OpenClaw skill
coding-opencode
An OpenClaw skill named coding-opencode that enables agents to interact with the OpenCode coding environment. It provides tools for generating code, executing code in a sandbox, viewing execution results, and managing code files. The skill supports multiple programming languages through OpenCode's interpreter capabilities.
Security notice: review the SKILL.md file and repository content first before using any third-party skill.
Files
Review the files below to add this skill to your agents.
SKILL.md content
Unable to load SKILL.md content from source.
How this skill works
- The skill receives a 'task' input: a string describing what code needs to be written or executed
- The skill generates Python code using an LLM prompted with the task and OpenCode instructions
- The generated Python code is executed in a sandboxed OpenCode environment
- The skill captures the execution output, including stdout, stderr, and any returned values
- The output is formatted and returned to the agent as the 'result'
When to use it
- When the agent needs to generate Python code for solving programming problems
- When executing and testing generated code snippets in a sandboxed environment
- When refining or debugging existing code provided by the user
- When creating scripts for data analysis or manipulation
Best practices
- Set the `OPENAI_API_KEY` environment variable before using the skill
- Always review and verify generated code for accuracy
- Use low temperature (e.g., 0.2) for more deterministic code generation
- Configure `max_tokens` appropriately to avoid truncation
- Test skill with simple coding queries initially
Example use cases
- Code generation from natural language: Uses the generate_code tool to create new code snippets in specified programming languages based on descriptive prompts, as listed in the tools section.
- Code completion for partial snippets: Employs the complete_code tool to finish incomplete code provided as input, supporting specified languages, per the documented tool functionality.
- Code explanation and understanding: Leverages the explain_code tool to provide detailed breakdowns and interpretations of submitted code snippets, directly from the skill's tools.
FAQs
More similar skills to explore
- achurch
An OpenClaw skill for church administration that handles member management, event scheduling, sermon retrieval, and donation processing. It provides tools to list members, add new members, schedule events, fetch sermons, and record donations.
- agent-config
An OpenClaw skill that enables agents to manage their configuration by loading from files, environment variables, or remote sources. It supports retrieving, setting, and validating configuration values. The skill allows for hot-reloading of configurations.
- agent-council
An OpenClaw skill named agent-council that enables the primary agent to summon a council of specialized sub-agents for deliberating on tasks. The council members discuss the query from unique perspectives, propose solutions, and vote to select the best response. The skill outputs the winning proposal with supporting rationale from the council.
- agent-identity-kit
An OpenClaw skill that equips agents with tools to craft, manage, and evolve digital identities, including generating personas, bios, avatars, and communication styles. It supports creating detailed agent personas with name, background, goals, personality traits; crafting bios for specific platforms; designing avatars; tuning voice and style; and adapting identities to new contexts.
- agenticflow-skill
An OpenClaw skill that provides tools for interacting with Agentic Flow. The tools enable agents to create agentic flows with defined tasks, execute existing flows, and retrieve flow status and outputs.
- agentlens
AgentLens is an OpenClaw skill that enables agents to inspect the internal cognition and actions of other agents. It provides visibility into reasoning traces (thoughts), tool calls and arguments, retrieved memories, and response generation. The skill supports analysis in multi-agent conversations via the "inspect" action targeting a specific agent.