NeoHaskell

Run a standing multi-phase development program with explicit ownership, independent verification and durable local bookkeeping.

The English summary is being prepared. Showing the original description.

Apply when two or more fixes that share one premise have failed the same gate. Write the premise down and test it directly before you write another fix that assumes it.

The English summary is being prepared. Showing the original description.

Apply when wiring validation, error handling, or framework adapters. Concentrate guards at their owning boundaries, including public framework APIs. Trust established invariants, retain necessary runtime checks, and keep core logic in pure functions.

The English summary is being prepared. Showing the original description.

Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.

The English summary is being prepared. Showing the original description.

Apply when designing, implementing or reviewing NeoHaskell framework data structures, service flows, concurrency, storage, codecs or generated APIs. Design toward a hypothetical 50,000 requests per second with explicit cost and workload assumptions; distinguish design reasoning from measured performance.

The English summary is being prepared. Showing the original description.

Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. For NeoHaskell internals, encode the rule through a Haskell type, the API that owns the invariant, existing Generic/Template Haskell derivation, a lint, metadata flag, runtime check, or script instead of more text.

The English summary is being prepared. Showing the original description.

Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 competing prototypes and compare side by side before committing.

The English summary is being prepared. Showing the original description.

Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.

The English summary is being prepared. Showing the original description.

Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.

The English summary is being prepared. Showing the original description.

Apply when debugging. Trace each symptom back to the first place the system went wrong and fix it there. A guard is a fix only when the state it handles is legitimate.

The English summary is being prepared. Showing the original description.

Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share. Get the data structures right so downstream code becomes obvious.

The English summary is being prepared. Showing the original description.

Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.

The English summary is being prepared. Showing the original description.

Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries. Converge to the same end state regardless of partial prior runs.

The English summary is being prepared. Showing the original description.

Apply when introducing a new internal API while old callers still exist. Migrate callers and delete the old API in the same wave instead of preserving compatibility layers.

The English summary is being prepared. Showing the original description.

Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem.

The English summary is being prepared. Showing the original description.

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.

The English summary is being prepared. Showing the original description.

Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files.

The English summary is being prepared. Showing the original description.

Apply when tempted to ask 'should I do X?' on reversible work.

The English summary is being prepared. Showing the original description.

Apply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don't preserve smooth intermediate states with throwaway compatibility code.

The English summary is being prepared. Showing the original description.

Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy or self-report. Compilation directly checks compilation and type-level claims; it does not prove runtime behavior.

The English summary is being prepared. Showing the original description.

Apply when integrating a new requirement into an existing design.

The English summary is being prepared. Showing the original description.

Apply when designing, implementing or reviewing NeoHaskell framework trust boundaries, authorization, secret handling, data isolation or resource access. Put security guarantees in owning APIs and safe defaults, grounded in reachable flows.

The English summary is being prepared. Showing the original description.

Apply when changing shared mutable state, worker coordination, or task lifetimes in NeoHaskell framework internals. Reuse the owning subsystem, separate genuinely independent state, and use existing concurrency primitives where synchronization is required.

The English summary is being prepared. Showing the original description.

Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.

The English summary is being prepared. Showing the original description.