Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Deep business logic bug finder using the Feynman technique. Language-agnostic — works on Solidity, Move, Rust, Go, C++, or any codebase. Questions every line, every ordering choice, every guard presence/absence, and every implicit assumption to surface logic bugs that pattern-matching misses. Triggers on /feynman, feynman audit, or deep logic review.
The Inescapable Auditor. Runs the full Feynman Auditor (Stage 1) and full State Inconsistency Auditor (Stage 2) as primary steps, then fuses their outputs in a feedback loop (Stage 3) to find bugs at the intersection that neither alone would catch. Language-agnostic. Triggers on /nemesis or nemesis audit.
Finds state inconsistency bugs where an operation mutates one piece of coupled state without updating its dependent counterpart, causing silent data corruption or reverts in subsequent operations. Triggers on /state-audit, state inconsistency audit, or coupled state audit.
Use when Rudder development work needs first-principles advisor analysis plus independent reviewer rounds: proposals, UI/product decisions, architecture, release readiness, workflow changes, agent outcomes, explicit acceptance gates, repeated review, or “没有通过 review 返工”.
Capture GPU kernel ATT (Advanced Thread Trace) via rocprofv3 on a remote Docker container or locally. Discovers kernel names, configures input.yaml with the target kernel_include_regex, runs rocprofv3 -i input.yaml with FLYDSL_DEBUG_ENABLE_DEBUG_INFO=1, and downloads the latest ui_output_agent_* directory for analysis. Usage: /capture-kernel-trace <test_script.py> [kernel_name_pattern]
Review code for quality, simplicity, and common mistakes before declaring work complete.
读取当前项目 code-review 文件夹中按分支名生成的审查结果，修复 P0、P1 问题，并继续修复必要问题直到下一次 code-review 评分超过 80 分
Use when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debugging help, or alternative implementation proposals. Requires Codex CLI to be installed and authenticated.
Use when reviewing a local Codex session, task, thread, or commit as a product manager or first-principles reviewer for product correctness, scope, behavior, validation, and whether the task solved the right user problem.
Complete testing strategy covering TDD workflow, test pyramid, unit/integration/E2E/property testing, framework best practices (Jest, Vitest, pytest), mock strategies, and CI integration. Use when writing tests, reviewing test quality, or establishing testing standards.