Creates structured Taskplane task packets (PROMPT.md, STATUS.md) for autonomous agent execution via the task-orchestrator extension (/orch). Use when asked to "create a task", "create a taskplane task", "stage a task", "prepare a task for execution", "write a PROMPT.md", "set up work for the agent", "queue a task", or whenever the user wants to define work that will be executed autonomously by another agent instance.
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
Use this skill for task coordination with workgraph (wg). Triggers include "workgraph", "wg", task graphs, multi-step projects, tracking dependencies, coordinating agents, or when you see a .workgraph directory.
Manage Hathor wallet-lib release process. Use when initiating a release (PR from master to release branch) or bumping version (minor/patch/major). Handles PR creation with proper templates, reviewer assignment, labels, and GitHub project integration.
Estimate the cost of a task before starting it. Analyzes task complexity, predicts token usage, and compares cost across all Claude models. Use when user says 'estimate cost', 'how much will this cost', 'cost estimate', or '/cost-estimate'.
- 📁 assets/
- 📁 references/
- 📄 CLAUDE_MD_INSTRUCTIONS.md
- 📄 SKILL.md
MANDATORY - INVOKE IMMEDIATELY after completing ANY development task (feature, bug fix, refactor, maintenance). Creates SR-PTD documentation for future skill extraction. This is NOT optional - every task MUST have documentation.
- 📄 bridge.py
- 📄 claude-bridge-answer.sh
- 📄 claude-bridge-dispatch.sh
Dispatch coding tasks to Claude Code with two-way communication. Send tasks, receive status updates, answer clarifying questions, and get results.
Break a design brief into an ordered checklist of independently buildable tasks using vertical slices. Saves as a markdown checklist. Use when user wants to break down work, create tasks from a brief, plan implementation order, or mentions "tasks" or "breakdown".
- 📁 .claude-plugin/
- 📁 .codex-plugin/
- 📁 docs/
- 📄 .gitignore
- 📄 AGENTS.md
- 📄 CLAUDE.md
Use when a well-specified task has meaningful design choices and you want to maximize quality by comparing multiple independent attempts. Works for coding, writing, and custom task types. Triggers on "slot-machine", "best-of-N", "pull the lever", "parallel implementations", or when quality matters more than speed and the spec is clear enough for independent work.
- 📁 bin/
- 📁 docs/
- 📁 pipeline/
- 📄 .gitignore
- 📄 CONTRIBUTING.md
- 📄 LICENSE
OPC — One Person Company. Task pipeline with independent multi-role evaluation. Builds, reviews, analyzes, and brainstorms with 11 specialist agents. Every task ends with evaluation. /opc <task>, /opc -i <task>, /opc <role> [role...]
Use when running or operating the Autoloop orchestration runtime, including starting new loops, resuming tasks, phase-scoped runs, troubleshooting stuck-looking runs, and interpreting run artifacts. Do not use for unrelated coding tasks.
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
