Capture repeatable failing and passing evidence for NeoHaskell runtime regressions or compiler acceptance and expected rejection, with distinct checks for assertion failures and diagnostics.
中文简介正在准备中。当前显示原文说明。
实测评分 未实测
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Choose the boundary with Verify This. Use the TDD workflow for a focused runtime regression. Use real positive and negative consumers for a compiler or generated-API contract.
For Hspec, run python3 .agents/skills/regression-evidence/scripts/evidence.py runtime --repo <root> --input <affected-source> --test <exact-example> --expect fail --failure <independent-assertion-text> -- <test-command>. Repeat with --expect pass after the fix. The command must run the affected implementation. Expected failure needs one matching assertion failure, a nonempty selection and no setup or compiler failure.
For compiler contracts, run python3 .agents/skills/regression-evidence/scripts/evidence.py compiler --repo <root> --positive <accept.hs> --negative <reject.hs> --diagnostic <expected-regex> -- <ghc-flags>. The helper first requires a successful positive compilation, then a failure in the negative fixture with the expected diagnostic. Add relevant framework sources, generated declarations and build configuration through repeated --input arguments. Compiler rejection proves that compiler contract, not runtime behavior.
Runtime claims require demanded values, executed Tasks or decisions, and the promised observable result. Select independent expectations and meaningful properties. A copied implementation, assertion on a fixture alone, setup failure or arbitrary compiler exit is insufficient evidence.
The helper retains argument arrays, selected source snapshots, hashes, logs and observed outcomes under .agents-state/regression-evidence/. It rejects changes to the selected inputs during execution. This binds the captured run to those inputs. It does not establish complete dependency coverage or authenticate a hand-edited receipt. State the tested revision, dirty state, inputs and limitations in the result.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.
中文简介正在准备中。当前显示原文说明。
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.
中文简介正在准备中。当前显示原文说明。
Inspect or supervise a PR or stack through review and CI to merge-ready, using current GitHub evidence and the requested mode.
中文简介正在准备中。当前显示原文说明。
Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you benchmark or report a measured speedup or regression, including complete framework flows and compilation of projects that consume the framework.
中文简介正在准备中。当前显示原文说明。
Restate the last message in plain human language, with no jargon.
中文简介正在准备中。当前显示原文说明。
Build or adapt a local harness to drive, inspect, and profile an interactive CLI or TUI without external services. Use for CLI UX checks, startup regressions, memory leaks, hangs, prompt flows, or terminal demos.
中文简介正在准备中。当前显示原文说明。