Loading...
Loading...
Found 6 Skills
Sanitize OpenClaw agent output before display. Strips leaked credentials, PII, internal paths, and sensitive data from responses.
Automates codebase environment configuration, troubleshooting, and repair. When non-technical users (editors, business personnel, operations staff) get a repository and say things like "it won't run", "how to start", "how to configure the environment", "help me set up the codebase", "initialize the project", "commit code", "what to do about conflicts", it automatically reads ONBOARDING.md, diagnoses environment gaps, fixes dependencies, verifies runnability, and safely completes git operations. It is also used by technical users to quickly standardize the setup process for new repositories (SessionStart hook, PII Guard, history sanitization, project-isolated API keys). This skill is triggered whenever users mention terms like "environment", "configuration", "won't run", "setup", "start", "clone", "how to run", "dependencies", "is it installed", "commit code", "merge conflict", "push failed".
Design and scaffold the code execution pattern for MCP-based agent systems. Use when building agents that interact with many MCP tools, when intermediate data is too large for model context, when you need loops/conditionals across tool calls, or when PII must stay out of the model context. Based on Anthropic's engineering guidance.
Analyzes and enforces security protocols on the skill ecosystem. Operates via Audit, Guard, and Trust modes to prevent malicious commands, PII leakage, and excessive permissions.
Structured logging strategy including log levels, correlation IDs, context propagation, and PII avoidance. Use when designing logging, reviewing log statements, or setting up log aggregation.
Fill a web form by mapping field-name → value, with optional template lookup from browser-templates for known forms