Brainstorm individual plugin components (skill, agent, command, hook) for existing or planned plugins. Trigger: ideate component, brainstorm skill, new agent idea, component concept, add skill to plugin.
From pqanpx claudepluginhub javimontano/jm-adk --plugin plugin-qaThis skill is limited to using the following tools:
examples/skill-ideation.mdprompts/component-brainstorm.mdreferences/component-patterns.mdSearches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Enables AI agents to execute x402 payments with per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents pay for APIs, services, or other agents.
"A component earns its place by doing one thing that no other component does."
Brainstorm individual components (skill, agent, command, or hook) for an existing or planned plugin. Produces a concept card that defines the component's responsibility, relationships, and placement within the plugin structure.
This is a read-only skill. It proposes but never creates files.
skill, agent, command, or hook.references/component-patterns.md for the decision matrix.plugin.json, list existing skills/agents/commands/hooks.[CODIGO] for file-derived info, [SUPUESTO] for assumptions.MINIMAL: SKILL.md only (simple, self-contained components).STANDARD: SKILL.md + references/ (needs reference material).FULL: SKILL.md + references/ + examples/ (complex, benefits from examples).DEEP: SKILL.md + references/ + examples/ + prompts/ (user-facing, needs prompt templates).## Component Concept Card
- Type: {skill|agent|command|hook}
- Name: {recommended-name}
- Responsibility: {one-sentence}
- Movement: {movement-name or N/A}
- Dependencies: {list}
- Conflicts: {list or "none"}
- MOAT Depth: {MINIMAL|STANDARD|FULL|DEEP}
- Tools Needed: {list}
- Estimated Lines: {range}
/pqa:design.[DOC][CODIGO][CODIGO][DOC][DOC]Bad concept card:
- Type: skill
- Name: do-stuff
- Responsibility: Does stuff.
Missing: no movement, no dependencies, no conflicts, no MOAT depth, no tools.
Good concept card:
## Component Concept Card
- Type: skill
- Name: validate-config
- Responsibility: Validates plugin configuration files against their JSON schemas.
- Movement: VALIDATE
- Dependencies: validate-manifest (shares plugin.json parsing), audit-security (config may contain secrets)
- Conflicts: None — validate-manifest checks plugin.json only; this covers settings.json and hooks.json
- MOAT Depth: STANDARD (needs reference for config schemas)
- Tools Needed: Read, Glob, Grep
- Estimated Lines: 80-120
Includes: type, descriptive name, precise responsibility, movement placement, dependencies, conflict analysis, MOAT depth with rationale, tool list, line estimate.