数据处理
数据转换、清洗与 ETL
prompt-creator
Melvynx
Expert prompt engineering for creating effective prompts for Claude, GPT, and other LLMs. Use when writing system prompts, user prompts, few-shot examples, or optimizing existing prompts for better performance.
better-stimulus
obie
Apply Better Stimulus best practices for writing maintainable, reusable StimulusJS controllers following SOLID principles
prompt-enhancer
sammcj
Knowledge for transforming poor or overly simple user prompts with expert-level framing. Triggers include: user explicitly asking to improve/refine/rewrite their prompt or user requesting help framing a request for another AI system.
experiment-design
lingzhi227
Design experiment plans with progressive stages — initial implementation, baseline tuning, creative research, and ablation studies. Plan baselines, datasets, hyperparameter sweeps, and evaluation metrics. Use when planning experiments for a research paper.
experiment-code
lingzhi227
Write ML experiment code with iterative improvement. Generate training/evaluation pipelines, debug errors, and optimize results through code reflection. Use when implementing experiments for a research paper.
figure-generation
lingzhi227
Generate publication-quality scientific figures using matplotlib/seaborn with a three-phase pipeline (query expansion, code generation with execution, VLM visual feedback). Handles bar charts, line plots, heatmaps, training curves, ablation plots, and more. Use when the user needs figures, plots, or visualizations for a paper.
self-review
lingzhi227
Automatically review an academic paper using the NeurIPS review form with three reviewer personas, ensemble scoring, and reflection refinement. Extracts text from PDF, runs structured review, and outputs actionable feedback. Use when the user wants to review a paper before submission or get feedback on a draft.
data-analysis
lingzhi227
Generate statistical analysis code with 4-round review. Select appropriate statistical tests, interpret results, and produce analysis reports with p-values, effect sizes, and confidence intervals. Use when analyzing experimental data for a paper.
auth-implementation-patterns
HermeticOrmus
Master authentication and authorization patterns including JWT, OAuth2, session management, and RBAC to build secure, scalable access control systems. Use when implementing auth systems, securing APIs, or debugging security issues.
error-handling-patterns
HermeticOrmus
Master error handling patterns across languages including exceptions, Result types, error propagation, and graceful degradation to build resilient applications. Use when implementing error handling, designing APIs, or improving application reliability.
nft-standards
HermeticOrmus
Implement NFT standards (ERC-721, ERC-1155) with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT contracts, building NFT marketplaces, or implementing digital asset systems.
modern-javascript-patterns
HermeticOrmus
Master ES6+ features including async/await, destructuring, spread operators, arrow functions, promises, modules, iterators, generators, and functional programming patterns for writing clean, efficient JavaScript code. Use when refactoring legacy code, implementing modern patterns, or optimizing JavaScript applications.
alias-nested-modules
blockscout
Define module aliases at the top of the file instead of using fully qualified nested module names in function bodies. Improves code readability and maintainability while addressing Credo style warnings.
SpeedTree Subsystem Audit
matiaszanolli
"Audit the SpeedTree (.spt) TLV walker (crates/spt), the placeholder-billboard import, and the TREE→billboard/wind wiring for Oblivion / FO3 / FNV"
Tooling and Host-Contract Audit
matiaszanolli
"Audit of tooling and host-facing contracts — SDK (Studio snapshots, typed commands, StorageUtil compat), debug server + protocol + byro-dbg, debug-ui panels, launcher/boot-request/settings-io handoff, install detection, byro-detect, texture-upscale"
Scripting Runtime Audit (M30 / M47.0–M47.3)
matiaszanolli
"Deep audit of the M30/M47 scripting runtime — AST→ECS recognizer chain (decline-on-unmodeled), fragment/quest-stage dispatch, ECS event/timer/condition/trigger systems, cell-loader script attach, scene/package/cinematic playback, legacy ObScript quest execution (M47.3), extender-compat provider layer. Compiler frontends (.pex decompiler, .psc parser) are /audit-papyrus"
UI Audit: Scaleform (R4 + M48) and MenuXml (M48.4-M48.7)
matiaszanolli
"Deep audit of the game UI tracks — Scaleform/SWF (Ruffle host bridge, AVM1/AVM2 profiles, ABC adapter injection, archive navigator, offscreen wgpu readback, overlay upload, input routing) and the Oblivion/FO3/FNV MenuXml track (eval, layout, raster) with both HUD drivers"
Parser Discipline Audit (archives, materials, packfiles, sidecars)
matiaszanolli
"Parser-discipline audit of the non-NIF, non-ESM readers of untrusted game-archive input — BSA/BA2/CSG archives, BGSM/BGEM, Starfield CDB, Havok HKX packfiles, FaceGen sidecars, MenuXml parse side, Steam VDF/ACF"
Performance Audit
matiaszanolli
"Audit GPU/CPU performance — hot paths, allocations, draw batching, GPU memory pressure, SSBO sizing, telemetry"
Papyrus Frontend Audit (crates/pex + crates/papyrus)
matiaszanolli
"Deep audit of the Papyrus compiler frontends — .pex reader + 5-phase decompiler (Champollion port, crates/pex) and the .psc lexer/Pratt parser (crates/papyrus): untrusted-input bounds, decompiler soundness, depth caps"
Flow Tracer
matiaszanolli
"Trace a data flow through the engine — from ECS to GPU or from file to entity"
Tech-Debt Audit
matiaszanolli
"Audit accumulated technical debt — stale markers, dead code, duplication, magic numbers, stub impls, doc rot, oversized files"
Physics / PHYSAL Audit
matiaszanolli
"Deep audit of PHYSAL — the Havok→Rapier physics layer: collider classification, fixed-step determinism + explosion recovery, 4-phase ECS sync, ragdoll articulation, character/NPC kinematic controller, WATAL buoyancy sink"
Oblivion Compatibility Audit
matiaszanolli
"Per-game audit of Oblivion (TES4) compatibility — NIF v20.0.0.4 + the v10.x NetImmerse family, BSA v103, live ESM path"