416 skills · sorted by relevance
Audit a repository or broad subsystem for security, correctness, and maintenance risks. Trace how inputs reach affected behavior, verify suspected defects, and report confirmed findings with severity, triggers, impact, and practical remedies.
Review existing R scripts for code quality, reproducibility, domain correctness, and coding standards. Produce a separate report for each script, plus a severity-based summary of findings and the three most critical issues, without changing source files.
Use ONLY when the user asks to check, validate, review or audit analysis code for scientific correctness, or when you are the reviewer agent running its checks. Never run it unprompted as part of ordinary analysis work. Covers physics, earth/geo, biology, chemistry, social science and bioprocess/fermentation. Runs a deterministic domain-correctness gate that catches code which runs but is scientifically wrong (unit/dimension mismatch, Euclidean distance on lat/lon without a CRS, 0-based/1-based coordinate and strand errors, impossible SMILES valence, uncorrected multiple comparisons, averaging a categorical code, unconstrained kinetic-parameter fits, kLa computed from raw DO instead of the driving force, arithmetic mean of raw CFU counts, ANOVA/Tukey with no assumption check, a curvature DOE design fit with a first-order model, an ML model fit across process scales with no correction). Surfaces structured findings; never claims the code is correct.
The English summary is being prepared. Showing the original description.
Comprehensive adversarial audit of a theory, proof, math/econ paper, codebase, or set of claims — decompose into components, fan out independent skeptics that must return CONCRETE defects, adjudicate every finding with a separate judge, fix all confirmed defects, then re-verify. Use when correctness must be bulletproof and single-pass or round-by-round review is too slow and too shallow. Invoke for "audit this rigorously", "find ALL the bugs/gaps", "make this rock solid", "converge faster on correctness".
The English summary is being prepared. Showing the original description.
Audit code for correctness and rigor — logic errors, silent error swallowing, wishful thinking, and unjustified fallbacks. This is not a style review; it's a logic review. Use when you want a focused correctness audit separate from the full code-police pass.
The English summary is being prepared. Showing the original description.
Re-ingest-correctness SOP for production RAG. Activate when a calling agent builds, reviews, or debugs an ingestion pipeline that runs more than once over a changing corpus — scheduled re-index, incremental updates, CI re-ingest, or a "retrieval has duplicates / shows deleted docs" bug. Encodes the rule — **ingestion must be idempotent: a document's content hash decides insert/update/skip, so re-running over unchanged docs is a no-op** — plus the docstore + doc-hash upsert machinery (LlamaIndex `IngestionPipeline` + `DocstoreStrategy`), the delete-propagation problem, and cross-framework equivalents (LangChain `index()` + `RecordManager`, manual hash table). ENHANCE overlay over [[llamaindex]]: the IngestionPipeline exists in the base skill but the re-ingest-correctness contract is not surfaced.
The English summary is being prepared. Showing the original description.
Verify code correctness statically against specifications using type checking, contract verification, and formal methods. Use when: (1) Verifying type safety and null safety in Python, Java, or C/C++ code, (2) Checking design-by-contract specifications (preconditions, postconditions, invariants), (3) Validating code against formal specifications, (4) Ensuring code quality and correctness before runtime, (5) Finding potential bugs through static analysis. Supports Python (mypy, contracts), Java (javac, JML), and provides verification scripts and contract specification guidelines.
The English summary is being prepared. Showing the original description.
Generate executable code together with formal proofs certifying safety and correctness properties in Isabelle/HOL or Coq. Use when building verified software, safety-critical systems, or when formal guarantees are required. Produces code with accompanying proofs for memory safety, bounds checking, functional correctness, invariant preservation, and termination. Supports extraction to OCaml/Haskell/SML and integration with existing codebases.
The English summary is being prepared. Showing the original description.
Audit code for correctness and rigor — logic errors, silent error swallowing, wishful thinking, and unjustified fallbacks. This is not a style review; it's a logic review. Use when you want a focused correctness audit separate from the full code-police pass.
The English summary is being prepared. Showing the original description.
