codyswanngt/lisa
Overview
This skill provides a knowledge base and practical guidance for creating and configuring anthropics/claude-code-action GitHub workflows. It focuses on authentication options, common workflow patterns (interactive, CI auto-fix, nightly), permission settings, tool allowlisting, and cost/security controls. Follow the patterns and inputs here to safely automate Claude-powered code tasks in CI and PR contexts.
How this skill works
The skill inspects and documents workflow inputs, triggers, and best-practice blocks you should include in GitHub Actions using claude-code-action. It explains the authentication choices (OAuth, API key, AWS Bedrock, GCP Vertex), standard permissions, allowed tools, and recommended guards against infinite loops and excessive cost. It also includes reusable snippets for interactive, CI auto-fix, and scheduled workflows and guidance for passing MCP config and secrets.
When to use it
- Add interactive responses to PRs or issue mentions when contributors tag @claude.
- Run automated code fixes after failing CI workflows to propose or open fix PRs.
- Perform maintenance tasks nightly or on a schedule (test improvements, coverage).
- Integrate Claude into CI for linting, refactors, or repository-wide updates.
- Set up secure, cloud-hosted Claude access via AWS Bedrock or GCP Vertex.
Best practices
- Prefer CLAUDE_CODE_OAUTH_TOKEN (requires Claude Pro/Max) for most CI setups; store as a GitHub secret.
- Never hardcode credentials; reference secrets like ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}.
- Use permissions block with minimal required scopes (contents: write, pull-requests: write, issues: write, actions: read, id-token: write).
- Guard CI automations to prevent infinite loops and exclude main/stable branches from auto-fix runs.
- Limit API usage with --max-turns per role: interactive unlimited, CI auto-fix ~25, nightly ~30.
- Allowlist only necessary tools (file ops, git, package managers, gh) and sanitize prompt inputs to avoid injection.
Example use cases
- Trigger Claude on PR comment to generate a concise code change suggestion or unit tests.
- Automatically run a CI quality-check workflow; on failure, have Claude propose fixes in a new branch and PR.
- Run nightly test-improvement passes that update flaky tests or improve coverage with an opt-in variable.
- Use Claude behind AWS Bedrock or GCP Vertex for enterprise-hosted model inference with cloud credentials.
- Integrate MCP configuration via claude_args to route requests through a private control plane.
FAQ
Use the OAuth token (CLAUDE_CODE_OAUTH_TOKEN) for most setups if you have Claude Pro/Max; use API keys or cloud provider credentials only when OAuth is not available or you require cloud-hosted instances.
How do I prevent automated fixes from creating infinite PR loops?
Add conditions that skip branches created by the automation, exclude main/staging/dev, and check the triggering workflow conclusion. Example: ensure head_branch does not start with the auto-fix prefix and only run when the CI workflow concluded with failure.
24 skills
This skill helps you configure and run Claude code-action workflows in GitHub, simplifying authentication, scheduling, and governance checks.
This skill manages the local Expo and serverless backend stack, starting, stopping, and monitoring full or individual services for rapid iteration.
This skill performs AI-powered mutation testing to reveal test gaps by generating mutants, running tests, and guiding hardening efforts.
This skill coordinates end-to-end planning and execution of complex requests by assembling an agent team, breaking work into tasks, and ensuring verification.
This skill creates conventional commits, submits a pull request, and verifies approval, auto-merging after checks pass.
This skill assists you create conventional commits for current changes by grouping files into feature, fix, or docs commits and ensuring a clean working tree.
This skill runs an OWASP ZAP baseline scan via Docker, analyzes results by risk, and offers remediation guidance.
This skill automates browser-based user acceptance testing with Playwright MCP tools, logging in, navigating features, and capturing visual proof via
This skill fixes ESLint violations across the codebase by analyzing errors, grouping by rule, and proposing actionable plan and tasks.
This skill manages database migrations, schema generation, and GraphQL codegen for Expo and serverless backends, with safe, environment-aware operations.
This skill reduces cognitive complexity threshold by two, identifies violations, and creates a practical plan to refactor code now.
This skill reviews pull request comments, generates a plan to address unresolved feedback, and bootstraps fixes to meet project standards.
This skill monitors Sentry for unresolved frontend and backend errors, filtering by project, environment, and time range to help you triage quickly.
This skill applies Lisa templates to a downstream project, validates build and tests, and retries with upstream fixes until all checks pass.
This skill reduces the maximum lines per file by updating eslint thresholds, identifying oversized files, and generating a refactoring plan with split tasks.
This skill helps you view and filter logs across local processes, browser, device, and remote CloudWatch to diagnose issues quickly.
This skill helps you design Claude Code agent files with focused domains, minimal tool access, and reusable definitions for safer, scalable AI teams.
This skill syncs your current session tasks to a project directory, ensuring persistence and automatic future updates.
This skill creates conventional commits, opens PRs, verifies approvals, and ensures deploy success across iterations for AI-assisted development.
This skill analyzes the last PR against SonarQube quality gates and reports all failure details from the MCP server.
This skill syncs plan progress to a linked JIRA ticket, posting milestones, branch and PR links to keep tickets aligned.
This skill analyzes Expo and serverless app performance, running Lighthouse audits, bundle size checks, and k6 load tests to optimize reliability.
This skill automates health checks for frontend and backend services across environments, reporting response times and status to guide remediation.
This skill helps compare Lisa's templates to a target project, identify drift, and propose adopting improvements back into Lisa.
