AI Agent Skills

在已选用 arc 规划且需要独立框架评估时，审查节点分配、人物弧和关键转折。

Skill phân tích và khắc phục các automation test không ổn định (flaky tests), xác định root cause và đề xuất fix.

Skill tích hợp Jira/Xray — lấy requirements từ Jira, xác thực Xray, và đẩy kết quả test lên Xray Cloud/Server.

Skill sinh test data có cấu trúc, unique, traceable cho automation tests, bao gồm positive, negative, boundary và edge cases.

Structured co-authoring workflow for specifications, proposals, decision docs, PRDs, RFCs, and other substantial written artifacts. Use when Codex should help a user gat…

Deep-dive spec interviewer. Reads a file, GitHub issue, or requirement, analyzes it against the codebase, then conducts a rigorous 1-on-1 interview using AskUserQuestion…

Crée une nouvelle branche Git à partir de la dernière version de main, avec un préfixe conventionnel feat/ (nouvelle fonctionnalité) ou fix/ (correction de bug). Utilise…

Investiguer méthodiquement un bug en 4 phases validées : localiser/reproduire, 3 hypothèses classées sur la cause racine, logs ciblés, fix minimal. Utilise sur /investig…

Export Swift to JavaScript and import JavaScript/TypeScript into Swift using BridgeJS; type-safe bindings via @JS and related macros or bridge-js.d.ts; setup, config, AO…

Check Swift on Wasm compatibility, identify incompatible frameworks, port and refactor code for WebAssembly

Configure a repository for Atelier's development workflow. Use only when explicitly invoked; inspect existing guidance, issue-tracker and domain-document conventions, pr…

Generate and validate conventional commit messages following the conventionalcommits.org spec. Use whenever the user wants to commit code, mentions commit messages, git…

Compact the current conversation into a handoff document for another agent to pick up.

Manage GitHub pull requests or GitLab merge requests: create, read/leave/respond to comments, and merge. Triggers on "open a PR", "make a PR", "merge this PR", "merge th…

Multi-agent code review with parallel specialized reviewers, architecture validation, challenge validation, and durable handling of previously decided findings. Use `rq`…

Implementation subagent dispatch patterns. Use when independent implementation work is available and subagents can execute it. Covers parallel dispatch, shared-tree patc…