Use when: User says `ct`, `claim task`, or wants to claim and implement the next available task from beads.
/plugin marketplace add ReinaMacCredy/my-workflow/plugin install reinamaccredy-my-workflow@ReinaMacCredy/my-workflowThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Use when: User says ct, claim task, or wants to claim and implement the next available task from beads.
ctclaim taskclaim next taskwork on next issueStart epic <epic-id> (handoff from planning session)If user message matches Start epic <epic-id>:
Load epic from beads:
bd show <epic-id> --json
Parse notes for plan location:
Look for PLAN: <path> in notes field
Read the plan:
cat <plan-path>
Get ready tasks:
bd ready --json
Filter to tasks that are children of this epic
Begin execution at Phase 1 with epic context loaded
If no handoff detected: Proceed directly to Phase 1.
bd ready --json
If no tasks available:
bd blocked --jsonSelect highest priority ready task
Mark as in-progress:
bd update <issue-id> --status in_progress
CRITICAL: Record thread URL for doc-sync integration
⚠️ This step is REQUIRED - doc-sync relies on thread URLs to extract knowledge.
Before proceeding, verify:
$AMP_THREAD_URL)https://ampcode.com/threads/T-... or http://localhost:.../threads/T-...)bd update <issue-id> --notes "THREAD: <current-amp-thread-url>"
If thread URL is unavailable: STOP and notify user. Do not proceed without recording the thread link - this creates orphaned work that cannot be synced to documentation.
Read task details:
bd show <issue-id>
For complex tasks, create isolated worktree:
using-git-worktrees skilltest-driven-development skillverification-before-completion skillbd update <issue-id> --notes "COMPLETED: <summary>. THREAD: <amp-thread-url>. Files changed: <list>"
Ask user:
finishing-a-development-branch skillCLAIMING: <issue-id> - <title>
PRIORITY: <priority>
DEPENDENCIES: <resolved deps>
[Implementation steps...]
STATUS: Complete | In Progress | Blocked
NEXT: <recommendation>
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.