01
Brainstorming
Turn ideas into fully formed designs through collaborative dialogue
Install in Claude Code
1
/plugin marketplace add wezzard/skills 2
/plugin install amplify@wezzard-skills Design Philosophy
Session Start
User Prompt Submit
Pre Tool Use
Post Tool Use
Exit Plan Mode
Enter Plan Mode
Stop
Subagent Stop
Subagent Spawn
Write Plan
Ensures plans follow a reviewable, consistent structure
Triggers structured plan template when writing the plan file
Plan Writing Harness
Prevents ad-hoc planning by requiring template compliance
Enforces use of write-plan skill before writing plan files
Parallelism Reminder
Maximizes concurrent execution of independent work
Reminds to spawn subagents for independent tasks
Parallelism Reminder
Maximizes concurrent execution of independent work
Reminds to spawn subagents for independent tasks
Blind Auditor
Catches defects at task granularity instead of after the whole plan.
Spawns a blind auditor subagent to verify each task before its successors run.
Explore
Emphasizes web search during exploration, injecting a chain-of-thought that checks ground truth source dates and resolves conflicts by recency.
Raw
→
Amplify
Plan
Explains the plan with diagrams and before/after comparisons.
Raw
→
Amplify
Task
Every user prompt triggers a reminder to spawn subagents for independent tasks, ensuring maximum throughput without manual orchestration.
Per-Task Implement-and-Audit
Each task is implemented by one subagent and verified by a separate blind auditor against its acceptance criteria. Successors run only after the audit passes; failures are logged and surfaced in a final audit table.
Explore
Emphasizes web search during exploration, injecting a chain-of-thought that checks ground truth source dates and resolves conflicts by recency.
Raw
↓
Amplify
Plan
Explains the plan with diagrams and before/after comparisons.
Raw
↓
Amplify
Task
Every user prompt triggers a reminder to spawn subagents for independent tasks, ensuring maximum throughput without manual orchestration.
Per-Task Implement-and-Audit
Each task is implemented by one subagent and verified by a separate blind auditor against its acceptance criteria. Successors run only after the audit passes; failures are logged and surfaced in a final audit table.
Skills
6 available 02
Write Plan
Create structured development plans with built-in verification and human oversight
03
Execute Plan
Turn your development plans into working code with automated execution and human oversight.
04
Be Thorough
Investigate, verify, and test before you conclude.
05
Same Page
Re-explain your reasoning with evidence and visuals so users truly understand.
06
Divide and Conquer
Break big jobs into parallel, subagent-driven task graphs