Software Development AI Skills

Any bug, failing or flaky test, or surprise behavior? Load BEFORE you investigate or guess.

为产品想法取证，判断是否值得继续验证或投入；适用时用十维评分卡，脚本确定性算分。用户要评判想法、打分或判断机会值不值得做时调用。可独立运行；OPC 内服从既有审批和编排。

Use when code changes on the current branch need matching internal or developer documentation — "update our internal docs", "the architecture docs are stale after this change", "document what I just…

Simplifies recently changed or explicitly scoped code while preserving observable behavior, error semantics, side effects, ordering, and public contracts. Use for readability cleanup, dead-code…

OWASP Top 10 with code examples, SAST/DAST tools, dependency scanning, CSP headers, and input validation patterns. Use when hardening applications, reviewing security posture, or implementing…

Run the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models: baseline evaluate, RCA, Cosmos AnomalyGen / AMP synthetic defects, k-NN mining, retraining, and…

Externalize working state to a checkpoint file so long tasks survive context compaction, interruption, and handoff. Use at the start of any task expected to exceed ~30 minutes, touch many files, or…

Manage inbox email. Uses the inbox script and stores metadata (ids) to open or archive messages later.

Performs a structured security code review against OWASP ASVS 4.0.3 verification requirements and CWE Top 25. Auto-invoked on pull request reviews, when code touching authentication, authorization,…

Receive and verify Ada (ada.cx) AI customer service webhooks, delivered through Svix. Use when setting up an Ada webhook endpoint, getting the per-endpoint whsec_ signing secret, debugging svix-id /…

Use when advising on UAE criminal procedure under the Federal Penal Code and Code of Criminal Procedure, including arrest and detention rights, the role of the Public Prosecution, bail, court…

Build, review, debug, and launch CUDA- and GPU-accelerated HPC workflows. Use when working with `nvcc`, host-compiler compatibility, CUDA-aware MPI, rank-to-GPU mapping, `CUDA_VISIBLE_DEVICES`, Slurm…

拿到 offer 后到落地安顿。当用户输入 /euro-visa，或说"拿到 offer 了下一步"、 "签证怎么办"、"资金证明"、"Sperrkonto"、"保证金"、"行前准备"、"落地后做什么"、 "Anmeldung"、"BSN"、"能带家属吗"、"永居"、"入籍"时触发。 visa after offer、blocked account、arrival checklist。

Rules for commits, branches, diffs, and history when working in a git repository — checkpoint strategy, pre-commit diff review, message format, and the hard prohibitions on destructive operations.…

Conduct multi-round deep research on any GitHub Repo. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of GitHub. Produces…

Audit a .glb or .gltf and make it small, correct, and fast to load in a browser, with a measured before/after report. Use when a model is "too big" or "slow to load", when the user asks to "optimize…

Svelte template directives ({@attach}, {@html}, {@render}, {@const}, {@debug}). Use for DOM manipulation, third-party libs, tooltips, canvas, dynamic HTML. @attach replaces use: actions.

当开发GraphQL API时，分析查询策略，优化API性能，解决数据获取问题。验证GraphQL架构，设计查询模式，和最佳实践。

Use when creating, updating, reviewing, or publishing Arch User Repository (AUR) packages. Runs /release-aur plan first, reviews PKGBUILD/.SRCINFO/build/namcap evidence, and only recommends…

Base44 server-side code: backend functions (HTTP handlers in base44/functions/<name>/entry.ts on Cloudflare Workers) for Vite SPA apps, or TanStack Start server functions and server routes. Secrets,…

List all shared skills, agents, and rules in the brain network.

Revisit a past Agent Council decision with current codebase context. Re-runs the same question through the council and shows a side-by-side comparison of what changed. Use for living decisions.

Load to bind an overseer's mailbox to a private Slack channel, run or check the relay, or post an alert or a file to Slack.

Use when building or debugging web 3D scenes, product configurators or portfolios with Three.js, React Three Fiber or Spline; review assets, loading, controls, fallbacks and performance.