音乐制作 / 混音 (音乐制作 / 混音 (Music Production & Mixing) — 录音棚与卧室工作室里把一首歌从编曲/录音/编程做到混音/母带成品的工程+艺术认知操作系统，面向制作人(producer)、混音师(mixing engineer)、母带工程师(mastering engineer)、beatmaker、唱作人/bedroom producer，以及想入行/服务这行(录音棚、plugin 厂商、sample 公司)的视角。覆盖: (a) 第一性张力 — **服务歌曲/情绪 (serve the song / emotion-first: 技术只为打动人，'if it sounds good it is good'，用耳朵不用眼睛) ⇄ 技术正确/工程纪律 (technical correctness: gain staging 增益结构、headroom 余量、相位 phase、监听校准、LUFS 响度规范)**; **黄金耳朵/直觉混音 (mix by ears, reference-driven, 不看分析仪) ⇄ 看表/分析仪/规则 (mix by metrics: EQ 曲线、频谱仪 spectrum analyzer、相关计 correlation meter)**; **少即是多/减法混音 (subtractive, 'less is more', 录好源头 = 混音成功一半) ⇄ 重度处理/'we'll fix it in the mix' (heavy processing, 后期补救)**; **In-the-box 全数字 (ITB: DAW + 插件，召回方便，bedroom 可达专业) ⇄ 模拟硬件/outboard (analog console + 硬件，'mojo'/谐波染色 vs 召回噩梦)**; **人性化/groove/不完美 (humanize, push/pull, 'the feel') ⇄ 量化/网格/修音 (quantize to grid, pitch-correct, 'in the pocket' 靠编辑)**; (b) 核心工作流 / pipeline (最标准、最易蒸高质量+CLI 化) — 编曲制作 arrangement/production → 录音/编程 tracking/programming → 编辑 editing (comping 选段/quantize/pitch-correct/time-align) → 混音 mixing (gain staging → balance 平衡 → EQ → compression → 空间 reverb/delay → 自动化 automation → 总线/母线处理 bus/mix-bus) → 母带 mastering (响度/EQ/限制 limiting/dither/排序+间隔) → 交付 delivery (DDP/streaming spec/stems); (c) 工具栈 — DAW (Pro Tools 录音棚标准/Ableton Live 电子+现场/Logic Pro Mac 性价比/FL Studio beatmaker/Cubase/Studio One/Reaper); 插件 (EQ: FabFilter Pro-Q/SSL/API; 压缩: 1176/LA-2A/SSL bus comp 及其复刻 Waves/UAD/Plugin Alliance; 混响: Valhalla/Lexicon/Bricasti; 调音: Auto-Tune/Melodyne; 限制器 limiter: Pro-L 2/Ozone); 硬件 (监听音箱 monitors: Yamaha NS-10/Genelec; 声学处理 acoustic treatment; 转换器 converters: Apollo/RME; 话筒 mics: U47/SM7B/57); 采样/音色 (Splice/sample packs/Kontakt/Serum 合成器); (d) 知识正典 — Mixing Secrets for the Small Studio (Mike Senior)、The Mixing Engineer's Handbook / Recording Engineer's Handbook (Bobby Owsinski)、Zen and the Art of Mixing (Mixerman)、The Art of Mixing (David Gibson 可视化)、Modern Recording Techniques、Sound on Sound 杂志、Mix With The Masters 大师课、Pensado's Place; (e) figures/流派 — 混音大师 (Chris Lord-Alge CLA 摇滚/Andrew Scheps 'Stadium' 3-bus/Tony Maserati/Manny Marroquin/Serban Ghenea 流行隐形混音/Michael Brauer multing); 制作人 (Rick Rubin 减法/氛围、Quincy Jones、Dr. Dre 完美主义、Max Martin 流行结构、Jack Antonoff、Finneas bedroom→Grammy、Metro Boomin/trap、Timbaland、Pharrell); 母带 (Bob Katz K-system/响度战争批判、Bob Ludwig、Greg Calbi); 教育者 (Mike Senior、Pensado、Warren Huart Produce Like A Pro、Dan Worrall 技术深挖); (f) 行业话术/黑话 — gain staging/headroom/LUFS/true peak/comping/bouncing/printing/stems/DI/reamp/sidechain/parallel compression 并行压缩/mid-side/bus/aux/send-return/dry-wet/transient/sibilance/de-ess/pumping/mud 浑浊/harsh 刺耳/boxy/muddy/in the pocket/the pocket/quantize/swing/groove/vibe/mojo/reference track/A/B/recall/print/glue 胶水; (g) 争议/批判 — 响度战争 loudness war (Bob Katz/Loudness Penalty/streaming 归一化 LUFS 终结了吗)、修音/Auto-Tune 之争 (artistic vs cheating)、ITB vs 模拟玄学 (硬件 'warmth' 是否安慰剂、null test 盲测)、preset/AI 混音 (iZotope/LANDR/sample-based 是否毁了 craft)、bedroom producer 民主化 vs 录音棚消亡、'loudness'/over-compression、plugin 复刻 vs 真硬件、Spotify normalization 对母带的影响、过度依赖 reference/抄袭; (h) 创意 vs 技术张力是本行业 deep tacit 知识的核心 — 大量隐性 '听感' 知识难以言传，靠 reference/学徒/千小时积累。不含: 现场扩声 live sound/PA、音乐理论/作曲 composition (虽相关但聚焦录音棚后期制作)、配乐/film scoring (虽相关但聚焦歌曲制作)、纯硬件电子工程/合成器 DIY、音乐商业/版权/发行 (虽相关但聚焦制作技艺本身)。) Master OS — automated mastery of 音乐制作 / 混音 (Music Production & Mixing) — 录音棚与卧室工作室里把一首歌从编曲/录音/编程做到混音/母带成品的工程+艺术认知操作系统，面向制作人(producer)、混音师(mixing engineer)、母带工程师(mastering engineer)、beatmaker、唱作人/bedroom producer，以及想入行/服务这行(录音棚、plugin 厂商、sample 公司)的视角。覆盖: (a) 第一性张力 — **服务歌曲/情绪 (serve the song / emotion-first: 技术只为打动人，'if it sounds good it is good'，用耳朵不用眼睛) ⇄ 技术正确/工程纪律 (technical correctness: gain staging 增益结构、headroom 余量、相位 phase、监听校准、LUFS 响度规范)**; **黄金耳朵/直觉混音 (mix by ears, reference-driven, 不看分析仪) ⇄ 看表/分析仪/规则 (mix by metrics: EQ 曲线、频谱仪 spectrum analyzer、相关计 correlation meter)**; **少即是多/减法混音 (subtractive, 'less is more', 录好源头 = 混音成功一半) ⇄ 重度处理/'we'll fix it i
The English summary is being prepared. Showing the original description.
