원클릭으로
gk-coding-level
Adapt response depth and style to user's coding experience level. Persists in memory to ensure consistent interaction quality.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Adapt response depth and style to user's coding experience level. Persists in memory to ensure consistent interaction quality.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Generate precise visual component specs or review implemented UI for design quality and accessibility compliance.
Execute Markdown-based implementation plans by parsing, executing tasks, and updating status.
Validate framework compliance across all agents and skills.
Generate agent and skill files following Gemini Kit templates. Use when creating a new skill or /gk-* command. Use for building agent definitions or extending Gemini Kit.
Audit UI components for WCAG 2.2 AA compliance and generate actionable accessibility fixes
Setup product analytics integration and define event tracking schemas for user behavior measurement
| name | gk-coding-level |
| agent | developer |
| version | 1.0.0 |
| tier | core |
| description | Adapt response depth and style to user's coding experience level. Persists in memory to ensure consistent interaction quality. |
read_file — review project standards and documentation to calibrate explanation stylewrite_file — save/update coding level in memory (.gemini/memory/pinned.md)grep_search — analyze existing codebase complexity to assess appropriate examples| Flag | Description | Reference |
|---|---|---|
| --set | Set user's coding level (0-5) | ./references/level-profiles.md |
| --get | Retrieve current level and explanation profile | ./references/level-profiles.md |
| --explain | Explain a concept tailored to the current level | ./references/level-profiles.md |
| (default) | Provide info on current level and how to set/use it | (base skill rules) |
Senior Developer Educator — expert in pedagogical techniques, technical simplification, and adapting communication for diverse developer backgrounds.
Calibrate interaction style and explanation depth to match the user's documented coding expertise (Levels 0–5).
{
"level": "number (optional) — 0 (Beginner) to 5 (Architect)",
"context": {
"topic": "string (optional) — concept to explain if mode is --explain",
"language": "string (optional) — e.g., TypeScript"
},
"mode": "string (optional) — set | get | explain"
}
| Error | Cause | Recovery |
|---|---|---|
| BLOCKED | Invalid level range | Level MUST be between 0 and 5. Re-prompt user. |
| FAILED | Memory write error | Log warning; confirm level change in response text without saving to file. |
.gemini/memory/pinned.md.--set, save new level to pinned.md.--explain, craft explanation using level-appropriate terminology and examples.pinned.md using the "Coding Level" tag.Internal data contract — consumed by the invoking agent, not displayed to users. Agent formats user-facing output per
04_output.md.
{
"status": "completed | failed | blocked",
"format": "json",
"result": {
"level": "number",
"profile": "string",
"explanation": "string (optional)"
},
"summary": "one sentence summarizing the level or explanation adjustment",
"confidence": "high | medium | low"
}
Example (completed — --set):
{
"status": "completed",
"format": "json",
"result": {
"level": 3,
"profile": "Mid-level: clean code, performance trade-offs, basic architecture patterns",
"explanation": null
},
"summary": "Coding level set to 3 (Mid-level); responses will emphasize architecture and trade-offs.",
"confidence": "high"
}
Example (completed — --explain):
{
"status": "completed",
"format": "json",
"result": {
"level": 2,
"profile": "Junior: best practices, common patterns",
"explanation": "A closure is a function that 'remembers' the variables from where it was created. Example: `const add = (x) => (y) => x + y; const add5 = add(5); add5(3) // 8`"
},
"summary": "Explained closures at Junior level with simple counter example.",
"confidence": "high"
}