Plan Task
Skill Verified ActiveRefine, parallelize, and verify a draft task specification into a fully planned implementation-ready task
To transform draft task specifications into high-quality, actionable plans by leveraging a structured, multi-agent refinement process.
Features
- Automated task specification refinement
- Multi-agent analysis (research, code, business)
- Architecture synthesis and decomposition
- Step parallelization and agent assignment
- LLM-as-Judge verification with quality gates
- Configurable workflow parameters (quality, iterations, stages)
- Human-in-the-loop checkpoints
Use Cases
- Refining complex feature requirements before implementation
- Breaking down large tasks into manageable, parallelizable steps
- Ensuring task specifications meet quality standards before development begins
- Automating the process of creating detailed implementation plans
Non-Goals
- Directly implementing the task (this skill only plans)
- Replacing human project management entirely
- Performing code reviews or refactoring (separate skills handle this)
Versioning
- info:Release ManagementWhile there is no explicit version number in the frontmatter or CHANGELOG, the installation instructions reference `main`, and the plugin is part of a larger marketplace, suggesting a versioning strategy exists at the marketplace level.
Installation
First, add the marketplace
/plugin marketplace add NeoLabHQ/context-engineering-kit/plugin install sdd@context-engineering-kitQuality Score
VerifiedTrust Signals
Similar Extensions
Add New Opc Skill
100Checklist and automation guide for adding a new skill to the OPC Skills project. Ensures all required files, metadata, logos, and listings are created before release. Use when adding a new skill, publishing a skill, or preparing a skill for release.
Init
100Creates, updates, or optimizes an AGENTS.md file for a repository with minimal, high-signal instructions covering non-discoverable coding conventions, tooling quirks, workflow preferences, and project-specific rules that agents cannot infer from reading the codebase. Use when setting up agent instructions or Claude configuration for a new repository, when an existing AGENTS.md is too long, generic, or stale, when agents repeatedly make avoidable mistakes, or when repository workflows have changed and the agent configuration needs pruning. Applies a discoverability filter—omitting anything Claude can learn from README, code, config, or directory structure—and a quality gate to verify each line remains accurate and operationally significant.
Openclaw Debugging
100Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code.
Using Git Worktrees
100Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
Baseline Ui
100Validates animation durations, enforces typography scale, checks component accessibility, and prevents layout anti-patterns in Tailwind CSS projects. Use when building UI components, reviewing CSS utilities, styling React views, or enforcing design consistency.
Ce Polish Beta
100[BETA] Start the dev server, open the feature in a browser, and iterate on improvements together.