NeoHaskell

Audit worktrees and their uncommitted work, merge state and project history before proposing authorized cleanup.

中文简介正在准备中。当前显示原文说明。

Cut AI tells from any writing.

中文简介正在准备中。当前显示原文说明。

Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.

中文简介正在准备中。当前显示原文说明。

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available evidence sources and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.

中文简介正在准备中。当前显示原文说明。

Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target.

中文简介正在准备中。当前显示原文说明。

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。

Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.

中文简介正在准备中。当前显示原文说明。

Select provider-aware models for workflow roles, or update the repository's central role-to-model-and-effort mapping.

中文简介正在准备中。当前显示原文说明。

Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.

中文简介正在准备中。当前显示原文说明。

Create factual diagrams, comparisons and visual explanations using the external drawio-skill dependency. Use for /visualize, an editable diagram request, or a caller that needs a visual explanation.

中文简介正在准备中。当前显示原文说明。

Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED, or INCONCLUSIVE.

中文简介正在准备中。当前显示原文说明。

Check authored skills for required metadata, duplicate names, missing local resources and broken cross-skill links without imposing a fixed skill inventory or agent-tool configuration.

中文简介正在准备中。当前显示原文说明。

Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.

中文简介正在准备中。当前显示原文说明。

Reconcile and safely complete NeoHaskell's ordinary generated release preparation PRs when explicitly asked to run a release sweep.

中文简介正在准备中。当前显示原文说明。

Apply when designing or reviewing Haskell types and signatures in NeoHaskell internals. Use algebraic data types, semantic newtypes, boundary parsing, exhaustive pattern matching, existing derivation, and total functions to express useful guarantees.

中文简介正在准备中。当前显示原文说明。

Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.

中文简介正在准备中。当前显示原文说明。

Run matched baseline and treatment measurements for NeoHaskell framework flows, compiled test suites and consumer compilation, retaining workload counts, inputs and raw samples.

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。

Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions. Use for /figure-it-out or 'figure it out'.

中文简介正在准备中。当前显示原文说明。

Select and run the maintained event-store regression fixtures against known-good and controlled-bad behavior when changing append preconditions, payloads, conflict refetch or concurrent stream creation.

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。

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。

Run NeoHaskell doctest examples, all local Cabal test targets, or the maintained Hurl testbed when a framework change needs runtime verification.

中文简介正在准备中。当前显示原文说明。

Prepare NeoHaskell release notes and breaking-change migrations, validate release fragments and generated release bookkeeping, and investigate or recover a failed release. Use before final PR review and when explicitly preparing or repairing a release.

中文简介正在准备中。当前显示原文说明。