quality-assurance-auditor
Audit the complete mathematical modeling solution before final submission and identify blocking issues.
265 repo starsObserved in 2 repos
Testing & Quality
Testing & Quality skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
robustness-checker
Design and run robustness, sensitivity, error, and baseline comparison checks.
265 repo starsObserved in 2 repos
Testing & Quality
bit-packed-double-debug
Debug pattern for bit-packed double parameters in yishape-math graph execution — Java packs integers into doubles via Double.longBitsToDouble(), Rust must unpack with f64::to_bits(), NOT 'as u64'. Covers the conv2d/maxpool2d scalarParam encoding and common decode bugs.
265 repo starsObserved in 1 repos
Testing & Quality
console-tests
Write tests for the akash-network/console monorepo following established team patterns and reviewer expectations. Use this skill whenever you need to write, fix, review, or refactor tests in the console project — including unit tests, functional tests, integration tests, or E2E tests for both frontend (deploy-web) and backend (api, notifications, indexer, provider-proxy). Also trigger when the user mentions 'write tests', 'add tests', 'fix tests', 'test this', 'spec file', or asks about testing patterns in the console codebase. When in doubt about whether to use this skill for a testing task in this repo, USE IT.
265 repo starsObserved in 1 repos
Testing & Quality
exercise_cluster
Deploy MultigresCluster fixtures, run mutation scenarios, and validate health using the observer. Finds bugs in the operator and upstream multigres by exercising real cluster operations and verifying end-to-end health beyond CRD phase status. Use this skill whenever the user wants to test the operator, exercise the cluster, run exerciser scenarios, validate cluster health after changes, find bugs through mutation testing, or deploy and mutate fixtures.
265 repo starsObserved in 1 repos
Testing & Quality
gpu-hpc-fallback-debug
Debug the GPU→HPC→CPU fallback chain in yishape-dl Trainer. When GPU is AVAILABLE but execution silently falls back to HPC or CPU, this skill covers the fallback chain, how to trace which path executed, and common causes for GPU silent failure.
265 repo starsObserved in 1 repos
Testing & Quality
senpi-qa
Manual QA harness for the senpi coding agent itself. MUST USE after changing packages/ai, packages/agent, packages/coding-agent, or packages/tui — a green typecheck and `npm test` are NOT QA. Drives the real CLI from source in an isolated sandbox (never touches ~/.senpi or real credentials) across four channels: remote RPC (--mode rpc JSONL stdio), TUI smoke (node-pty on Windows, tmux on POSIX), mock loop (a local fake model server for deterministic, zero-token agent-loop runs), and CLI smoke (--help/--print/--list-models). Every helper ships a --self-test. Use whenever someone says qa senpi, test the agent, verify my change, rpc qa, tui qa, mock-loop qa, smoke the cli, or needs evidence that an agent-loop, tool, keybinding, or provider change works end to end. Capture evidence to local-ignore/qa-evidence/.
265 repo starsObserved in 1 repos
Testing & Quality
tmux-manual-qa
Run a single manual tmux-based QA scenario for the todo continuation feature against the real CLI (./pi-test.sh) in an interactive TUI. Captures scrollback, asserts deterministic pass/fail count markers, and cleans up test fixtures. Use only for the manual-qa milestone features.
265 repo starsObserved in 1 repos
Testing & Quality
sibyl-codex-reviewer
Sibyl Codex 独立第三方审查 - 使用 OpenAI Codex 提供不同 AI 视角的评审
264 repo starsObserved in 3 repos
Testing & Quality