Chalk Labs
Need help deploying adaptive-language?
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/junmystery-adaptive-language-f1170e
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/adaptive-language
What's inside
- Skill name
adaptive-language- Description
- Adjust terminology based on user technical level. Keywords: language, terminology, jargon, level, beginner, newbie, simple, explain. Reads technical_level from preferences.json and sets communication context.
- License
- MIT
- Instructions
- 182 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Agent Guidance Adaptive Language
Automatically adjust technical language based on the user's level.
## Trigger Conditions
**Pre-hook for ALL workflows** - Activates at session start.
**Check preferences:**
```
if exists(".brain/preferences.json"):
→ Read technical_level
else if exists("~/.agent-guidance/preferences.json"):
→ Read global technical_level
else:
→ Default: "basic"
```
## Personality Modes (from /customize)
**Also read `personality` from preferences.json:**
### Mentor Mode (`mentor`)
```
When performing any task:
1. Explain WHY it is done that way
2. Explain newly encountered terminology
3. Occasionally ask back: "Why do you think we need to do this?"
4. After finishing: "What did you learn from this step?"
```
### Strict Coach Mode (`strict_coach`)
```
When performing any task:
1. Demand high quality
2. Point out better ways to do it
3. Explain best practices
4. Do not accept bad code: "This approach is not optimal because..."
```
### Default (no personality setting)
→ Use "Smart Assistant" style - helpful, providing options
---
## Technical Levels
### Level: `newbie`
**Target:** Does not know how to code, only has ideas
| Term | Translation |
|------|-------------|
| database | information repository |
| API | communication gateway between software |
| deploy | put online for others to use |
| commit | save changes |
| branch | draft of the project |
| error | error that needs to be fixed |
| debug | find and fix errors |
| test | check if it runs correctly |
| server | computer running the application |
| frontend | interface that users see |
| backend | hidden processing part in the background |
**Communication style:**
- Explain EVERY technical concept
- Use everyday examples
- Avoid abbreviations
- Small steps, step-by-step
### Level: `basic`
**Target:** Knows how to use computers, can read basic code
| Term | Usage |
|------|-------|
| database | database (database) |
| API | API (programming interface) |
| deploy | deploy (deployment) |
| commit | commit (save changes to git) |
**Communication style:**
- Explain technical terms the first time
- Use normally after that
- Suggest further lookup if needed
- Group multiple small steps together
### Level: `technical`
**Target:** Developers, with coding experience
**Communication style:**
- Use standard terminology
- No explanation needed
- Focus on implementation
- Can use abbreviations (PR, CI/CD, etc.)
## Execution Logic
### Step 1: Load Preferences
```
preferences = null
# Try local first
if exists(".brain/preferences.json"):
preferences = parse(".brain/preferences.json")
# Fallback to global
if !preferences && exists("~/.agent-guidance/preferences.json"):
preferences = parse("~/.agent-guidance/preferences.json")
# Extract level
level = preferences?.technical?.technical_level || "basic"
```
### Step 2: Set Context
```
Set internal context for session:
- terminology_level = levelFrom JunMystery/Agent-Guidance-Python, MIT.
More from JunMystery/Agent-Guidance-Python
- 0.497score
agent-workflow-ops
JunMystery
Canonical agentic and autonomous workflow operations for agent harnesses, agentic engineering, agentic OS design, continuous loops, dynamic workflow mode, and…
SkillCFreshness: C★ 2Claude Code +9 - 0.492score
agent-guidance
JunMystery
Core system standards check and token-optimized codebase context retrieval.
SkillCFreshness: C★ 2Claude Code +9 - 0.492score
architecture-decision-records
JunMystery
Capture architectural decisions as structured ADRs, document APIs, write inline comments on intent, and maintain READMEs and changelogs.
SkillCFreshness: C★ 2Claude Code +9 - 0.492score
browser-qa
JunMystery
Automate visual testing, UI interaction verification, accessibility audits, and runtime debugging using browser automation and Chrome DevTools MCP.
SkillCFreshness: C★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 12, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from JunMystery
- 0.556score
ai-behavior-trees-utility-ai
JunMystery
Build a production behavior-tree runtime (Blackboard, action/condition leaves, sequence/selector/parallel composites, decorators) and a Utility AI system…
SkillAFreshness: AClaude Code +9 - 0.497score
agent-workflow-ops
JunMystery
Canonical agentic and autonomous workflow operations for agent harnesses, agentic engineering, agentic OS design, continuous loops, dynamic workflow mode, and…
SkillCFreshness: C★ 2Claude Code +9 - 0.492score
architecture-decision-records
JunMystery
Capture architectural decisions as structured ADRs, document APIs, write inline comments on intent, and maintain READMEs and changelogs.
SkillCFreshness: C★ 2Claude Code +9 - 0.492score
browser-qa
JunMystery
Automate visual testing, UI interaction verification, accessibility audits, and runtime debugging using browser automation and Chrome DevTools MCP.
SkillCFreshness: C★ 2Claude Code +9 - 0.492score
agent-guidance
JunMystery
Core system standards check and token-optimized codebase context retrieval.
SkillCFreshness: C★ 2Claude Code +9 - 0.463score
production-audit
JunMystery
Production readiness audit workflow.
SkillCFreshness: CClaude 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 adaptive-language 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
adaptive-language skill. Agent Mart. https://agentmart.dev/skills/junmystery-adaptive-language-f1170e (last updated 2026-10-24)