Software Development AI Skills

After a code change (diff/fix/requirement change), decide what to regression-test: changed files → functions → features → cases traceability; outputs a ranked list. Not for: editing case files…

Implements a saved plan through to a tested, independently reviewed pull request, handing it to an agent in its own worktree when possible. Use this skill when the user asks to implement, execute, or…

Generate dev server lifecycle scripts (start/stop/status/ports) from detected project structure

Use gh CLI to view, triage, fix, link, create, or close GitHub Issues.

对 AutoResearch 目录或 ZIP 做只读质检；先审优化面是否仅调参、Baseline 是否合理、Reference 提升是否充分，再查 21 项实现、严格 Docker 路径、Harbor 接口与成对训练证据。输出方法介绍、完整跑分、专家退回说明及 TXT/Markdown/JSON 报告；不用于求解任务。

Zero-knowledge proofs and privacy patterns on Stellar. Covers Groth16 verification in smart contracts via BLS12-381 host functions (CAP-59), the BN254 + Poseidon host functions (CAP-74/75), and…

Apply when reviewing or writing code that processes untrusted input, constructs queries or commands, or handles user-supplied data. Covers SQL, LDAP, OS command injection, prototype pollution, and…

LightCraft is a native photo library and non-destructive raw developer — an open-source, clean-room reimplementation of Adobe Lightroom Classic — written in pure Rust (macOS app at…

Diagnose the cc-suite setup in the current project. Runs the full health check, explains every issue, and fixes what can be fixed automatically. Skill counterpart to /cc-suite:diagnose.

Rethink code using Corbin Crutchley's purpose-first cleanroom workflow when an implementation repeatedly struggles to pass review, needs frequent rewrites, or the user explicitly requests a fresh…

Geospatial routing data handling for depot and station coordinates, route node IDs, internal index mappings, great-circle distance matrices, and route-distance reconstruction. Use when optimization or…

AI-first design decomposition for any project. Given a design doc or topic, ground in the actual codebase, produce (or refine) a PLAN file with problem, approach, alternatives, constraints, and a task…

Optional modelling stage: regression, mixed effects, clustering, dimensionality reduction, forecasting. Only runs when the design supports it; every model carries diagnostics.

Use when building dynamic blocks or block-editor features - a render_callback, server-side rendered blocks via ServerSideRender, REST-backed block data, or register_rest_field for the editor.…

Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks.

Maps an unfamiliar repo before touching its code.

Submit compact RCSB PDB requests for core metadata, Search API queries, and FASTA downloads. Use when a user wants concise RCSB summaries; save raw JSON or FASTA only on request.

运行 ATB (Ascend Transformer Boost) CSV 测试。当用户需要执行 CSV 格式的 ATB 测试用例、 验证算子正确性、或运行任何ATB下的 CSV 测试文件时调用此技能。 需配合 CANN 环境和已编译的 ATB 测试框架使用。

Open markdown files in a cmux formatted viewer panel with live reload. Use when you need to display plans, documentation, or notes alongside the terminal with rich rendering (headings, code blocks,…

(alamops) Hard, respectful interrogation of the owner about a feature or code change before it's planned or built, so no load-bearing unknown reaches the plan. Grounds itself in the code (or an…

将 IUPAC 化学名称转换为 SMILES 字符串。完全使用 OPSIN API，支持聚合物智能解析。

System architecture design skill with pattern recognition, trade-off analysis, and documentation. Use when designing new features, evaluating architecture decisions, or planning system refactoring.

Use when conducting security assessments — OWASP Top 10 / API / LLM, CWE Top 25, CVSS scoring — auditing PHP/TYPO3, APIs, frontend, Terraform/K8s/Docker IaC, AWS cloud, AI agent configs, or scanning…

Pre-flight cost estimate for a planned /article run. Use BEFORE /article or when user asks "how much will this cost?" / "what's the estimate?". Outputs USD breakdown by category + 80% confidence band…

给业务人员推荐历史营销模型——解析自然语言需求(客群+用途)→读模型台账语义筛选排序→展示详情→询问是否评估→(可选)委托 classification-model-evaluation 产三档评估。当用户说"推荐历史模型""找可复用模型""有没有现成模型""历史模型""模型推荐"时使用。

