debug-and-fix
Strategies for debugging build failures, runtime errors, writing complete output files (ICS/JSON/config), and constraint satisfaction tasks.
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Strategies for debugging build failures, runtime errors, writing complete output files (ICS/JSON/config), and constraint satisfaction tasks.
Verification patterns to confirm task completion before submitting. Read this before calling submit().
Resolve open drift contracts — the review obligations between code and docs declared in drift.toml. Use whenever `make drift-check` (or the `make check` aggregate, or the CI lint-drift job) fails with open contracts, when the user says "drift check failed", "resolve the drift contract", "ack the drift", "run drift plan", or after any change that touches drift trigger files (the config model / pipelex.toml, CLI code, the keyword-only guard). Also use when recording a drift dogfood observation. Performs the review for real, records an honest ack, and logs the dogfood observation the pilot phase depends on.
Test an AI model on a specific backend using the Pipelex inference test infrastructure. Handles test profile creation, fixture regeneration, and running the right test class for the model type (LLM, image gen, extract, search). Use when the user says "test model X", "test gpt-5.4 on openai", "test model on gateway", "run inference test for model", "try model X on backend Y", "verify model X works", or any variation of running inference tests against a specific model on a specific backend. Also use when the user mentions testing a model after adding it, or wants to verify a model works end-to-end with real API calls.
Guide for writing tests in torch-harmonics. Use this skill whenever the user asks to add tests, check or extend test coverage, write a new test class, test a new layer or kernel, or add distributed tests. Also use when the user asks about tolerance values, how to compare tensors, how to structure distributed test infrastructure, or how to test gradients. Covers serial tests in test_convolution.py and distributed tests in test_distributed_*.py.
在临时目录中用 uvx 或 uv tool run 安装 specify-cn 的 main 分支最新提交,对源码声明支持的 agent 执行 init,并校验版本、中文化、模板完整性、agent 文件落点与 ai-skills 安装结果。用于本地发布后验收。
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos (auto-detected). Activates on "revdiff", "review diff", "review changes", "annotate diff", "git review with revdiff", "hg review with revdiff", "review jj change", "interactive diff review", "revdiff all files", "review all files", "browse all files", "revdiff <file>", "revdiff README.md", "revdiff /tmp/notes.txt", "review this file", "annotate this file", "review file with revdiff", "open this review in revdiff", "show review in revdiff", "review in revdiff", "revdiff config", "revdiff themes", "revdiff keybindings", "how to configure revdiff", "what themes does revdiff have".
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response", "annotate codex output".
Use when adding or updating EasyPostman Swing/TestNG UI tests that may run in headless CI or no-display Linux environments.
MASTER Vue.js application testing with strict enforcement of verification protocols. Systematically test functionality with Playwright, validate bug fixes, verify features work, and enforce zero-tolerance policies for false success claims. MANDATORY testing with visual evidence before any deployment or functionality claims.