chore: rewrite repo in idiomatic English (agents, skills, docs, codex)#21
Conversation
Sweep of Portuguese prose across .claude/agents (25), .claude/skills + .agents/skills (6), .codex/agents (6 TOML), AGENTS.md, CLAUDE.md. Rewritten for clarity, not literal translation. Trigger vocabulary in skill descriptions is now English; technical anchors (Anchor, Codama, Pinocchio, Surfpool, cargo-dist, stdio JSON-RPC, gRPC) preserved. Preserved verbatim: code blocks, identifiers, file paths, exit codes, NDJSON event names, JSON payloads, marker tags, dates, PR numbers. Untouched (already fluent English): README, CHANGELOG, ROADMAP, IMPLEMENTATION-KICKOFF, all docs/adr, all docs/reference, all docs/site/src. No Rust source, tests, templates, or golden snapshots modified. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
|
Warning Review limit reached
More reviews will be available in 41 minutes and 55 seconds. Learn how PR review limits work. Your organization has run out of usage credits. Purchase more in the billing tab. ⌛ How to resolve this issue?After more reviews become available, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans include higher PR review limits than trial, open-source, and free plans. In all cases, reviews become available again over time. During sustained high-volume PR review activity, CodeRabbit may temporarily slow when the next review becomes available. Please see our Fair Usage Limits Policy for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: Organization UI Review profile: ASSERTIVE Plan: Pro Run ID: 📒 Files selected for processing (39)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Summary
Repo-wide sweep converting residual Portuguese prose into idiomatic English. Not a literal translation — text was rewritten so trigger vocabulary in skill/agent descriptions stays discoverable in English while all technical anchors are preserved verbatim.
Changes
.claude/agents/*(25 subagent definitions): publishers, docs, test-harness, implementation team..claude/skills/* + .agents/skills/*(6SKILL.md): orchestrator, docs-orchestrator, test-harness, publisher.description:fields rewritten — the auto-invocation contract is now English ("real tests","next phase","run it again", etc.) but technical anchors are kept (Anchor, Codama, Pinocchio, Surfpool, cargo-dist, stdio JSON-RPC, gRPC, Phase 6/7/8, scaffold, recipes, …)..codex/agents/*.toml(6 files): TOML structure preserved, prose rewritten.AGENTS.md,CLAUDE.md: trigger phrases and one variation-log row.Preserved verbatim
Code blocks, identifiers, file paths, exit codes, NDJSON event names, JSON/YAML payloads, marker tags, YAML
name:/tools:/model:, ADR cross-refs, dates, PR numbers, commit hashes.Already fluent English (no edits)
README, CHANGELOG, ROADMAP, IMPLEMENTATION-KICKOFF, all
docs/adr/ADR-*, alldocs/reference/*, alldocs/site/src/**(Learn, Guides, Concepts, Reference, Contributing),assets/learn/*,assets/examples/*/README.md, GitHub templates.Untouched
Rust source, tests, templates, golden snapshots. No code changes —
cargo check --no-default-featuresclean.Reviewer notes
description:fields, which drive auto-invocation. Triggers were remapped (not literally translated) to English equivalents — please skim and flag if any PT phrase you commonly use should also be retained as an alias.docs-tutorial-writer.mdanddocs-reviewer.mdhad a "⏱" emoji replaced with "Time:" per the no-emoji guidance — easy to revert if you'd rather keep the icon.Checklist
cargo check --no-default-featuresgreen)cargo fmt --all— n/acargo clippy --all-targets -- -D warnings— n/acargo test --all— n/a (no code touched)🤖 Generated with Claude Code