Guidelines for writing pseudocode for functions and algorithms. Use this skill whenever the user asks to write pseudocode, sketch out an algorithm, or describe the logic of a function at a high level.…

Nature-style materials science manuscript reviewer skill for testing materials design, synthesis, processing, structure-property, mechanism, stability, scalability, computational prediction and…

Teaches CI/CD from first principles to a non-developer, then scaffolds a working test + deploy pipeline. Handles the common hosts (GitHub Actions, GitLab CI, CircleCI, Travis, Jenkins) and common…

Use this skill when the user asks to "make an icon", "generate an icon", "create a scientific icon", "make a transparent icon", "make a minimal icon", "icon for a figure", "icon for a paper",…

JSpecify nullness annotations for Java APIs and tooling. Use when adopting or migrating JSpecify annotations, designing null-safe Java signatures, fixing generic bounds and type-use placement, or…

5 legendary engineers debate your problem in parallel using the most powerful AI model available. Spawns sub-agents as John Carmack, Rich Hickey, Sandi Metz, Linus Torvalds, and Kent Beck — each…

List, create, close, comment on, and triage GitHub issues and pull requests via the gh CLI.

为 GitHub 项目生成作品集级 README.md。适用于「帮我写 README」「生成 README」「优化 README」「README 最佳实践」「项目首页」「开源说明」「README 信息图」「README 封面」「用 Codex Image Gen / gpt-image-2 生成 README 图片」等请求。输出包括克制的 README…

用于审查已完成的工作、重大功能或合并前的变更，核对需求并按严重程度识别风险。未经审查不得合并。

Required dispatch procedure for running a subagent on Fable 5.1: positive harness detection, the Claude Code CLI shim for other harnesses, the fallback ladder, the result-parsing contract, the…

查询Moltbook（Agent社区）热门帖子信息。当用户想要查询Agent社区热帖、最新讨论、热门话题时使用此skill。

Stage 6 of the Software Factory - the fresh-eyes review after the overnight loop says "done". Reads ONLY the contract and the code changes (never the loop's chat or reasoning), re-runs every…

Power Platform Critic and Quality Reviewer (Razor). Use when: reviewing architecture, reviewing code, code review, accessibility audit, WCAG compliance check, UX review, ALM review, Dataverse schema…

Use when a repository needs deterministic pull-request checks for new accessibility, design-token, component-structure, responsive, and UI-state regressions with file-level evidence.

Turn a feature request, stakeholder request, idea, complaint, or vague design assignment into a clear UX problem frame with user outcome, evidence, constraints, assumptions, unknowns, and success…

Theme Bullframe CSS with token overrides, dark or system builds, and a short project stylesheet. Use when branding colours or fonts, picking a dark or prefers-color-scheme build, or adding custom.css…

Guidelines and instructions for Agent memory persistence store setups

Safely maintain the public accessibility-skills repository. Use when adding tracked-file hygiene scanners, proving whether reset or rebase work was lost, splitting mixed changes into focused commits,…

Creates and modifies evolving-scene browser presentations. Use when the user asks to "create a presentation", "build a talk", "add steps", "modify a presentation", "update/resync the scene kit", or…

Manage the risks of redesigns when users have built up exposure-based preference for the existing design. Use when planning a major redesign, evaluating user backlash to changes, deciding between…

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative…

Load scoped repository context, then search and navigate a hraness/wordcell Markdown vault with hybrid text retrieval, exact metadata, bounded links and typed relationships, backlinks, whole-vault…

Audit a web page for RGAA v4.1.2 Theme 6 – Links accessibility compliance. Checks that every link is explicit (its purpose can be understood from its text alone or from context) and that every link…

Use when writing PHP code - modern PHP 8 features, strict typing, enums, readonly, OOP patterns, PSR standards, security (file inclusion, SQL injection, XSS, CSRF, sessions, password hashing, file…

Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing,…

UI shell and component semantics. Use when building a product page (list, dashboard, settings, detail, agent-admin), or when the wrong template and Badge-Tag pairing is about to be coded.