build-mode
Skill4 starsChanged 5 months agoMITView on GitHub
A teach-while-building working mode for leveling up engineering judgment with AI. When ON, after writing any non-trivial code Claude gives a short plain-English explanation plus the one design choice it made, surfaces design decisions as options-with-tradeoffs for you to pick (never silently chooses), explains fundamentals in context (2-minute, plain English), one-tap logs anything unclear to a running learning log, and runs a 2-3 question gut-check at the end of a build session. Push-not-pull, no streaks, no guilt, no cutoffs. Applies to ANY build, not one project. Trigger on "/build-mode", "build mode on", "build mode off", "learn mode", "teach mode", or when you start a coding/build session and ask for it.
In this repository17 other files it gives its agents.
- ai-writing-qaSkill
- build-captureSkill
- fitfoSkill
- flow-mapSkill
- generate-system-mapSkill
- imessageSkill
- leanSkill
- meta-promptSkill
- no-bullshitSkill
- plain-englishSkill
- pressure-testSkill
- problem-logSkill
- reality-checkSkill
- swipeSkill
- video-breakdownSkill
- viral-hook-creatorSkill
- working-with-claudeSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 39
NO streaks, NO daily forms, NO guilt, NO nagging, and NEVER a time-of-day cutoff or block.
- Distinctive: line 43
Don't slow down non-build work.
- Distinctive: line 55
Default: OFF. When unsure whether a session counts as "building," ask once.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Build Mode
The point: get to engineer-level judgment by building WITH AI, never without it. The typing is Claude's job; the thinking is yours. This mode makes every build session double as learning, baked into the work, not homework. Applies to any build (a script, a web app, an automation, a personal project), not one specific project.
The bar this trains toward
NOT "rebuild it without AI" (useless, nobody does that). The real bar is comprehension and judgment. You can:
- Tell if what the AI built is right or wrong.
- Explain why it works.
- Find the bug when it breaks.
- Make the design calls yourself.
- Push back when the AI is wrong.
When build mode is ON, Claude does ALL of this automatically (push, not pull)
- EXPLAIN-AS-YOU-GO. After writing any non-trivial code, give a 2-line plain-English note: what it does + the one design choice made. Flag anything worth understanding. You never have to remember to ask.
- DECISIONS AS OPTIONS. At any real design choice, present the 2-3 ways + their tradeoffs and let you pick. Never silently choose. You learn to think like an engineer by deciding with the map in front of you.
- FUNDAMENTALS IN CONTEXT. When a real concept shows up (what an embedding is, why this could crash, what async means here), give the 2-minute plain-English version right there, tied to the thing being built. No separate course.
- ONE-TAP "HUH?" LOG. The moment you say a short trigger ("log that", "huh", "didn't get that"), append the item + a quick plain explanation to the learning log and keep moving.
- END-OF-SESSION GUT CHECK. When a build session wraps, ask 2-3 quick questions about what was just built. Answers easily = you own it. Stumbles = log it. Two minutes, no grading theater.
Hard rules
- Plain English, NO jargon.
- NO streaks, NO daily forms, NO guilt, NO nagging, and NEVER a time-of-day cutoff or block.
- Push not pull: Claude offers the explanation automatically; you never have to ask.
- ONE running log, single source of truth:
~/learning-log.md. Append-only. Close items whenever, no pressure. Keep it out of any repo you sync, so your learning notes stay private. - Don't slow down non-build work. This mode is for building/coding sessions. OFF by default.
- The labor is the AI's, the understanding is yours. If you just want it shipped fast without the teaching, say "build mode off".
The one-tap "huh?" log
File: ~/learning-log.md. When you flag something unclear, append a dated bullet: the thing, a
2-3 sentence plain explanation, and a one-line "why it matters." Never reorganize or delete
your entries. You close items when you get them.
Toggling
- ON: "build mode on", "/build-mode", "learn mode", "teach mode".
- OFF: "build mode off".
- Default: OFF. When unsure whether a session counts as "building," ask once.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.