Run any Skill in Manus with one click

prepare-build

Stars2

Forks2

UpdatedJune 18, 2026 at 10:41

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.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

https-deeplearning-ai

https-deeplearning-ai/spec-build-lab

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Postsecondary Teachers, All OtherEducational Instruction and Library Occupations·SOC 25-1199

SKILL.md

readonly

name	prepare-build
description	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.
allowed-tools	["Bash","Read"]

prepare-build

Allocate the next run-NN, snapshot the spec, drop a session breadcrumb that /extract-build-log will use later, and move into the build folder. Does NOT start the build — building is the agent's subsequent work.

Steps

Verify cwd is a course folder. Confirm all exist relative to cwd: spec.md, builds/, evals/, materials/. If any are missing, refuse with: "Run /prepare-build from inside a course folder — cd courses/<name> first." Stop.

Allocate the next run number.

highest=$(ls -1 builds/ 2>/dev/null | grep -E '^run-[0-9]+$' \
  | sed 's/run-//' | sort -n | tail -1)
next=$(printf "run-%02d" $(( ${highest:-0} + 1 )))

Create the run dirs and snapshot the spec.
```
mkdir -p "builds/$next" "evals/$next"
cp spec.md "evals/$next/spec.md"   # frozen snapshot, read by /eval-spec-vs-build
cp spec.md "builds/$next/spec.md"  # working copy, read by the build agent
```
The eval snapshot at evals/$next/spec.md is judged against later by /eval-spec-vs-build, so the run is judged against the spec it was actually built from even if spec.md is regenerated. The working copy at builds/$next/spec.md makes the build folder self-sufficient — the agent reads ./spec.md from inside the build folder and has no reason to navigate back up to the course folder, where materials/ sits and is forbidden.
Drop the session breadcrumb. Write the absolute path of the current Claude Code transcript JSONL to evals/$next/.session. The path is built from $CLAUDE_PROJECT_DIR and $CLAUDE_CODE_SESSION_ID:
```
slug=$(echo "$CLAUDE_PROJECT_DIR" | sed 's:/:-:g')
transcript="$HOME/.claude/projects/$slug/$CLAUDE_CODE_SESSION_ID.jsonl"
echo "$transcript" > "evals/$next/.session"
```
If $CLAUDE_CODE_SESSION_ID is unset for any reason, fall back to the most recently modified *.jsonl in $HOME/.claude/projects/$slug/ and write that path. The file is per-run, write-once at allocation, never updated.
Announce. Say verbatim, replacing NN: "Run NN — building in builds/run-NN/. Read spec.md (in this folder) and nothing else from the parent course folder. When the build is in a state worth capturing, run /extract-build-log run-NN to slice the conversation into evals/run-NN/session-log.md."
Move into the build folder. cd builds/$next. From here on the agent develops the app inside this folder.

Notes

The breadcrumb at evals/run-NN/.session is a label on the run-NN folder, not coordination state. It's never updated and never read by any other tool — only /extract-build-log consumes it, and only when the user explicitly asks for an extract. Nothing recorder-like is running in the background.
The whole conversation is already being persisted by Claude Code into ~/.claude/projects/<slug>/<session>.jsonl; the breadcrumb just remembers which transcript to slice.

Don't

Don't generate or modify spec.md here — that's /generate-spec.
Don't ask the user for a run number — allocation is automatic.
Don't reuse an existing run-NN folder. Every new build is a new run, even with the same spec.md, so runs and their evals can be compared.
Don't read ../materials/, ../../materials/, or any course materials during the build. The build is a function of spec.md only — that's what the eval pipeline assumes. A PreToolUse hook blocks materials access from inside a build folder; if the hook is bypassed for any reason, /extract-build-log surfaces a contamination warning.

More from this repository

same repository

generate-spec

https-deeplearning-ai/spec-build-lab

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". Optionally accepts a git repo (SSH URL or local path) as an argument to auto-ingest the notebooks + helper.py into materials/notebooks/ before generating; without an argument it uses whatever is already in materials/. 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 f

2026-07-202

new-course

https-deeplearning-ai/spec-build-lab

Adds a new course to the spec-build-lab. Use this skill ANY time the user wants to register, scaffold, set up, add, create, init, or start tracking a NAMED COURSE in this repo — including phrasings like "scaffold a new course called X", "set up a course folder for X", "make a new course called X", "add the X course", "init the X course", "let's start tracking the X course", "I want to add a new course", "/new-course X", or any user message naming a course they want to begin. This skill copies templates/course/ to courses/<name>/ and nothing else; it does NOT read materials, write spec.md, or run a build. If the user asks anything about an EXISTING course, do NOT use this skill. Always run from the repo root.

2026-07-012

eval-materials-vs-build

https-deeplearning-ai/spec-build-lab

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.

