teach-mode
Learning-mentor mode with three sub-modes — Code Mentor (Socratic pair-programming, student writes all code), Explain Mode (deep verified concept explanation…
Skill by davidnbr
Chalk Labs
Need help deploying teach-mode?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/davidnbr-teach-mode
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/teach-mode
What's inside
- Skill name
teach-mode- Description
- Learning-mentor mode with three sub-modes — Code Mentor (Socratic pair-programming, student writes all code), Explain Mode (deep verified concept explanation for any domain, no assumed knowledge), Scenario Mode (retrieval-practice quiz loop — student attempts first, then scored against verified ground truth). Every non-trivial technical claim in any sub-mode is checked against a primary source before being stated. Triggers on "teach me", "teach mode", "learning mode", "tutor mode", "mentor mode", "I want to learn", "explain mode", "explain this" (concept, not code), "quiz me", "scenario mode", "give me scenarios", "practice mode", "vibe code", "vibe-code", "vibe coding", "learn while building".
- License
- unknown
- Instructions
- 291 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from davidnbr/.claude
- 0.547score
local-worker
davidnbr
Delegate edit/implementation work to a local LLM (Ollama-backed) running as a separate claude or opencode CLI process, while this session stays the…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
bmad-verified-tackle
davidnbr
End-to-end verified delivery for BMAD projects: runs the bmad-tackle-story dev→review→resolve loop on the given story id/range, then the code-enforced…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
complete-pr-review
davidnbr
Run a grounded, senior-engineer PR review on a branch — verify EVERY claim against real source (no assumptions), trace the changed logic like a state-machine…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
bmad-tackle-story
davidnbr
Tackle an existing BMAD story (or story range like aks-1-3..aks-1-5) end-to-end by orchestrating a dev→review→resolve loop: a coder subagent runs…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
bmad-resolve-review
davidnbr
Verify, address, and reply to PR/code-review findings from a senior-engineer perspective.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
verified-tackle
davidnbr
End-to-end verified delivery for non-BMAD projects (openspec/ or no spec tooling): plan-verify, implement, then the code-enforced Workflow verification loop…
SkillBFreshness: B★ 1Claude Code +9 - 0.497score
pr-reviewer
davidnbr
Comprehensive code review skill for TypeScript, JavaScript, Python, Swift, Kotlin, Go.
SkillCFreshness: C★ 1Claude Code +9 - 0.489score
recall
davidnbr
Spaced repetition learning system for developers using multiple AI tools.
SkillCFreshness: C★ 1Claude Code +9 - 0.402score
verified-answer
davidnbr
Use this skill whenever the user asks a technical question where a wrong answer could cause real harm — broken infrastructure, failed deployments, production…
SkillDFreshness: D★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 5, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/davidnbr/.claude
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from davidnbr
- 0.547score
local-worker
davidnbr
Delegate edit/implementation work to a local LLM (Ollama-backed) running as a separate claude or opencode CLI process, while this session stays the…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
bmad-verified-tackle
davidnbr
End-to-end verified delivery for BMAD projects: runs the bmad-tackle-story dev→review→resolve loop on the given story id/range, then the code-enforced…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
complete-pr-review
davidnbr
Run a grounded, senior-engineer PR review on a branch — verify EVERY claim against real source (no assumptions), trace the changed logic like a state-machine…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
bmad-tackle-story
davidnbr
Tackle an existing BMAD story (or story range like aks-1-3..aks-1-5) end-to-end by orchestrating a dev→review→resolve loop: a coder subagent runs…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
bmad-resolve-review
davidnbr
Verify, address, and reply to PR/code-review findings from a senior-engineer perspective.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
verified-tackle
davidnbr
End-to-end verified delivery for non-BMAD projects (openspec/ or no spec tooling): plan-verify, implement, then the code-enforced Workflow verification loop…
SkillBFreshness: B★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get teach-mode running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
teach-mode skill. Agent Mart. https://agentmart.dev/skills/davidnbr-teach-mode (last updated 2026-10-24)