Use when reviewing, debugging, or improving frontend code in this repo (website/ HTML, CSS, JS, service workers, PWA assets) or when asked to "review frontend", "revisa el html/css", "review JS", or "audita el frontend". Reviews for correctness, browser compatibility, accessibility, performance, security (XSS), responsive behavior, and PWA/service-worker correctness, and ends with a "what a user/reviewer would catch" pass.
The English summary is being prepared. Showing the original description.
Audit code for correctness and rigor — logic errors, silent error swallowing, wishful thinking, and unjustified fallbacks. This is not a style review; it's a logic review. Use when you want a focused correctness audit separate from the full code-police pass.
The English summary is being prepared. Showing the original description.
Unity New Input System correctness patterns. Catches common mistakes with action reading (triggered vs IsPressed vs WasPressedThisFrame), action map switching, rebinding persistence, InputValue lifetime, PassThrough vs Value, local multiplayer device assignment, and control scheme auto-switching. PATTERN format: WHEN/WRONG/RIGHT/GOTCHA. Based on Unity 6.3 LTS.
The English summary is being prepared. Showing the original description.
Audit code for correctness and rigor — logic errors, silent error swallowing, wishful thinking, and unjustified fallbacks. This is not a style review; it's a logic review. Use when you want a focused correctness audit separate from the full code-police pass.
The English summary is being prepared. Showing the original description.
Quantitative agent evaluation using 4-metric framework (correctness/step_ratio/tool_call_ratio/latency_ratio) with ideal trajectory annotation and capability-categorical taxonomy. Use when measuring agent efficiency, comparing agent variants, or gating new agents through correctness→efficiency phases. Complements harness-eval (SE benchmarks) and evaluator-optimizer (qualitative rubric).
The English summary is being prepared. Showing the original description.
Verifies bug fixes are correct and complete by tracing callers, checking imports/exports, validating path resolution, and confirming no regressions. Does the code work? Use when reviewing code changes for functional correctness.
The English summary is being prepared. Showing the original description.
コード品質の最終確認。Skill: code-review (built-in) で correctness bug を検出 → main agent が findings を修正 → lint/ty 静的解析 → 条件付きで security-reviewer / critic を spawn (security 関連変更 or plan/requirements.md がある時のみ)。「品質チェックして」「品質ゲート通して」「レビューして」「コードを確認して」「PR 出す前にチェック」「セキュリティ大丈夫？」「コード見て」で発動。
The English summary is being prepared. Showing the original description.
Investigate performance bottlenecks in REA analysis workflows and improve caching, queries, or shared processing. Compare completed tasks before and after changes while preserving correct results, examined coverage, and access to supporting evidence.
Audit REA’s automated checks and test suites to find missed failures, outdated test data, and unnecessary work. Use reproducible experiments and timing measurements to assess fixes or efficiency changes while preserving checks that catch real defects.
Organize a task into parallel work streams with clear dependencies, separate places for changes, and explicit checks. Batch independent reads and tests, coordinate concurrent work, and report completed or blocked tasks with verification results.
Find bottlenecks in large data transfers, imports, transformations, and historical data catch-up. Benchmark alternative processing methods, turn the fastest correct approach into a repeatable workflow, and verify file counts, row counts, and timestamps after execution.
Display a text scoreboard of published Ponytail 5 benchmark results, comparing code volume, generated text tokens, cost, time, and check results against an agent without the skill. The figures describe benchmark averages, not savings in the current project.
Check project dependency versions and consult the relevant official documentation before writing framework-specific code. Produce implementations with source links, identify deprecated APIs, and flag unverified approaches or conflicts between documentation and existing project patterns.
Challenge important design and implementation decisions with a separate reviewer that does not inherit the working session's context. Identify hidden assumptions and failure cases, then assess each finding against the artifact and its requirements.