agentsclimarketplace

Know code teach

Skill chtnnh/know-code/skills/know-code-teach

k(no)w-code - your agents dont push until you know exactly whats changed

Install
npx -y skills add chtnnh/know-code --skill know-code-teach

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 12 days oldThe repository was created 12 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Explain architecture, decisions, and trade-offs to the human BEFORE making code edits and while coding. Use at session start, before any non-trivial implementation or refactor, when the user asks what is being built or why, after a know-code gate deny (before the quiz), or when the human is unfamiliar with the area. Does not open the gate.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.5 KB, 505 tokens by cl100k_base, as published. Nobody here has run it

know-code-teach

Teach the human what is changing and why — before you edit files, then keep teaching in small increments while you code. This skill never writes a know-code gate receipt. Verification is know-code.

When to run (required)

Run this skill before you create or modify project files for any non-trivial task:

  • New features, refactors, bug fixes that touch more than a one-liner
  • Session start on an unfamiliar codebase / area
  • After a know-code gate deny (before know-code quiz)
  • After a quiz failure (re-teach weak spots)
  • User asks “what are you doing?”, “why this approach?”, or “catch me up”

Skip only if the human explicitly says so (“skip teach”, “just do it”, “I know this”).

Playbook

Read references/explain-playbook.md and follow it. Defaults:

  1. Intent — one sentence: problem + proposed outcome
  2. Touch map — which areas of the codebase will change (paths/modules)
  3. Approach — chosen design in plain language
  4. Trade-offs — 1–3 alternatives and why not
  5. Risks — what could go wrong; what you will verify
  6. Checkpoint — ask if the human wants a different approach before editing

While coding, keep explanations incremental: after meaningful chunks, narrate what landed and what is next. No lectures. No wall of text.

Pairing with know-code

SkillRole
know-code-teachBuild understanding before/during work
know-codeVerify understanding before commit/push/PR

Required order: teach → edit → (teach deltas) → know-code quiz → know-code commit / push.

After a gate deny: teach first, then quiz, unless the human explicitly skips teaching.

Hard rules

  • Do not start non-trivial edits until you have taught (or the human skipped)
  • Do not run know-code pass
  • Do not quiz here (hand off to know-code)
  • Prefer questions that invite the human to steer (“prefer A or B?”) over monologue
  • If the human is already expert and asks to skip teaching, comply and stay brief

What ships with it: 1 file

1.6 KB alongside SKILL.md

references/

Gives 0 of the 12 instructions most learn study skills give in 505 tokens

Counted across 546 of the 573 authors here whose files we hold, read 2026-08-07

  • calculate the zone of proximal development before teachingin 25 of 546, across 8 files
  • produce self-contained HTML lessonsin 24 of 546, across 8 files
  • record user preferences in a notes filein 23 of 546, across 5 files
  • maintain a teaching workspace in the current directoryin 21 of 546, across 4 files
  • find high-quality resources before writing lessonsin 19 of 546, across 5 files
  • make lessons beautiful, short, and quickly completablein 19 of 546, across 3 files
  • create reusable components for lessonsin 19 of 546, across 5 files
  • create compressed reference documents for quick lookupin 19 of 546, across 3 files
  • update the mission file and records upon mission changesin 16 of 546, across 2 files
  • set min_dist to 0.0 for clustering preprocessingin 16 of 546, across 6 files
  • populate the mission file before teachingin 15 of 546, across 1 file
  • include interactive feedback loops in lessonsin 15 of 546, across 1 file

Said here and by no other author read

  • teach the human before editing files
  • keep explanations incremental while coding
  • read the explain playbook and follow it
  • state the intent in one sentence
  • provide a touch map of changing areas
  • explain the chosen approach in plain language

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.