2026-06-182

eval-spec-vs-build

https-deeplearning-ai/spec-build-lab

Scores how faithfully a recorded build run followed its spec.md, in the spec-build-lab. Use this skill ANY time the user asks to evaluate, score, check, judge, assess, or compare a specific build run AGAINST THE SPEC — including phrasings like "evaluate run-02 against the spec", "score run-02 against the spec", "did the build follow the spec", "did run-02 implement the spec", "spec fidelity check on run-NN", "how closely did run-02 follow spec.md", "run a spec-vs-build eval", "evaluate the spec adherence of the latest run", or "/eval-spec-vs-build run-NN". Reads the per-run snapshot evals/<run>/spec.md (NOT the live spec.md) and the contents of builds/<run>/, then writes evals/<run>/spec-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 course materials — that's /eval-materials-vs-build, a different reference and different question.

2026-06-182

extract-build-log

https-deeplearning-ai/spec-build-lab

Extracts the build conversation for a recorded run in the spec-build-lab and writes it to evals/<run>/session-log.md. Use this skill ANY time the user wants to capture, save, snapshot, extract, export, or render the conversation for a specific build run — including phrasings like "extract the build log", "save the conversation for run-02", "snapshot run-02", "export the build log", "render the session log", "log this build", "produce the session log for run-NN", or "/extract-build-log run-NN". Reads the transcript recorded by Claude Code (located via the .session breadcrumb at evals/<run>/.session) and slices it between an opening bookend (the /prepare-build announcement) and a closing bookend (a fuzzy diagram/structure phrase by default, or a user-supplied --until pattern). Idempotent — re-runnable with different bookends. 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 the run — that's /eval-spec-vs-build or /eval-m

2026-06-182

name	prepare-build
description	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.
allowed-tools	["Bash","Read"]

prepare-build

Steps

Verify cwd is a course folder. Confirm all exist relative to cwd: spec.md, builds/, evals/, materials/. If any are missing, refuse with: "Run /prepare-build from inside a course folder — cd courses/<name> first." Stop.

Allocate the next run number.

highest=$(ls -1 builds/ 2>/dev/null | grep -E '^run-[0-9]+$' \
  | sed 's/run-//' | sort -n | tail -1)
next=$(printf "run-%02d" $(( ${highest:-0} + 1 )))

Create the run dirs and snapshot the spec.
```
mkdir -p "builds/$next" "evals/$next"
cp spec.md "evals/$next/spec.md"   # frozen snapshot, read by /eval-spec-vs-build
cp spec.md "builds/$next/spec.md"  # working copy, read by the build agent
```
The eval snapshot at evals/$next/spec.md is judged against later by /eval-spec-vs-build, so the run is judged against the spec it was actually built from even if spec.md is regenerated. The working copy at builds/$next/spec.md makes the build folder self-sufficient — the agent reads ./spec.md from inside the build folder and has no reason to navigate back up to the course folder, where materials/ sits and is forbidden.
Drop the session breadcrumb. Write the absolute path of the current Claude Code transcript JSONL to evals/$next/.session. The path is built from $CLAUDE_PROJECT_DIR and $CLAUDE_CODE_SESSION_ID:
```
slug=$(echo "$CLAUDE_PROJECT_DIR" | sed 's:/:-:g')
transcript="$HOME/.claude/projects/$slug/$CLAUDE_CODE_SESSION_ID.jsonl"
echo "$transcript" > "evals/$next/.session"
```
If $CLAUDE_CODE_SESSION_ID is unset for any reason, fall back to the most recently modified *.jsonl in $HOME/.claude/projects/$slug/ and write that path. The file is per-run, write-once at allocation, never updated.
Announce. Say verbatim, replacing NN: "Run NN — building in builds/run-NN/. Read spec.md (in this folder) and nothing else from the parent course folder. When the build is in a state worth capturing, run /extract-build-log run-NN to slice the conversation into evals/run-NN/session-log.md."
Move into the build folder. cd builds/$next. From here on the agent develops the app inside this folder.

Notes

The breadcrumb at evals/run-NN/.session is a label on the run-NN folder, not coordination state. It's never updated and never read by any other tool — only /extract-build-log consumes it, and only when the user explicitly asks for an extract. Nothing recorder-like is running in the background.
The whole conversation is already being persisted by Claude Code into ~/.claude/projects/<slug>/<session>.jsonl; the breadcrumb just remembers which transcript to slice.

Don't

Don't generate or modify spec.md here — that's /generate-spec.
Don't ask the user for a run number — allocation is automatic.
Don't reuse an existing run-NN folder. Every new build is a new run, even with the same spec.md, so runs and their evals can be compared.
Don't read ../materials/, ../../materials/, or any course materials during the build. The build is a function of spec.md only — that's what the eval pipeline assumes. A PreToolUse hook blocks materials access from inside a build folder; if the hook is bypassed for any reason, /extract-build-log surfaces a contamination warning.