Skill

strategic-planning

From nx

Use when facing multi-step development work that needs decomposition into tasks, before writing any implementation code

npx claudepluginhub hellblazer/nexus --plugin nx

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Delegates to the **strategic-planner** agent. See [registry.yaml](../../registry.yaml) for details.

SKILL.md

Similar Skills

plan

332

Decompose goals into issue plans.

15 files

agentops

plan

129

Creates tactical implementation plans for features/tasks: analyzes codebase with grep/Bash, breaks into specific subtasks, identifies dependencies, defines success criteria.

4 tools

core

plan-crafting

Generates executable Markdown implementation plans for multi-step tasks from context briefs, resolving ambiguities, ordering dependencies, and enabling parallel worker execution.

engineering-discipline

Stats

Parent Repo Stars1

Parent Repo Forks0

Last CommitMar 22, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Strategic Planning Skill

Delegates to the strategic-planner agent. See registry.yaml for details.

When This Skill Activates

Before implementing a feature, component, or module
After brainstorming-gate approves a design — decompose into executable tasks
When creating beads for a multi-phase effort
When breaking vague requirements into concrete, sequenced steps
Before architectural changes affecting multiple files or modules

Agent Invocation

Use the Agent tool to invoke strategic-planner:

## Relay: strategic-planner

**Task**: [what needs to be done]
**Bead**: [ID] or 'none'

### Input Artifacts
- Files: [relevant files]

### Deliverable
Implementation plan with tasks and dependencies

### Quality Criteria
- [ ] Execution plan created
- [ ] Dependency graph established
- [ ] Success criteria defined per task

For full relay structure and optional fields, see RELAY_TEMPLATE.md.

Planning Methodology

The agent uses mcp__sequential-thinking__sequentialthinking:

Analyze codebase to understand context and constraints
Form hypothesis about optimal architecture approach
Validate approach against existing patterns
Break down work into logical tasks
Identify dependencies between tasks
Create beads for trackable work items
Define success criteria and test strategy

REQUIRED SUB-SKILL: Use nx:plan-validation (plan-auditor) after creating any plan.

Success Criteria

Epic/feature breakdown documented
Phased execution plan created
Dependency graph established
Beads created for all tasks
Success criteria defined per task
Risks identified and mitigated
Plan validated by plan-auditor

Agent-Specific PRODUCE

Outputs generated by the strategic-planner agent:

T3 knowledge: Validated architectural decisions via store_put tool: content="# Decision: {topic}\n{rationale}", collection="knowledge", title="decision-planner-{topic}", tags="decision,planning"
T2 memory: Continuation state via memory_put tool: content="content", project="{project}", title="continuation-state.md", ttl="30d"
T1 scratch: Analysis notes via scratch tool: action="put", content="Planning note: {consideration}", tags="planning,analysis" (flagged for T2 at plan completion)
Beads: Epic and task beads with context links, success criteria, and file paths

Session Scratch (T1): Agent uses scratch tool for ephemeral working notes during the session. Flagged items auto-promote to T2 at session end.