Planner
Skill Razaib-khan/ForgeWeave/src/forgeweave/templates/gemini/.gemini/skills/planner
Converts user intent into structured execution plans, including steps, dependencies, risks, and required toolsFrom its SKILL.md
npx -y skills add Razaib-khan/ForgeWeave --skill plannerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
2.7 KB, 562 tokens by cl100k_base, as published. Nobody here has run it
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 |
What ships with it: 3 files
3.1 KB alongside SKILL.md, 1 of them executable
references/
scripts/
- decompose_task.pyruns1.9 KB
templates/
- plan_template.md391 B
Gives 0 of the 12 instructions most plan spec skills give in 562 tokens
Counted across 1,099 of the 1,860 authors here whose files we hold, read 2026-08-07
- Ask one question at a timein 51 of 1099
- Break plans into vertical slicesin 29 of 1099, across 11 files
- Publish issues in dependency orderin 27 of 1099, across 9 files
- Iterate until user approves the breakdownin 25 of 1099, across 7 files
- Explore the repository to understand the codebase statein 24 of 1099, across 7 files
- Use domain glossary vocabularyin 23 of 1099, across 5 files
- Apply correct triage labels to published issuesin 23 of 1099, across 5 files
- Prefer AFK slices over HITLin 22 of 1099, across 7 files
- Write a specification before writing any codein 22 of 1099, across 14 files
- Write failing tests before implementation codein 22 of 1099, across 20 files
- Ask clarifying questions until requirements are concretein 21 of 1099, across 13 files
- Respect existing architecture decision recordsin 20 of 1099, across 5 files
Said here and by no other author read
- Decompose goal into ordered atomic steps
- Map each step to required tools
- Assess risks for each step
- Ask questions iteratively if goal is too vague
- Report steps with no matching skill as uncovered
- Restructure steps to break circular dependencies
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.