Writing & Editing

Use when writing or reviewing tests, or when asked how to write a good single test. Encodes the per-test rules behind the "test the contract / responsibility, not the implementation" principle — name and structure one behavior per `it`, drive through the public surface, stub only true external boundaries, control time and config via documented knobs, and keep tests clear, isolated, and refactor-resilient. The same rules drive both authoring (write mode) and auditing existing tests (review mode).

Use ONLY for code review and test write/review guidance in `packages/agent-core-v2` (the DI × Scope agent engine). Does NOT apply to the legacy `packages/agent-core` or to any other package — for those, do not load this skill. Groups the review and testing lenses used for agent-core-v2 — `slop` (single-level-of-abstraction / layered error-handling review, invoked only on explicit request) and `test` (contract-driven per-test rules for both authoring and reviewing tests). Apply the sub-skill that matches the task; do not apply `slop` unprompted.

Code like Fable 5 — methodical, verified, and deeply informed by context. Use this skill whenever you need to write, edit, or create code.

Use in the BuilderIO/skills repo whenever adding, updating, publishing, documenting, validating, or wiring a public skill. Covers the repo-local skill files, root catalog docs, plugin metadata, @agent-native/skills dynamic install path, optional managed AGENTS/CLAUDE instruction blocks in ../agent-native/framework, and generated/synced Plan skill gotchas.

Use when asked to compare, cross-review, merge, judge, choose, or arbitrate competing plans from multiple agents such as Codex and Claude Code; when given two or more proposed plans, session IDs, transcripts, plan documents, PR descriptions, or pasted strategies; or when the user wants one recommended execution plan after agents review each other's proposals.

Claude skill: remove AI writing patterns from Chinese text (translated from blader/humanizer, MIT)

Recently updated agent-skill-related GitHub repository: darshithedpara/resume-cross-examine-and-interview-prep-claude-skill.

Find quality X posts and turn them into Douyin & Xiaohongshu content｜自动搜集 X 优质帖子，转化为抖音、小红书双语图文素材的 Codex Skill

An OpenAI Codex skill that prevents long-running task drift across context compaction, corrections, resumed sessions, and multi-agent workflows.

Translate complex content into plain language. A Claude Code / Codex skill.

Forma Copywriting Claude Skills for B2B marketing teams

Codex skill for auditing X posts against platform rules and creator monetization standards.

Codex skill for blind multi-agent benchmark Evaluate auditing and safe JSONL writeback

Codex skills for Obsidian study notes, tag normalization, and editable schedule workflows.

Reusable Codex skills

A secure, automation-friendly Pushover CLI for sending notifications from terminals, scripts, and AI agents

Codex skill for a verified end-to-end WeChat article workflow

Distilled operating skills for daily-driver Claude models — few dense rules, executable gates over long prose.

Global 2 million hotels booking skill. Featuring price monitoring and alert functions. Powered by official data from world's #3 B2B travel platform. It supports credit card payments, full order tracking, and 24/7 customer support.

Codex skill：将带UI的游戏图片转化为可编辑的PSD

Agent skill that turns a Git repo's real code history into a per-day project worklog under PROJECT_WORKLOG/ (one Markdown file per day + an index) — reads actual diffs, not just commit messages, and previews every change before writing.

Open-source Codex skill for keeping long-running tasks aligned across context compaction, corrections, and resumed work.

Claude Code agent skill: IEEE-only paper survey — search, triage, translated-abstract cards, one-confirmation PDF fetch. Requires institutional IEEE Xplore network access.

A Claude Agent Skill that finds the root cause of flaky (non-deterministic) tests and rewrites them to be deterministic. pytest · Jest · RSpec · Go · JUnit.