雅思写作批改教练。四维评分 + 句子级标注 + 改写对比 + 审题检查 + 历史追踪。 触发方式：/ielts-writing、「批改作文」「帮我看看这篇」「审题」「写作练习」

Reads the current Mac clipboard (pasteboard) contents to stdout or writes new text to the clipboard using pbcopy/pbpaste. Use when the user asks to copy, paste, read clipboard, write to clipboard,…

Persist this session's intent, extract change points, refresh the iteration timeline, and list optimization suggestions.

Use when designing, implementing, or reviewing platform-specific integrations in KMP projects, including source-set placement, hierarchical sharing, expect/actual usage, platform API access, and…

myfy web routing with FastAPI-like decorators. Use when working with WebModule, @route decorators, path parameters, query parameters, request bodies, AuthModule for authentication, RateLimitModule for…

Meta-validator for HARD-GATEs. Use when auditing whether a skill's mandatory constraints were actually followed during a workflow (not just claimed). Called by cook, team, and audit for discipline…

Step-by-step guides for upgrading Shopify Hydrogen between versions — breaking changes, code diffs, and migration steps for each release.

Getting listed on developer tool directories, awesome lists, and curated resources. Covers which directories matter for developer tools, submission best practices, contributing to awesome-lists on…

Use when all territories report completion after the hit — handles integration, verification, consigliere final review, cleanup, and ledger updates to produce clean production-ready code

Go interface design patterns: implicit interfaces, consumer-side definition, interface compliance verification, composition, the accept-interfaces-return-structs principle, and common pitfalls. Use…

Convert an existing program / system into an n8n workflow that preserves enterprise governance — login, audit, version control, handover, cross-system orchestration. Use when the user asks to "把這個程式 /…

RouterOS v7 domain knowledge for AI agents. Use when: working with MikroTik RouterOS, writing RouterOS CLI/script commands, calling RouterOS REST API, debugging why a Linux command fails on RouterOS,…

This skill should be used when building agent evaluation systems: deterministic checks, regression suites, multi-dimensional rubrics, quality gates, production monitoring, baseline comparison, and…

Guidance and local audit tools for Python workflows that directly use GeoPandas GeoSeries, GeoDataFrame, spatial operations, or vector-data I/O.

Implements instrumental variables and 2SLS in R or Python with first-stage diagnostics, weak instrument detection, and overidentification tests. Use when user mentions IV, instrument, 2SLS,…

Analyze CIF files for Wyckoff position multiplicities and approximate fractional coordinates. Use when a task requires parsing crystallographic CIF files, determining Wyckoff positions via symmetry…

Testany Git 导入：把 Git 仓库里的测试脚本批量注册成 Testany platform cases，并持续同步、切 commit、演化 binding、配 webhook

Create PydanticAI agents with type-safe dependencies, structured outputs, and proper configuration. Use when building AI agents, creating chat systems, or integrating LLMs with Pydantic validation.

Use when you need to assess the quality of a gstack-game skill, decide which skill to improve next, or refactor a skill for progressive disclosure. Run on a single skill or scan all skills. Not for…

Audits GPIO assignments in ESP32-family firmware against the verified pin facts of the actual target chip and board, flagging flash/PSRAM pins, strapping pins, input-only pins, USB-Serial-JTAG and…

FeatBit official documentation real-time Q&A assistant. Activate when user mentions "FeatBit", "feature flag", "feature toggle", or asks about FeatBit SDK integration, deployment, or configuration.…

Deploy compatible server, static-web, worker, scheduled-job, or reviewed remote-desktop workloads from GitHub or local source to Sealos Cloud, then run the default Runtime Truth Pass against the…

Optimizing frontend (re-render, memoization, lazy loading) and backend (N+1, indexing, caching, async) performance, plus continuous auto-tuning loops for GC/threadpool/cache/worker settings.

Turn a refined requirements document into a structured implementation PLAN.md a fresh session can execute. Planning only — decides the "how", not the "what". Invoke manually only.

Use when writing or adding tests for Spring Boot code at a service's edges: HTTP clients that call other services (WireMock: 4xx and 5xx responses, timeouts, retries), Kafka or RabbitMQ listeners…

View and manage the runtime changelog for observability

Parallelize large-scale geospatial operations on a single fat node — tile-edge dissolve, polygon elimination, polygonize, spatial joins, reprojection, simplification — at national/continental scale…