Erzeugt einen konsistenten Satz Bilder (Slide-Hintergruende, Bildserien) via OpenAI gpt-image-1. Trigger bei 'Slide-Hintergrund', 'deck background', 'Folien-Bilder generieren',…
Vercel AI SDK v6 development. Use when building AI agents, chatbots, tool integrations, streaming apps, or structured output with the ai package.
Vercel AI SDK v7 development and migration. Use when building or upgrading AI SDK 7 apps, especially ToolLoopAgent, WorkflowAgent, HarnessAgent, Claude Code/Codex/Pi harnesses,…
Analyze the codebase for a spec. Detects complexity (LOW/MEDIUM/HIGH), maps affected files with file:line references, and creates an implementation plan with TDD.
Archive a finished spec and feed its durable knowledge back into the project's living documentation — resolving the branch's merge conflict with the default branch first, if there…
Close a spec that is not going to work: record the reason, move it to archive/, and delete its code branch without merging it — resolving the specs branch's merge conflict with…
Create a spec — a title and a description — as the 4-file spec structure (description, analysis, solution, status).
No-stakes thinking partner before /aide-create: explore a problem or idea, weigh approaches, sharpen the scope — without creating any files.
Implement the solution for a spec with Test-Driven Development (RED → GREEN → VERIFY). Reads the existing analysis and plan, writes tests first, implements, and runs the quality…
Draft or refresh the project's .aide/project.yaml manifest — what the project IS: stack, dependencies, deployment, logging, statistics, reports, docs.
Take an archived spec back into the active list for another round, keeping every file as it is, or, when asked, resetting the analysis, the plan and the status as well.
Generate PDF from a spec. Use when: exporting documentation to PDF, generating a print-friendly spec. Do NOT use for: creating documentation (use aide-create)
Build the project's wiki: a map of how its parts hang together, kept in the project's folder of the specs repository and read first by /aide-analyze.
Generate professional Agent Skills for AI agents. Creates complete skill packages with SKILL.md, references, scripts, and templates.
Analyzes Claude Code sessions from a user-defined start date through today. Executes SWOT analyses, self-critiques, and self-reflections for each skill, sub-agent, command,…
Installs or updates this architecture's `.claude/` inside a Java project — norms with their globs derived for the project's own packages, the development skills and agents, the…
Execute project-specific verification rules. Validates business logic, architecture patterns, and naming conventions that linters cannot catch.
Classify tracked markdown for five noise shapes — historical citations, ghost refs to ephemeral working-directory paths, \"Why this file exists\" preambles, hard-coupled…
List every lint and type-checker suppression in a change, a path, or the tree (`--all`): eslint-disable, @ts-expect-error, noqa, type: ignore, pylint, pyright, shellcheck disable,…
Manage git and Claude Code bash aliases. Run without flags for interactive wizard.
Python 执行增强（uv heredoc 规范）。TRIGGER when: Bash 工具中需要执行 Python 代码（多行脚本、依赖安装、uv run 调用）。SKIP: 纯 shell 命令、不涉及 Python 的 Bash 操作。
Cross-model benchmark for gstack skills. Runs the same prompt through Claude, GPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost, and optionally quality…
Analyze binary size and dependency bloat using cargo-bloat. Use when the user asks about binary size, large dependencies, or size optimization.
Compare two git branches side-by-side using a configurable diff tool (defaults to Beyond Compare) and temporary worktrees.
Scaffolds a standalone Bash 4.0+ script — a single-file CLI tool, glue automation, or ops utility — with explicit shebang, `set -euo pipefail`, header comment, `readonly`…
Builds a throwaway generator the person tunes for an artifact prompting cannot hit, whose saved output goes into the project.
Add a new package to the Reactive Agents monorepo. Covers scaffolding, package.json, tsconfig, layer wiring, and index exports.
Scaffolds a reproducible pre-commit configuration — a `.pre-commit-config.yaml` at the repo root (optionally with local shell scripts under `scripts/hooks/`) that runs formatters,…
Scaffolds a project's top-level README.md — the `README.md` at a repository root that orients a first-time reader in the top 30 seconds.
Optional manual drift audit — report stale provenance-tracked docs, then per stale doc offer re-scout, re-baseline, or defer.
Slash-command entry point for outside-pipeline issue capture. Parses `/capture-issue
` (create-mode) or `/capture-issue --update ` (update-mode); spawns the…
Install or use the ccap CLI for camera capture, webcam inspection, device listing, frame capture, and video metadata.
