skills.rest
jellydn
jellydnCOMMUNITY
Explore all skills by this author →
Website𝕏@jellydnGitHub

ccs-delegation

Automate CCS CLI delegation by auto-selecting profiles from config.json.

114|13|Updated Jan 8, 2026
Search Tags:#delegation#CLI#deterministic#prompt-enhancement#profile-selection#ccs
One-click install
npx skills add https://github.com/jellydn/my-ai-tools --skill ccs-delegation-jellydn
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ccs-delegation
Source: https://github.com/jellydn/my-ai-tools/tree/main/configs/gemini/skills/ccs-delegation
Command: npx skills add https://github.com/jellydn/my-ai-tools --skill ccs-delegation-jellydn

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates deterministic task delegation to the CCS CLI by auto-selecting the optimal profile from the local config and enriching prompts with contextual information. It reduces manual profile tuning and prompt crafting, enabling faster, more reliable delegation.

Core Features & Use Cases

  • Auto-selects the best CCS profile from ~/.ccs/config.json based on the task requirements.
  • Enhances prompts with context and preserves user slash commands for seamless interaction.
  • Executes delegation via CCS CLI (ccs {profile} -p "task" or ccs {profile}:continue) and reports results.
  • Triggers on natural phrases like "use ccs [task]" or tweaks like "ccs --glm [task]" and adapts for follow-ups.
  • Use Case: delegating a code-quality review to the cost-effective glm profile, or long-context reasoning with kimi for architecture discussions.

Quick Start

Trigger delegation by typing a natural prompt such as: use ccs to analyze the codebase in src/ or use ccs --kimi "refactor module X". The skill will auto-select a profile, augment the prompt, run the delegation, and present results.

Frequently Asked Questions about ccs-delegation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate CCS CLI delegation for deterministic tasks?▼

Automate CCS CLI delegation by using natural triggers like 'use ccs [task]'. The system parses input, auto-selects an optimal profile from ~/.ccs/config.json, enhances prompts with context, executes the task, and reports results and costs.

How does auto profile selection work for CCS commands?▼

Auto profile selection reads your local ~/.ccs/config.json file to evaluate task requirements. It automatically matches the deterministic task to the best available profile, reducing manual configuration and ensuring reliable CLI execution.

Can I manually override the CCS profile for a specific task?▼

Yes, you can manually specify a profile using tweaks like 'ccs --kimi [task]' or 'ccs --glm [task]'. This overrides auto-selection, allowing you to target specific models like kimi for long-context reasoning or glm for cost-effective reviews.

How do I continue a CCS delegation task across different contexts?▼

Continue CCS delegation tasks by appending ':continue' to the profile name, such as 'ccs {profile}:continue'. This preserves the conversation context and allows follow-up interactions without restarting the prompt enhancement process.

Do I need to manually format prompts before delegating to the CCS CLI?▼

No, you do not need to manually format prompts. The delegation process automatically enhances your input with contextual information and preserves user slash commands to ensure seamless interaction with the CCS CLI.

What is the best way to execute a code-quality review using the CCS CLI?▼

Delegate a code-quality review by triggering the command 'use ccs to review src/'. The system auto-selects a cost-effective profile like glm, augments the prompt with context, runs the CLI delegation, and presents the results.

Related Skills

Explore More Software Engineering Skills→
kaitrannttkaitranntt
2.8k

ccs-delegation

Delegate deterministic tasks to the CCS CLI with auto-profile selection.

Community
Advanced
JansenAnalyticsJansenAnalytics
5

model-usage

Summarize per-model usage and costs from CodexBar local logs.

Community
Intermediate
Codename-IncCodename-Inc

spectre_agent_tools

Detect @agent and /command patterns and dispatch to Spectre subagents.

Official
Intermediate
Snowflake-LabsSnowflake-Labs
12

read-ors-configuration

A concise summary of your roleplay character: name,</name> personality, and/or behavior, formatted as a single string sentence. Typically不超过50字，此处省略

Official
Intermediate