TacoSkill LABTacoSkill LAB

The full-lifecycle AI skills platform.

Product

  • SkillHub
  • Playground
  • Skill Create
  • SkillKit

Resources

  • Privacy
  • Terms
  • About

Platforms

  • Claude Code
  • Cursor
  • Codex CLI
  • Gemini CLI
  • OpenCode

© 2026 TacoSkill LAB. All rights reserved.

TacoSkill LAB
TacoSkill LAB
HomeSkillHubCreatePlaygroundSkillKit
  1. Home
  2. /
  3. SkillHub
  4. /
  5. subagent-prompt-construction
Improve

subagent-prompt-construction

6.1

by majiayu000

54Favorites
80Upvotes
0Downvotes

Systematic methodology for constructing compact (<150 lines), expressive, Claude Code-integrated subagent prompts using lambda contracts and symbolic logic. Use when creating new specialized subagents for Claude Code with agent composition, MCP tool integration, or skill references. Validated with phase-planner-executor (V_instance=0.895).

prompt engineering

6.1

Rating

0

Installs

AI & LLM

Category

Quick Review

Well-structured skill for constructing Claude Code subagent prompts with strong documentation architecture. The lambda contract notation provides clear input/output specifications, and the artifact organization (templates, examples, reference, scripts) demonstrates excellent separation of concerns. Task knowledge is comprehensive with explicit validation criteria (≤150 lines, integration ≥0.50, clarity ≥0.80) and quantified validation metrics (V_instance=0.895). The description clearly indicates when to use the skill (orchestration needs, MCP integration) and references specific file locations for each component. Novelty is moderate-to-good: while prompt engineering exists broadly, the systematic methodology combining symbolic logic notation, strict compactness constraints, and Claude Code-specific integration patterns (agent composition, MCP tools, skill references) provides meaningful structure that would be token-intensive for a CLI agent to replicate from scratch. The validated metrics and transferability score (95%) add credibility. Minor limitation: the symbolic logic notation may have a learning curve, but the referenced templates and examples mitigate this effectively.

LLM Signals

Description coverage8
Task knowledge9
Structure9
Novelty7

GitHub Signals

49
7
1
1
Last commit 0 days ago

Publisher

majiayu000

majiayu000

Skill Author

Related Skills

prompt-engineermcp-developerrag-architect

Loading SKILL.md…

Try onlineView on GitHub

Publisher

majiayu000 avatar
majiayu000

Skill Author

Related Skills

prompt-engineer

Jeffallan

7.0

mcp-developer

Jeffallan

6.4

rag-architect

Jeffallan

7.0

fine-tuning-expert

Jeffallan

6.4
Try online