Use after /diagnose-agent when you have a struggle profile and need training challenges. Generates edge-case and commit-replay challenges calibrated to weak areas.
Audits a Bash 4.0+ script against 34 deterministic rules emitted as JSON envelopes (shebang, `set -euo pipefail`, header comment, main + sourceable guard, readonly constants,…
Audit enabled eslint / prettier / biome rules and rank keep / tune / drop via Wilson consensus across 5 independent lenses. Args:
Audits a `.pre-commit-config.yaml` (and referenced local hook scripts) against 20 deterministic checks (YAML shape, `rev:` pinning, scope declarations, network-call /…
Check a text fragment for potential secrets (API keys, tokens, passwords) BEFORE sending to chat / committing / publishing.
Hub for the claude-cli-wrapper MCP server — execute, session, context, review, agent, and config tools. Routes to spoke skills.
Build custom agents with the Claude Agent SDK. Programmatic Claude Code via CLI (-p flag), Python, and TypeScript. Structured output, streaming, tool approval, and CI/CD scripting.
Run the full local cleanup pipeline — stale git worktrees, dead personal forks, Docker prune, Go caches, and Homebrew — in one pass, each stage report → confirm → execute, then a…
部署 Swift CLI 工具（編譯 universal binary、建立 GitHub Release、安裝到 ~/bin）。在 Swift CLI 專案目錄中使用。
CLI development expert for building production-grade command-line tools. Covers System.CommandLine, POSIX conventions, help text design, output formatting, and MCP-to-CLI feature…
モダン CLI ツール (rg/fd/bat/eza/dust/btm/procs/delta/sd/hyperfine/tldr/jless/tokei/zoxide) の使い方を即引きする。「rg の使い方」「grep の代替」「du より見やすいやつ」などの問い合わせで cheatsheet から該当箇所を抜粋する
Compose the versions CLI in shell pipelines, scripts, and CI/CD — output formats, exit codes, input methods, and command patterns.
Use when: reviewing, designing, or refactoring CMake build configuration, CMakeLists.txt, target-based usage requirements, PUBLIC PRIVATE INTERFACE propagation, find_package vs…
Fix PHPStan, PHPCS, twigcs, and yamllint violations from error output. Use when the user pastes linter errors, mentions GrumPHP failures, asks to fix PHPStan or PHPCS issues, or…
根据代码改动智能选择并执行本地静态检查（checkstyle / style-checks / static-analysis-checks / functional-test-checks / npm-lint），与用户确认后运行，失败时自动分析并修复，最多重试 3 次。Use when:…
Analyzes the current WPF working session and produces an accumulable wpf-dev-pack improvement-feedback markdown file in the current directory.
Commit finished work cleanly on the shared trunk — lint the subject with `fak commit --preview`, then stage-and-commit EXACTLY your paths in one locked step via `fak commit --path…
Write value-first commit message (subject + body) for staged/unstaged changes or branch work. Use when: writing commit message, about to stage changes, before commit, drafting…
List recent git commits linked to agent sessions, optionally filtered by branch or repo. Use when the user asks "show agent commits", "what has the agent shipped", "list linked…
Generate conventional commit messages without scope from staged changes. Use when: preparing commits with #git_diff_staged to create concise commit messages following conventional…
Generate descriptive commit messages by analyzing git diffs, very fast and context pollution safe. Use on any request to commit staged changes.
Validates and corrects commit messages against project guidelines after a commit is created. Invoke automatically after every git commit to ensure messages conform to…
Commit changes with well-crafted messages, grouping related files into separate commits
Audit project gates (jest/vitest coverage thresholds, tsconfig strictness, eslint rules, husky/lint-staged, sonar quality gate, branch protection) and flag values mathema — from…
Use this skill PROACTIVELY at session start when working in a project that uses aide (look for aide config, .aide directory, or aide CLI on PATH).
Generates an interactive HTML view of a contract review with clause drill-down, severity filters, side-by-side comparison (their language vs proposed), and inline comment threads.
Composite CI gate — runs cost-budget-check + cost-burn + cost-anomaly + cost-projection in parallel and surfaces a single combined health status with max exit code.
Generate and run comprehensive test suites — unit tests, integration tests with real services (testcontainers/docker-compose), and Playwright E2E tests.