Agent skills for ChatGPT

/============================================================================/ / SKILL SKILL :: VERILINGUA x VERIX EDITION /…

Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based…

This skill should be used for structured feature development with codebase understanding.

将需求发现、领域建模、一致性审计整合到 /team-* 主链， 以 artifacts/adr/memory 为唯一落盘目标产出可审计文档。 当 Tech Lead、Architect、QA 需要补齐或演进架构文档时使用。

Guide users through a structured workflow for co-authoring documentation.

Crawl repository for scattered docs and consolidate into categorized reference index in .aiwg/docs/

Compare design documents against actual code/config, find inconsistencies, and output a prioritized attention list.

Use when you need to gather context for a Jira ticket or PR.

Use this skill to perform adversarial review of AsciiDoc documentation against context sources.

Use when user asks about 'documentation workflow', 'how to document', 'doc system', 'what is llmdoc', 'how does llmdoc work', or needs…

Checks Docker Compose configuration for PHP stacks.

Use when deploying Docker Compose applications to production including security hardening, resource management, health checks, logging…

Checks Docker layer efficiency for PHP builds.

Generates Nginx configuration for PHP-FPM Docker containers.

Checks Docker production readiness for PHP applications.

Use when recording, superseding, reversing, or indexing an architecture decision (ADR) — capturing why a non-obvious technical decision…

Automate Docnify tasks via Rube MCP (Composio).

Research documentation, find examples, explain APIs and libraries - Use when you need to look up official documentation, find code…

Score a technical doc (RFC, ADR, README, CLAUDE.md, blog-style post) against the 5-category 100-point rubric in .rules/docs-rubric.md.

Improve an existing technical doc in-place via a phased Audit → Research → Rewrite → Validate workflow.

Find documentation for APIs, libraries, and error messages.