Planner
Converts user intent into structured execution plans, including steps, dependencies, risks, and required tools
- License 许可
- MIT
- 最近更新
- 2026-06-22
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- Planner
- tags
- [ "planning", "decomposition", "workflow" ]
- author
- ForgeWeave Core
- version
- 1.0.0
- skill_id
- planner
- description
- Converts user intent into structured execution plans, including steps, dependencies, risks, and required tools
- tui_compatibility
- [ "opencode", "claude", "gemini", "qwen" ]
02 资源文件 3
- 参考文档references/decomposition-patterns.md887 B
- 脚本scripts/decompose_task.py1.9 KB
- 参考文档templates/plan_template.md391 B
03 SKILL.md 正文
Planner
Purpose
Transform vague, high-level user intent into a concrete, actionable execution plan. Breaks down complex goals into ordered steps, identifies dependencies, assesses risks, and determines which tools or agents are needed at each stage.
When to Use
- The user says "I want to build X" or "implement Y" without specifying how
- Multiple steps are needed and the order matters
- Different parts of the task require different tools or skills
- The task has dependencies that must be resolved in sequence
When Not to Use
- The user has already given step-by-step instructions — execute directly
- The task is a single, well-defined action (e.g., "rename this function")
- The task is purely research — use
deep-researchorquick-research
Inputs
| Input | Type | Required | Description |
|---|---|---|---|
goal |
string | Yes | What the user wants to accomplish |
context |
string | No | Project context, constraints, or existing work |
available_skills |
array | No | Which skills are available for execution |
Expected Outputs
A structured plan containing:
- Goal restatement (clarified)
- Ordered steps with dependencies
- Required tools or skills per step
- Risk assessment per step
- Estimated complexity
Exact Workflow Steps
- Clarify the goal by restating it and asking for confirmation if ambiguous
- Decompose into ordered, atomic steps
- Identify dependencies between steps (blocking, parallel, sequential)
- Map each step to required tools, skills, or agents
- Assess risks per step (e.g., "this step may break existing tests")
- Present the plan for user approval before execution
Required Checks
- [ ] Goal is clarified and unambiguous
- [ ] Steps are ordered with dependencies identified
- [ ] Each step maps to an available tool or skill
- [ ] Risks are documented
Failure Modes
| Failure Condition | Response |
|---|---|
| Goal is too vague to decompose | Ask clarifying questions iteratively |
| No available skill covers a step | Report as uncovered and suggest creating a new skill |
| Steps have circular dependencies | Restructure to break the cycle |
Examples
Example: "Build a CLI tool"
Plan: 1) Choose framework (argparse/click/typer), 2) Define commands, 3) Implement each command, 4) Add tests, 5) Write README
References
| Reference | Path |
|---|---|
| Workflow Orchestrator skill | ../workflow-orchestrator/SKILL.md |
04 同仓库更多 Skills
Workflow Orchestrator
Coordinates multi-skill execution pipelines (e.g., research → plan → build → test)
Web Research
Browser-driven or scraping-based skill for real-time internet extraction using Playwright and HTTP-based fetching
Validation Engine
Checks outputs from other skills for consistency, correctness, and adherence to AGENTS.md rules
Tool Selector
Determines which tools, APIs, MCP actions, or system capabilities are required for a given task
Test Generator
Creates test plans and test cases (unit, integration, edge cases) based on existing or planned code
Skill Generator
Meta-skill that creates new SKILL.md files from research outputs and patterns discovered in execution