Coding & Development

Agent skill 'systematic-debugging' from DanhDue/ai-agent-tools.

Invoke Google's Antigravity CLI (agy) from inside Claude's own sandbox, authenticated via the user's personal Antigravity subscription sign-in (never an API key). Use this ONLY when the user explicitly asks to use Antigravity CLI, agy, or "this bridge" for a task — never invoke it on your own judgment the way you might reach for a general-purpose tool. Typical explicit phrasings: "Antigravityに聞いて", "agyに投げて", "use antigravity for this", "run this through the antigravity bridge".

Agent skill 'debugging-investigator' from alphasafal/production-agent-skills.

Agent skill 'verification-before-completion' from DanhDue/ai-agent-tools.

Agent skill 'production-code-review' from alphasafal/production-agent-skills.

Agent skill 'repo-architect' from alphasafal/production-agent-skills.

Use when coordinating engineering work in this project: selecting which original upstream skill to follow for discovery, architecture, frontend, backend, data, infrastructure, testing, security, release or operations work, and resolving its original file paths and tools.

Agent skill 'using-git-worktrees' from DanhDue/ai-agent-tools.

Agent skill 'feature-to-production' from alphasafal/production-agent-skills.

Use when this project's work involves Metrics definitions and cohort-based feedback alongside provider instrumentation — covers product analytics/feedback. Loads the original pm skills bundled with this pack.

Agent skill 'subagent-driven-development' from DanhDue/ai-agent-tools.

Use when this project's work involves Original agent skill evaluation and MCP server engineering specialists — covers testing, api contracts. Loads the original anthropic skills bundled with this pack.

Use when this project's work involves Rust ownership, errors, testing and performance conventions — covers backend, reliability/resilience, testing. Loads the original apollo skills bundled with this pack.

Agent skill 'system-design-reviewer' from alphasafal/production-agent-skills.

Make CLIs agent-friendly: structured help, machine-readable output, and safe automation hooks.

Deep project review skill for thorough codebase and architecture audits.

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

将已收敛的 map、ADR、spec 或 implementation plan 编译为 Gate 计划、状态账本和跨轮复用的固定执行提示词。

基于项目证据创建或更新指定作用域的 AGENTS.md；发现既有匹配指南时，先取得文件选择、合并或覆盖和最终写入确认。

Standardized compliance QRA benchmarks against candidate LLMs

Perform a read-only, defect-first review of a specified code change and return every actionable finding. Use when another agent delegates review of uncommitted changes, a base-branch diff, a commit, or custom review instructions.

Pre-flight validation and quality gates for batch LLM operations. ACTUALLY tests samples through LLM before burning tokens. Uses SPARTA contracts for DuckDB validation queries. Integrates with task-monitor for enforced quality gates.

从已完成的代码框架、配置和工程资料建立、新增、补充或重构技术文档的信息架构、内容边界与表达方式。

Step back and critically reassess project state. Use when asked to "assess", "step back", "fresh eyes", "check alignment", "sanity check", "health check", "prune documentation", or "evaluate what's working". Offers documentation pruning and doc-code alignment analysis. Offer to run after major changes (don't auto-run).