planlisted
Install: claude install-skill synaptiai/agent-capability-standard
## Intent
Create a structured, executable plan that decomposes a goal into ordered steps with clear dependencies, verification criteria for each step, checkpoint placement for safety, and rollback strategies for recovery.
**This capability is the GATEWAY to all actions.** No mutating operation should proceed without a validated plan.
**Success criteria:**
- Goal is decomposed into atomic, verifiable steps
- Dependencies form a valid DAG (no cycles)
- Each mutating step has rollback strategy defined
- Checkpoints placed before high-risk operations
- Estimated risk level accurately reflects plan complexity
**Compatible schemas:**
- `schemas/output_schema.yaml`
## Inputs
| Parameter | Required | Type | Description |
|-----------|----------|------|-------------|
| `goal` | Yes | string | Clear statement of what the plan should achieve |
| `context` | No | object | Current state, available resources, constraints |
| `constraints` | No | object | Time limits, resource bounds, policy restrictions |
| `risk_tolerance` | No | string | low, medium, high - affects checkpoint frequency |
| `max_steps` | No | integer | Maximum number of steps to generate |
## Procedure
1) **Understand the goal**: Parse and clarify the objective
- Identify success criteria explicitly
- Detect ambiguity and resolve or flag it
- Determine scope boundaries
2) **Analyze context**: Gather relevant information
- Read minimal files needed to understand current state
- Identify existing pat