All Skills

Reviews code, diffs, or PRs for correctness, regressions, security, architecture, maintainability, and test gaps.

Reviews cohesion, naming, responsibility, complexity, and maintainability. Do not use as a default companion to every code change.

Updates technical docs for verified behavior, public contracts, commands, configuration, and operations.

Stores verified cross-session facts, decisions, preferences, and open questions without secrets, speculation, or monitoring.

General implementation only when no narrower task or ecosystem skill fits. Do not combine with a clear specialist skill.

Selects scoped architecture, backend, frontend, security, data, DevOps, QA, docs, performance, or product roles.

Reviews authorization, tenant isolation, roles, ownership, row access, admin boundaries, sharing, and privilege escalation.

Updates AGENTS.md after a repeated verified failure. Do not use for one-off preferences or speculative rules.

Audits external agent, skill, plugin, hook, or marketplace packs for licenses, installers, secrets, runtime state, and safe adaptation.

Produces durable, structured documentation in codebases with sparse docs — readable by humans and agents alike. Two invocation modes — `survey` proposes a doc plan; `draft` writes one specific doc end-to-end with a factcheck-then-persona review gate. Triggered by phrases like "doxcavate this repo", "doxcavate the X", "doxcavate `runbook-deploy`", "what should be documented?", "document this code", "write a how-it-works for X", or any request to inventory or write project documentation.

针对明确问题查阅高可信一手来源，并将带逐项引用的结论保存为仓库内单个 Markdown 调研文件。用于用户要求调研技术主题、核实文档、API、规范或源码事实，或希望把资料阅读工作委托给后台 agent；不用于完整代码库架构调研、无需落盘的简短事实回答或代码评审。

当用户已有确认过的行为规格（理想来自 write-spec），要在编码前把技术问题问清楚、比较方案、锁定技术决策——技术选型、架构、数据模型、接口契约、错误处理、测试策略——并沉淀成可 review 的技术设计依据时使用。不要用于：行为/需求还没钉死（先 write-spec）、想法还模糊（先 refine-idea）、任务拆解或实现计划（那是下游 split-task）、调试或代码评审。

当要在开始一段开发、或并行多个任务前，建立隔离的 git 工作区（worktree）以免污染当前工作区时使用——如"开个 worktree、隔离工作区、并行任务各自隔离"。通常由 execute-task 在执行前调用。先锁定 expected base，再选择能保证该基线的创建方式，并在创建后验证 HEAD。不要用于：不需要隔离的小改动、收尾/合并/清理（那是 finish-branch）、非 git 仓库。

用于编写和编辑高质量 Skill 的参考框架：通过调用设计、信息层级、引导词与剪枝提高执行过程的可预测性。

Use for writing, reviewing, debugging, or testing Python analysis of Bayesian inference results with ArviZ, including 1.x DataTree groups, legacy InferenceData inputs, xarray dimensions and coordinates, conversion, summaries, R-hat/ESS/MCSE diagnostics, posterior predictive checks, PSIS-LOO, Pareto-k, and model comparison. Trigger on chain/draw shape errors, mislabeled groups, flattened samples, missing log likelihood, or misleading diagnostic claims. Do not use to construct or sample PyMC, NumPyro, or Bambi models, for generic plotting, or for deterministic statistics without Bayesian draws.

Use for writing, reviewing, debugging, testing, or optimizing Python NumPy ndarray code. Trigger on array construction, shape/axis reasoning, dtypes and casting, broadcasting, indexing, copies/views, ufuncs, reductions, vectorization, random Generator, linear algebra, FFT, masked/structured arrays, memory layout, or NumPy interoperability. Do not use for pandas/Polars table semantics, JAX/CuPy-only arrays, symbolic SymPy, or pure Python sequences without a NumPy boundary.

Build, review, debug, or test declarative statistical visualizations in Python with Altair and Vega-Lite, including chart marks, typed encodings, transforms, parameters, layers, facets, and specification export.

Build, verify, and debug interactive Python visualizations with Plotly, including Plotly Express, graph_objects, subplots, facets, hover/customdata, axes, legends, FigureWidget events, and HTML/image export.

Provides guidance for using python-xxhash to implement fast non-cryptographic hashing, including algorithm selection, byte encoding, streaming updates, digest representation, and collision-aware identity for checksums, bucketing, and sampling.

Creates executable Polars dataframe contracts using Pandera's Polars backend for runtime validation of schemas, columns, and checks.

Write, review, debug, migrate, or test Python code using Pydantic v2 with explicit boundaries, validation, and serialization contracts.

---

---

Use for creating, reviewing, debugging, or testing GitHub Copilot agent hooks in Visual Studio Code, including .github/hooks JSON, lifecycle events, Python handlers, permissions, and structured stdin/stdout. Do not use for advisory instructions, one-off commands, CI workflows, or shell profile hooks.

Write, review, debug, or test Python datetime, date, timedelta, timezone, and zoneinfo code, especially UTC conversion, DST gaps and folds, recurring local schedules, parsing, and interval boundaries.

Use for creating, reviewing, debugging, or packaging portable GitHub Copilot Agent Skills with SKILL.md, precise triggers, progressive disclosure, scripts, examples, and resources. Do not use for always-on repository rules, a single prompt command, custom agent personas, or Skill Foundry maintenance.

Choose between scikit-learn for predictive workflows and statsmodels for inferential modeling, with guidance on preprocessing, leakage prevention, validation, and result handoff.

Review code with specialized security, quality, and silent-failure agents.

Go backend conventions, patterns, and test infrastructure. Use when working with Go files, go.mod projects, Go modules, Go CLI, go build, go test, BubbleTea TUI apps, Lip Gloss styling, Charm libraries, goroutines, channels, interfaces, or Go dependency management.

Visually verify UI changes with Playwright screenshots and Pencil layout checks before proceeding. Use when a change touches frontend/UI files and needs visual confirmation, not just passing tests.

Resolve cenci's neutral project configuration and shared guidance consistently.

Decide which work is safe to delegate to worker agents. Use before delegating tasks that may require user interaction, approval, authentication, external writes, or shared-state mutation.

Designs collaborative AI agent teams using CrewAI, covering agent roles, task definitions, crew orchestration, process types, memory, and flows.

Firebase gives you a complete backend in minutes - auth, database, storage, functions, hosting. But the ease of setup hides real complexity. Security rules are your last line of defense, and they're often wrong. Firestore queries are limited, and you learn this after you've designed your data model. This skill covers Firebase Authentication, Firestore, Realtime Database, Cloud Functions, Cloud Storage, and Firebase Hosting. Key insight: Firebase is optimized for read-heavy, denormalized data. I

Expert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern. Used in production at LinkedIn, Uber, and 400+ companies. This is LangChain's recommended approach for building agents. Use when: langgraph, langchain agent, stateful agent, agent graph, react agent.

Bash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems.