eval-materials-vs-build

Scores how faithfully a recorded build run aligned with the course materials, in the spec-build-lab. Use this skill ANY time the user asks to evaluate, score, check, judge, or compare a specific build run AGAINST THE COURSE — including phrasings like "evaluate run-02 against the materials", "score run-02 against the course", "is run-02 faithful to the course", "did the build match the course", "course alignment check on run-NN", "how does run-02 compare to the notebooks and transcripts", "is the build aligned with what the course taught", "run a materials-vs-build eval", or "/eval-materials-vs-build run-NN". Reads materials/notebooks/, materials/transcripts/, and builds/<run>/, then writes evals/<run>/materials-vs-build.md. Requires an explicit run-NN; if none is given, list the runs in builds/ and ASK which one — never default. Do NOT use this skill to evaluate against spec.md — that's /eval-spec-vs-build, a different reference and different question.

Ir para a instalação Revisar arquivos

Repositório: https-deeplearning-ai/spec-build-lab
Última atividade na origem: 18 de junho de 2026 às 10:41
Idioma detectado do SKILL.md: inglês
Estrelas: 4
Forks: 4

Opções de instalação

Por padrão, está selecionado o prompt que primeiro revisa a origem. Você pode mudar para um comando direto ou baixar uma cópia local.

Instalar com um assistente de IA

Copie este prompt para o assistente de IA que você usa.

Follow https://skillsmp.com/skill-install/prompt.md to install only the Agent Skill at https://github.com/https-deeplearning-ai/spec-build-lab/tree/main/.claude/skills/eval-materials-vs-build.

Um comando direto ignora o prompt de revisão. Verifique a origem antes de executá-lo.

npx skills add https://github.com/https-deeplearning-ai/spec-build-lab --skill eval-materials-vs-build

O comando permanece em uma só linha. Role horizontalmente para revisá-lo antes de copiar.

Prefere uma cópia local? Baixe os arquivos disponíveis atualmente no SkillsMP.

Revise os arquivos de origem

Leia o SKILL.md e os arquivos complementares exibidos pelo SkillsMP antes de decidir se vai instalar.

SKILL.md

Instruções da origem · Visualização somente leitura

name: eval-materials-vs-build
description: Scores how faithfully a recorded build run aligned with the course materials, in the spec-build-lab. Use this skill ANY time the user asks to evaluate, score, check, judge, or compare a specific build run AGAINST THE COURSE — including phrasings like "evaluate run-02 against the materials", "score run-02 against the course", "is run-02 faithful to the course", "did the build match the course", "course alignment check on run-NN", "how does run-02 compare to the notebooks and transcripts", "is the build aligned with what the course taught", "run a materials-vs-build eval", or "/eval-materials-vs-build run-NN". Reads materials/notebooks/, materials/transcripts/, and builds/<run>/, then writes evals/<run>/materials-vs-build.md. Requires an explicit run-NN; if none is given, list the runs in builds/ and ASK which one — never default. Do NOT use this skill to evaluate against spec.md — that's /eval-spec-vs-build, a different reference and different question.
argument-hint: <run-NN>
allowed-tools: ["Read","Write","Glob","Grep","Bash"]

