Software Development AI Skills

Use for non-trivial implementation, debugging, refactoring or code review in any project: requirement drift, speculative complexity, agent-facing interfaces. Not workflow or role selection.

Generate documentation from code. Supports Markdown, RST, and JSDoc. Reads source code and produces clear, accurate, maintainable documentation in the format appropriate to the project. Use when the…

A strict, scientific debugging protocol (The "Iron Law"). No fixes allowed without root cause investigation.

OpenClaw skill for the agent-browser CLI (Rust-based with Node.js fallback) enabling AI-friendly web automation with snapshots, refs, and structured commands.

Organize Nim modules and multi-step workflows with explicit state ownership, cohesive boundaries, narrow exports, and structured orchestration. Use when refactoring a large Nim file, splitting logic…

Control Blender scenes, execute Python code, and import 3D assets from PolyHaven/Sketchfab/Hyper3D/Hunyuan3D via CLI. Use when user needs to manipulate Blender objects, generate AI 3D models, or apply…

Use when naming Lean declarations, organizing files, adding docstrings, or cleaning code so it matches Mathlib conventions and review expectations.

Delegates coding tasks to Codex CLI for prototyping, debugging, and code review. Use when: (1) Backend/logic implementation, (2) Algorithm design and optimization, (3) Bug analysis and debugging, (4)…

Detect Chrome extension framework/stack, find proper docs, implement features, and debug across service worker, content script, and popup contexts.

Install, onboard, and run multi-model coding orchestration or solo single-model mode. Invoke when the user says install Parable, install parable.sh, set up or onboard Parable, connect coding…

Virtual screening by molecular docking with AutoDock Vina — dock a set of small-molecule ligands (given as SMILES in a .smi/.csv/.txt file, or as an .sdf) into a receptor pocket, rank the hits by…

Primitive web crawling and scraping for one or more URLs. Use when a user shares links, asks to ingest or archive web content, or needs raw source artifacts normalized into reusable local records…

Comprehensive ABAP code quality checking using abaplint (automated static analysis) and Clean ABAP principles (manual code review). Use when users ask to check, lint, validate, review, or analyze ABAP…

Answer questions about the AI SDK and help build AI-powered features. Use when developers ask about Vercel AI SDK, generateText, streamText, ToolLoopAgent, useChat, providers, tools, structured…

Enforces a lean GitHub Actions Flutter CI where every gate maps to one named release-blocking contract — pinned runner + subosito/flutter-action@v2 toolchain, dart format --set-exit-if-changed,…

查询龙虎榜总览。接口：GET /api/v1/market/data/abnormal-trading-overview。所有请求必须设置 FTSHARE_API_KEY。

Search ClinicalTrials.gov with natural language queries. Find clinical trials, enrollment, and outcomes using Valyu semantic search.

Resolve conflicts and continue an interrupted git rebase, merge, or cherry-pick. Use for unmerged paths, conflict markers, or a paused history operation.

Use when building, deploying, or using PowerApps Component Framework (PCF) controls. Covers field controls and dataset controls, React virtual controls, control lifecycle, manifest configuration,…

Writes and executes JavaScript-based shell scripts using Google's zx library. Use when writing shell scripts, automation, build tools, file processing, CLI tools, deployment scripts, data pipelines,…

Analyzes the current CDD session for bugs and enhancement opportunities and files a single aggregate GitHub issue against Oscaner/skills via gh CLI. Open dedup matches become links in the issue body…

Android testing patterns — ViewModel unit tests with Turbine, Compose UI semantics, Hilt TestInstallIn fakes, coroutine test dispatchers, and release quality gates. Use when writing tests, setting up…

Tiles 3D volumes into overlapping patches for inference and averages overlapping regions to produce seamless predictions.

