Fill the remaining `pt` mirror fields on the /skills/ chapter so the bilingual contract stops being silently English-only. 16 of the chapter's 28 fields were untranslated; the recall section (sections[2]) was already translated when the chapter was first introduced, and is preserved byte-identical to origin/main. The chapter composes: - Hero (eyebrow, title, lede). - Section 0 (Package anatomy): eyebrow, multi-line title, copy. - Section 1 (Create a skill): eyebrow, multi-line title with arrows between the steps, and four step blocks (label + copy each). - Section 2 (Check yourself): recall Q/A pairs and citation links. Already translated; preserved byte-identical. Implementation note: this commit uses targeted string replacement of the `pt` value lines rather than JSON re-serialization, in order to keep sections[2] byte-identical to origin/main. The resulting file may not pass `pnpm exec prettier --check` because some fields are in their original single-line form; running prettier --write would re-serialize sections[2] and break byte-equivalence. Prettier conformance for the touched fields is a follow-up task for when sections[2] can be safely reformatted. Translation register follows the conventions established by src/content/commonSkills/*.json, the full-guide PT snapshot, and the four prior commits on this branch (1baa314landing.json,fd031b0summary.json,160a324models.json,18bf6b0agents.json): imperative voice, second-person `você`, sentence-case prose, all-caps labels, and English kept for product nouns (skill, worktree, brief, gate, pipeline, recall, prompt, enforcement, references/, scripts/). Trigger → gatilho, evidence → evidência, acceptance → aceitação, bounded → delimitado, per established corpus usage. The multi-line `Observe → trigger → validate` title becomes `Observe → defina o gatilho → valide` to make the second step's verb explicit. Verified by .agents/scripts/audit-translations.mjs: skills.json contribution to the offenders list drops from 16 to 0. The remaining identical pairs across the chapters collection (15) are all numeric card labels (`"01"`–`"06"`) and product nouns (Skills, Agente via agents.json, Brief via agents.json), which are correctly identical across locales. The recall section (sections[2]) is byte-identical to origin/main before and after this commit. Verified by reading the parsed JSON and comparing each field.
AI For Dummies
A lightweight, presentation-style field guide to AI-assisted engineering.
It explains how to combine a strong planning/review model with faster workers,
reusable skills, subagent handoffs, Git worktrees, and explicit verification. An
interactive field kit compares common behavior skills such as ponytail-lite,
caveman, unlazy, research, debugging, and review. The skill-forge workflow
covers discovery, triggers, package anatomy, progressive instructions,
structural validation, and behavioral iteration. The hands-on lab provides a
tiny starter project and copy-ready baseline and skill-enabled prompts for a
short side-by-side exercise. An interactive model gearbox separates capability
tier from reasoning effort across OpenAI, Claude, and Gemini, and every featured
skill links to a pinned source with an approval-first installation prompt.
Run locally
This is an Astro static site. It builds to dist/ and ships no runtime
dependencies.
pnpm install
pnpm run dev # http://localhost:4321/ai-for-dummies/
pnpm run build # writes dist/
pnpm run preview # serves the built output
Verify the content and interaction contracts with:
pnpm run verify # reads dist/, so build first
The full gate — astro check, astro build, verify.mjs, audit-ui.mjs,
check-tokens.mjs, and the assertion-count floor — runs as:
bash .agents/scripts/gate.sh
Project structure
src/pages/— one file per route: the landing route map, the complete bilingualfull-guide, the chapter pages,rules,skills, andskills-reviewsrc/components/— blocks and islands; the interactive diagrams, selectors, and the language togglesrc/content/— the content collections every page renders fromsrc/styles/tokens.css— the design tokenslegacy/— the editorial visual system and the review-desk modules, not yet migrated into components. Still imported by the pages that need them; see.agents/context/architecture.mdpublic/— assets copied to the site root verbatim: fonts, the hands-on labs, andsubmitted-skills/docs/references/— bundled research sources and notesdocs/operations-guide.md— canonical SilverBullet operations and skills guidepublic/hands-on/starter/— dependency-free Tiny Tasks exercisepublic/hands-on/rules/— dependency-free Guardrails lab; toggles rule sources into the promptskills/— reusable design and rules-case-study skillsGATES.md— acceptance ledger for the project
Publishing
The Gitea instance has a Pages Server configured to publish a repository’s
pages branch under pages.marcospaulo.dev.br. pages now carries the
built site — the contents of dist/ — not a copy of main. The intended
site address is:
https://netcracker.pages.marcospaulo.dev.br/ai-for-dummies/
If the URL is not available yet, verify that the pages branch exists and that
the repository’s pages branch exists. Gitea itself does not provide a built-in
Pages server; this setup uses the instance’s separate Pages Server and Actions
deployment path.
For the complete authoring, verification, publication, rollback, worktree, and skill workflow, see docs/operations-guide.md.
Reader voting on the skills-review desk
skills-review/ is static, so its "which draft would you ship?" vote widget
calls a separate stateful service — a small Go API on its own pod, one vote per
visitor enforced server-side by IP (a MAC address is never visible to a server
across the internet, so it cannot be used). Its source no longer lives in this
repository; the deployed service is unchanged. src/pages/skills-review.astro
sets window.SKILLS_REVIEW_VOTE_API to point at it.
Research
See docs/references/README.md for official Claude, Codex, and Git documentation. The additional reading path bundles 12 verified articles and guides, including Medium and practitioner sources. See model routing for current provider controls and verified skill sources for commit-pinned provenance.
Rules and enforcement case study
Open /rules/ for a concise walkthrough grounded in the netcracker/interview
repository. It shows how AGENTS.md, project-local skills, machine-readable
repo ledgers, a UI contract ratchet, lint-staged, Husky, commitlint, specialist
verifier agents, and PR review reinforce one another. Every example links to its
source file in Gitea, and the page includes a copy-ready prompt for mapping the
same layers in another repository.
The implementation patterns are also packaged as project-local skills in
skills/. Use editorial-playbook when adding chapters or
sections, and rules-case-study when turning repository controls into a
source-linked teaching page.