Do — Feature Development Orchestrator

Name: Do — Feature Development Orchestrator
Rating: 76 (1 reviews)
Author: stellarlinkco

Trust Score 76/100

Orchestrates a five-phase, multi-agent feature development workflow (Understand, Clarify, Design, Implement, Complete) using codeagent-wrapper; manages task wor

triggers:/dofeature developmentcodeagent-wrapperworktreephase 1implement agent

GitHub SKILL.md

What it does

Provides an orchestrated, phase-based workflow for structured feature development using multiple specialized agents. It initializes task directories, manages phases (Understand, Clarify, Design, Implement, Complete), and coordinates read-only analysis agents with worktree-backed implementers so code changes are produced safely and reviewed.

When to use it

Trigger this skill when you want to run a structured feature development flow (e.g. /do <task>). Use it for non-trivial changes where exploration, design, parallel agent runs, and staged implementation are needed — especially when you want to preserve an isolated worktree for implementation and automatic phase updates.

What's included

Scripts: setup and task management scripts under scripts/ (has_scripts=true) for initializing worktrees and updating phase state.
References: workflow examples and agent invocation patterns are embedded in the skill body.
Instructions: detailed phase-by-phase commands, constraints (never write code directly; defer worktree until implement phase), agent roles and example command templates.

Compatible agents

Designed for multi-agent orchestration controllers (Claude Code, codeagent-wrapper, code-architect, code-explorer, code-reviewer, develop agents).

Audit Summary

A multi-agent feature development orchestrator skill (5-phase workflow: Understand, Clarify, Design, Implement, Complete) using codeagent-wrapper to delegate to sub-agents. SKILL.md is well-structured with clear phases, agent tables, and code examples. Scripts handle task directory management and context retrieval. setup-do.py has a broken import (from task import …) that fails when scripts are run individually — it expects task.py to be importable as a module. get-context.py works but requires an active task to function. task.py CLI itself is solid.

Watch Out

setup-do.py fails with ModuleNotFoundError — it uses 'from task import create_task, PHASE_NAMES' assuming task.py is on the Python path, but scripts are executed individually in isolated dirs
Requires CLAUDE_PROJECT_DIR env var or falls back to cwd — may not work outside Claude Code environment
Git worktree creation in task.py calls subprocess.run(['git', ...]) — shell injection risk is low since args are programmatic, but task_id uses random chars which is good
Simple YAML parser in task.py won't handle nested structures, lists, or complex values

Notes

No security concerns — no network calls, no credential handling, no exfiltration. Scripts only manage local task directories and git worktrees. The broken import in setup-do.py is a real usability bug. The skill is niche — it's tightly coupled to the 'codeagent-wrapper' CLI tool and Claude Code's environment, limiting broad applicability.

Information

Repository: stellarlinkco

Trust Score

Overall76

Security82

Code Quality68

Architecture72

Usefulness58

More from stellarlinkco

Harness — Long-Running Agent Framework

A framework for long-running, multi-session agent tasks: progress checkpointing, failure recovery, task dependency management, and concurrency controls.

Codeagent Wrapper

Run and orchestrate codeagent-wrapper tasks across multiple AI backends (Codex, Claude, Gemini, OpenCode) for parallel code analysis, large refactors, and multi

OmO - Multi-Agent Orchestrator

Routing-first orchestrator that invokes and coordinates specialized agents for code analysis, bug investigation, planning, and implementation.

Related Skills

Development Worktree

Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.

ds-fix — data-science mid-analysis fixer

Orchestrates diagnosis and targeted fixes mid-analysis: diagnose root cause, apply fixes with output-first verification, and update project learnings.

Readwise Reader Document Management

Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.

Bounty Hunter — Atlas

Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.

Junshi — Research Advisor

Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.

Full Stack Builder

End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.

ezBookkeeping API Tools

Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi

Feishu Voice Sender

Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.

Back to Skills