Look up WoW Combat, Damage Meter, Threat, Loss of Control, Combat Text, Combat Audio Alert, Secret Values, and Spectator APIs. Use when working with combat data, damage meters, threat, loss of…

Reviews implementation plans during iterative backpressured development. Use when a backpressured loop's Phase 1 reviewer subagent is judging whether a lightweight implementation plan's…

Launch a consulting engagement with a focused kickoff, discovery plan, stakeholder assessment, and working arrangements. Use after award or when resetting an engagement that lacks shared scope,…

Find unclaimed open source issues that match the user's skills and experience level. Searches for issues created by maintainers/org admins, checks contribution eligibility, and ranks by learning…

Source-first external repository research using durable, human-findable local clones. Use when the user asks about an open-source repo, GitHub/GitLab URL, library internals, framework behavior,…

Remediate one specific vulnerable container image and deliver the fix as a PR/MR, a tracking ticket, or both — this skill is the sole ticket creator in the Sysdig vulnerability workflow. Deduplicates…

Analyze VictoriaMetrics query trace JSON to diagnose slow queries and produce a structured performance report with time breakdown, bottleneck analysis, and optimization recommendations. ALWAYS use…

Everything Claude Code 的交互式安装程序 —— 引导用户选择并将技能（Skills）和规则（Rules）安装到用户级或项目级目录，验证路径，并可选地优化已安装的文件。

Create a persistent structured plan (plan.md, phases/, todo.md) when work needs multi-phase or multi-session coordination, durable tracking, or an explicitly requested plan.

Odoo 18 development reference for Python models and ORM (search, domain, read_group, compute fields), XML/CSV data and views, OWL/JS client code, QWeb reports, security (ACL, record rules, groups),…

Use when David is preparing for or running a consulting call (lawyer, accountant, tax advisor, etc.) and wants to manage a question list — adding, marking as asked, moving between Main/Potential, or…

对明确指定的抖音公开 video 或 note 作品执行一次点赞、收藏或评论，或返回分享链接。用户要求点赞、收藏、评论、取消相应状态或获取抖音作品链接时使用。

Bevisst KI-bruk i Nav: grønn og rød sone, tre-forsøks-regelen, erfaringsnivå og generer-så-forstå, med forskningen bak. Bruk når utvikleren spør om KI bør gjøre en oppgave, vil lære, eller når en…

Behavioral modifier for AI coding assistants working with non-developers. Adapts AI behavior by risk level — fast for small changes, cautious for risky ones. Prevents debug death spirals, translates…

Read or resolve a pull request's Qodo review using Qodo managed tools through MCP or the CLI — fetch structured status, reviewed commit SHA, and findings for ANY PR as JSON, with optional extended…

Stripe payment platform integration guide covering API authentication, webhooks, error handling, testing, Connect platforms/marketplaces, SDKs, and development best practices. This skill should be…

Conversion-optimized landing page design — single-file HTML with embedded CSS, no external dependencies. Hero sections, social proof, CTA placement, A/B variants, responsive design, accessibility, and…

Load this skill when configuring axe-core scans, reviewing automated accessibility test results, or writing tests that use @axe-core/playwright, @axe-core/react, or similar integrations. Provides a…

Invoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent…

Run several coding agents in parallel in Superset workspaces, each under its own clausona profile (another Claude Code or Codex account, or an API model such as GLM or DeepSeek), then watch them,…

Orchestrate comprehensive Python refactoring - coordinates security, complexity, testing, code health, and modernization skills to systematically improve code quality.

Use before claiming anything works, is fixed, is done, or passes; before status updates on changes you haven't run; before agreeing with someone else's claim about your work; and before state-changing…

Use when the user names a coding, Claude Code, research, documentation, or technology-selection task; asks which prompt to use; says to use the right prompt; or when an agent enters this repository…

Router for the /docs command. Look up Claude documentation, ask plain-English questions, generate interactive courses and HTML changelog reports, check freshness, and sync the local cache. Dispatches…

Querying Stellar chain data via Stellar RPC (preferred) and Horizon (legacy). Covers RPC JSON-RPC methods, Horizon REST endpoints, streaming, pagination, historical queries, Hubble/Galexie for deep…

Set up and run autonomous experiment loops to optimize Simmer trading skills. Mutates skill code + config, measures P&L, keeps what works. Use when asked to "optimize a skill", "run autoresearch", or…

Audit any OpenPersona (or peer LLM-agent) persona in three complementary modes: structural (CLI, deterministic, CI-friendly: 4 Layers × 5 Systemic Concepts × Constitution gate with role-aware…

Draft git commit messages. Use when asked to create, draft, or prepare a commit message. Analyzes staged/unstaged changes and recent history to match project style.