Browse Skills

Tutti Agent Session Replay runs, audits, and freshly replays CDP-recorded Session Replay cassettes from case-repository scenario scripts against live AI Providers. Use it to diagnose transport or semantic-state mismatches and add support for new Agent Targets.

Tutti Architecture Review reviews Tutti git diffs for project structure, layering, module ownership, and duplicate event-center infrastructure. Use it when reviewing a Tutti change or named module for architecture compliance.

Tutti Test Audit audits, designs, writes, revises, or removes Tutti tests. Use it when changing or reviewing unit, component, conformance, integration, regression, platform, or repository tests, enforcing protected contracts, credible failure, correct ownership, negative controls, overlap review, deterministic setup, and CI execution.

Verify runs the app, relevant command, or focused server flow after a code change and reports concrete evidence of what passed, what was not verified, and remaining risk. Use it when a task is not finished until the change is exercised.

Feishu Troubleshooting provides FAQ answers and a /feishu_doctor diagnostic command that checks account configuration, API connectivity, app permissions, and user authorization status to generate detailed reports and solutions for Feishu plugin issues.

Nexu E2E Testing runs end-to-end verification of the Nexu→OpenClaw gateway stack, including skills loading after restart and integration tests against the local stack. Use it when verifying OpenClaw gateway fixes, testing skill loading after restart, or running integration tests.

Process PR Reviews extracts and filters actionable inline review comments from CodeRabbit and Codex pull requests, excluding summaries and nitpicks. Use it when asked to process, fetch, view, count, list, or resolve review feedback in a GitHub PR.

Ast-Grep performs AST-aware code search and rewrite, letting you match code by structure rather than text. Use it for deterministic codemods like rewriting console.log to logger.info, stripping `as any`, or migrating require to import across a codebase.

Bug Fix Contribution debugs a concrete LazyCodex or Codex defect, implements the smallest tested fix in a fresh temporary workspace, and delivers it as a verified-fix issue for LazyCodex-owned repos or a fork PR for upstream openai/codex.

Debugging applies a hypothesis-driven workflow to find root causes of crashes, silent failures, wrong responses, memory leaks, and async misbehavior in any language or binary, using runtime evidence and locking fixes with failing tests. Use it when attaching debuggers, reverse engineering binaries, or reproducing flaky or CI-only failures.

LSP connects Codex to language servers for diagnostics, definitions, references, symbols, and rename safety checks. Use it when you need type-aware feedback or to verify edits in the current workspace.

Programming enforces strict typed, test-driven coding standards across Python, Rust, TypeScript, and Go. Use it before writing or editing code in those languages to load language-specific references and apply the shared seven axioms.