ccw-cli-tools
CLI tools execution specification (gemini/claude/codex/qwen/opencode) with unified prompt template, mode options, and auto-invoke triggers for code analysis and implementation tasks. Supports configurable CLI endpoints for analysis, write, and review modes.
npx skills add majiayu000/claude-skill-registry --skill ccw-cli-tools --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Orchestrates CLI tool usage through a configuration-driven workflow. It loads a global configuration file, infers user intent and required capabilities, selects an enabled tool (with models), builds a 6-field prompt, selects an execution rule, runs a CLI command, and handles results with fallbacks to secondary models or tools if needed.
How it works
- Initialization: Checks in-memory configuration; if absent, reads
~/.claude/cli-tools.jsonviaRead(file_path="~/.claude/cli-tools.json")and parsestoolsforenabled,primaryModel,secondaryModel,tags, andtype. - Process Flow: Follows STEP 1 load config, STEP 2 understand intent, STEP 3 select tool (explicit
--toolif provided, else tag-based matching, else first enabled tool), STEP 4 build prompt using a 6-field template (PURPOSE, TASK, MODE, CONTEXT, EXPECTED, CONSTRAINTS), STEP 5 select rule via--rule, STEP 6 execute command:ccw cli -p "<PROMPT>" --tool <tool> --mode <mode> --rule <rule>, STEP 7 handle results with success or fallback tosecondaryModelor another tool. - Configuration: Reads from
~/.claude/cli-tools.json(memory-first when available). Structure of each tool includesenabled,primaryModel,secondaryModel,tags, andtype. - Prompt Template: Uses the universal 6-field template for all commands, including
PURPOSE,TASK,MODE,CONTEXT,EXPECTED, andCONSTRAINTS.
When to use it
- When you want to perform code analysis, implementation, or review tasks via CLI-tools, selected from a configured set of tools, with a unified prompt and routing based on capabilities.
What it can touch
- Tools:
gemini(builtin),qwen(builtin),codex(builtin),claude(builtin),opencode(builtin) as reference. The actual touch depends onenabledstatus andprimaryModel/secondaryModelin~/.claude/cli-tools.json. - Execution:
ccw cli -pprompts fed to the selected tool via--tool,--mode, and--rule.
Caveats
- Requires
~/.claude/cli-tools.jsonto exist for non-in-memory setups. Configuration may differ between environments; tool availability and models come from the file. - Default behavior if no tag match: use the first enabled tool in the config.
- Tool selection prioritizes explicit tool specification over tag-based routing, then falls back to the first enabled tool.
# CLI Tools - Unified Execution Framework **Purpose**: Structured CLI tool usage with configuration-driven tool selection, unified prompt templates, and quality-gated execution. **Configuration**: `~/.claude/cli-tools.json` (Global, always read at initialization) ## Initialization (Required First Step) **Before any tool selection or recommendation**: 1. Check if configuration exists in memory: - If configuration is already in conversation memory → Use it directly - If NOT in memory → Read the configuration file: ```bash Read(file_path="~/.claude/cli-tools.json") ``` 2. Parse the JSON to understand: - Available tools and their `enabled` status - Each tool's `primaryModel` and `secondaryModel` - Tags defined for tag-based routing - Tool types (builtin, cli-wrapper, api-endpoint) 3. Use configuration throughout the selection process **Why**: Tools, models, and tags may change. Configuration file is the single source of truth. **Optimization**: Reuse in-memory configuration to avoid redundant file reads. ## Process Flow ``` ┌─ USER REQUEST │ ├─ STEP 1: Load Configuration │ ├─ Check if configuration exists in conversation memory │ └─ If NOT in memory → Read(file_path="~/.claude/cli-tool
- Initialization (Required First Step)
- Process Flow
- Configuration Reference
- Configuration File Location
- Reading Configuration
- Configuration Structure
- Expected Tools (Reference Only)
- Configuration Fields
- Universal Prompt Template
- Field Specifications
- CLI Execution Modes
- MODE: analysis
- MODE: write
- MODE: review
Read configuration file cat ~/.claude/cli-tools.json ccw cli -p "PURPOSE: [goal] + [why] + [success criteria] + [scope] ccw cli -p "<PROMPT>" --tool <tool-id> --mode <analysis|write|review> Single directory ccw cli -p "CONTEXT: @**/* @../shared/**/*" \ Multiple directories ccw cli -p "..." \ ccw cli -p "Continue analyzing" --tool <tool-id> --mode analysis --resume # Resume last ccw cli -p "Fix issues found" --tool <tool-id> --mode write --resume <id> # Resume specific
What does the ccw-cli-tools skill do?
CLI tools execution specification (gemini/claude/codex/qwen/opencode) with unified prompt template, mode options, and auto-invoke triggers for code analysis and implementation tasks. Supports configurable CLI endpoints for analysis, write, and review modes.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill ccw-cli-tools --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.