+
+    if [[ "$open_deps" -eq 0 ]]; then
+      # No open blockers - unblocked
+      unblocked+=("#$number $title")
+    else
+      # Has open blockers - blocked
+      blocker_list=$(echo "$deps_json" | jq -r '[.[] | select(.state == "open") | "#\(.index)"] | join(", ")')
+      blocked+=("#$number $title (blocked by $blocker_list)")
+    fi
+  done < <(echo "$issues_json" | jq -r '.[] | [.index, .title] | @tsv')
+
+  # Display unblocked issues
+  echo "✓ Unblocked (${#unblocked[@]}):"
+  if [[ ${#unblocked[@]} -eq 0 ]]; then
+    echo "  (none)"
+  else
+    printf '  %s\n' "${unblocked[@]}"
+  fi
+  echo ""
+
+  # Display blocked issues
+  echo "⊘ Blocked (${#blocked[@]}):"
+  if [[ ${#blocked[@]} -eq 0 ]]; then
+    echo "  (none)"
+  else
+    printf '  %s\n' "${blocked[@]}"
+  fi
+  echo ""
+
+done <<< "$milestone_names"

skills/gitea/SKILL.md

@@ -3,6 +3,9 @@ name: gitea
 model: claude-haiku-4-5
 description: View, create, and manage Gitea issues and pull requests using tea CLI. Use when working with issues, PRs, viewing issue details, creating pull requests, adding comments, merging PRs, or when the user mentions tea, gitea, issue numbers, or PR numbers.
 user-invocable: false
+allowed-tools:
+  - Bash(tea*)
+  - Bash(jq*)
 ---
 
 # Gitea CLI (tea)

skills/worktrees/scripts/create-worktree.sh

@@ -27,8 +27,8 @@ case "$MODE" in
     WORKTREE_NAME="${REPO_NAME}-issue-${ISSUE_NUMBER}"
     WORKTREE_PATH="${WORKTREES_DIR}/${WORKTREE_NAME}"
 
-    # Get issue title for branch name
-    ISSUE_TITLE=$(tea issues "$ISSUE_NUMBER" 2>/dev/null | grep -i "title" | head -1 | cut -d: -f2- | xargs || echo "untitled")
+    # Get issue title for branch name (tea issues output has title on line 2: "  # #1 Title here")
+    ISSUE_TITLE=$(tea issues "$ISSUE_NUMBER" 2>/dev/null | sed -n '2p' | sed 's/.*#[0-9]* //' | xargs || echo "untitled")
 
     # Create safe branch name
     BRANCH_NAME="issue-${ISSUE_NUMBER}-$(echo "$ISSUE_TITLE" | tr '[:upper:]' '[:lower:]' | tr ' ' '-' | tr -cd '[:alnum:]-' | cut -c1-50)"