# eval-materials-vs-build Compare a recorded run's app against the original course materials. **Course alignment only.** Spec fidelity is `/eval-spec-vs-build`. ## Steps 1. **Verify cwd is a course folder.** Confirm `spec.md`, `materials/`, `builds/`, `evals/` exist. Refuse otherwise. 2. **Require a run.** If `$ARGUMENTS` is empty: ```bash ls -1 builds/ 2>/dev/null | grep -E '^run-[0-9]+$' | sort ``` List those runs and ask which one. Never default. 3. **Validate the run.** Confirm `builds/$ARGUMENTS/` is a non-empty directory. Refuse otherwise. The report reflects whatever the build folder contains — evaluating an in-progress run is fine; just re-run after the build finishes for a clean score. 4. **Read the inputs.** - Materials: every non-empty file under `materials/notebooks/` and `materials/transcripts/`. - Build: walk `builds/$ARGUMENTS/` (skip node_modules, .venv, dist, build, .git, and anything matching its own .gitignore). 5. **Produce the report at `evals/$ARGUMENTS/materials-vs-build.md`** with sections: - **Summary** — one-paragraph verdict on course faithfulness. - **Concept coverage** — concepts/techniques the materials taught → present / partial / missing in the build, with file references. - **Divergences from the course** — what the build did that the materials never covered (this can be fine, but call it out). - **Course concepts skipped** — what the course emphasized that the build ignored. - **Score** — judgment on a 0–10 scale, with reasoning. 6. **Report the path written, then hand off.** After echoing the report path, tell the user: "Course-alignment report written. The companion eval is /eval-spec-vs-build $ARGUMENTS — different reference, different question (spec fidelity, not course alignment). Say 'go ahead' to run it next, or skip if you've already done it." ## Don't - Don't read `evals/$ARGUMENTS/spec.md` or the top-level `spec.md` — that collapses this eval into `/eval-spec-vs-build`. Different reference, different question. - Don't default a run. List the runs in `builds/` and ask the user which one. - Don't penalize the build for not implementing something the materials didn't actually cover — that belongs in the spec eval.

Ver no GitHub

Voltar à pesquisa Voltar à instalação

generate-spec

Produces spec.md for a course in the spec-build-lab by reading the course's materials and writing a build-ready specification. Use this skill ANY time the user asks to generate, write, produce, build, regenerate, create, or run the spec for a course — including phrasings like "generate the spec", "write spec.md", "produce spec.md", "make a spec from this course", "turn the materials into a spec", "build the spec out of materials/", "regenerate spec.md", "run the spec generation", "I've added the notebooks, please create the spec", or "/generate-spec". Reads every file under materials/notebooks/ and materials/transcripts/ and follows references/spec-generation-guide.md. Writes spec.md in the current working directory. Must run from inside a course folder (courses/<name>/). Do NOT use this skill for editing an existing spec.md or for writing product specs unrelated to a course. Pass --env=<slug> to generate for a known build environment instead of the agnostic learner takeaway (e.g. "/generate-spec --env=coding

2026-09-14

prepare-build

Prepares a new build run for a course in the spec-build-lab — allocates the run folders, snapshots the spec into a frozen eval copy and a working copy, drops a session breadcrumb, and moves into the build folder. Does NOT do the building itself; that's the user + agent's subsequent work in builds/run-NN/. Use this skill ANY time the user signals intent to begin building an app from spec.md — including phrasings like "prepare a build", "set up a build", "start a new build", "begin the build", "kick off the build", "kick off run-02", "let's build the app", "let's build it", "build the X app from the spec", "implement the spec", "I'm ready, let's build", "let's do another build", "/prepare-build", or simply launching into coding work inside a course folder that has a spec.md. INVOKE PROACTIVELY — treat any clear build intent as the trigger. Do NOT use this skill to run an existing build, build a docker image, or build features in unrelated projects. Pass --env=<slug> to prepare a build from that environment's sp

2026-09-13

promote-to-guide

Runs a promotion pass in the spec-build-lab — triages a course spec's hand edits and filed observations, promotes the universal ones into the spec-generation guide, validates the amended guide with clean-room regenerations, and optionally re-baselines the course spec. Use this skill ANY time the user wants spec improvements carried into the guide or future courses — including phrasings like "promote these spec edits", "make the guide learn this", "run a guide pass", "evolve the guide", "the next guide pass", "implement the residuals from issue

2026-09-08

Ver todas deste repositório

eval-materials-vs-build

Informações da origem

Opções de instalação

Instalar com um assistente de IA

Revise os arquivos de origem

Mais deste repositório

Instalar com um assistente de IA

Mais deste repositório