nano-banana-pro-prompts-recommend-skill
AI skill for OpenClaw & Claude Code — recommend from 10000+ Nano Banana Pro (Gemini) image prompts. Smart search by use case, content remix, sample images.
Explore codebase and create spec + phased implementation plan with file-level task breakdown. Use when user says "plan this feature", "create implementation plan", "write a spec", "battle plan", or describes a feature/bug/refactor. Zero questions — researches code instead. Do NOT use for idea validation (use /validate) or execution (use /build).
请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求,再添加到工作流。
SkillHub CLI
skillhub install fortunto2/solo-plan打开来源仓库,查看说明和兼容环境后,按来源提供的命令或步骤安装。
将来源链接提供给你的 Agent,让它先读取说明、核对依赖,并向你说明将执行的安装步骤。
This skill is self-contained — follow the steps below instead of delegating to external planning skills (superpowers, etc.).
Research the codebase and create a spec + phased implementation plan. Zero interactive questions — explores the code instead.
Creates a track for any feature, bug fix, or refactor with a concrete, file-level implementation plan. Works with or without /setup.
session_search(query) — find similar past work in Claude Code chat historyproject_code_search(query, project) — find reusable code across projectscodegraph_query(query) — check dependencies of affected filescodegraph_explain(project) — architecture overview: stack, languages, directory layers, key patterns, top dependencies, hub fileskb_search(query) — search knowledge base for relevant methodologyIf MCP tools are not available, fall back to Glob + Grep + Read.
Parse task description from $ARGUMENTS.
Detect context — determine where plan files should be stored:
Project context (normal project with code):
package.json, pyproject.toml, Cargo.toml, *.xcodeproj, or build.gradle.kts exists in working directorydocs/plan/{trackId}/
Knowledge base context (documentation-centric project):
docs/, notes/, or structured numbered directories existdocs/plan/{shortname}/
Set $PLAN_ROOT based on detected context. All subsequent file paths use $PLAN_ROOT.
Load project context (parallel reads):
CLAUDE.md — architecture, constraints, Do/Don'tdocs/prd.md — what the product does (if exists)...这些信息来自收录时的来源分析,可能滞后;使用前请核对最新来源文件。
# /plan
This skill is self-contained — follow the steps below instead of delegating to external planning skills (superpowers, etc.).
Research the codebase and create a spec + phased implementation plan. Zero interactive questions — explores the code instead.
## When to use
Creates a track for any feature, bug fix, or refactor with a concrete, file-level implementation plan. Works with or without `/setup`.
## MCP Tools (use if available)
- `session_search(query)` — find similar past work in Claude Code chat history
- `project_code_search(query, project)` — find reusable code across projects
- `codegraph_query(query)` — check dependencies of affected files
- `codegraph_explain(project)` — architecture overview: stack, languages, directory layers, key patterns, top dependencies, hub files
- `kb_search(query)` — search knowledge base for relevant methodology
If MCP tools are not available, fall back to Glob + Grep + Read.
## Steps
1. **Parse task description** from `$ARGUMENTS`.
- If empty, ask via AskUserQuestion: "What feature, bug, or refactor do you want to plan?"
- This is the ONE question maximum.
2. **Detect context** — determine where plan files should be stored:
**Project context** (normal project with code):
- Detected by: `package.json`, `pyproject.toml`, `Cargo.toml`, `*.xcodeproj`, or `build.gradle.kts` exists in working directory
- Plan path: `docs/plan/{trackId}/`
**Knowledge base context** (documentation-centric project):
- Detected by: NO package manifest found, BUT directories like `docs/`, `notes/`, or structured numbered directories exist
- Plan path: `docs/plan/{shortname}/`
- Note: the shortname is derived from the task (kebab-case, no date suffix for the directory)
Set `$PLAN_ROOT` based on detected context. All subsequent file paths use `$PLAN_ROOT`.
3. **Load project context** (parallel reads):
- `CLAUDE.md` — architecture, constraints, Do/Don't
- `docs/prd.md` — what the product does (if exists)...AI skill for OpenClaw & Claude Code — recommend from 10000+ Nano Banana Pro (Gemini) image prompts. Smart search by use case, content remix, sample images.
AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agent-to-agent messaging. Manage Claude, Codex or any AI Agent from one dashboard. Move Agents between c...
AI agent skills for the Universal Registry - search, chat, and register 72,000+ agents across 14+ protocols. Works with Claude, Codex, Cursor, OpenClaw, and any AI assistant.
A cross-platform skills manager for AI IDEs. Search marketplace, download locally, and install to Claude, Cursor, Windsurf, and more with one click.