gap-prompting

gap-prompting is a Prompt design & optimisation skill for AI agents, published by justinlietz93 in the Perfect_Prompts repository on GitHub. Skillspace rates gap-prompting D (66/100) and it passed the safety scan; the rating is based on static analysis only.

Guided Autonomy Prompting (GAP) — a meta-methodology for AI-assisted software architecture. This skill operates in TWO modes. MODE A (Respond): When the user sends a GAP-structured prompt (collaborative framing + theoretical/system constraints + logical bridge + open architectural question), Claude activates deep architectural reasoning — analyzing the full codebase context before writing any code, treating named constraints as inviolable axioms, and designing the architecture before implementing it. MODE B (Craft): When the user asks for help writing a prompt for an AI coding agent, or is struggling to communicate constraints to an AI, or says things like "help me prompt this", "how should I frame this for Claude Code", "write a GAP prompt", "I need to get the agent to respect my architecture", "the AI keeps breaking my design pattern", or "how do I tell the AI about my constraints without micromanaging" — Claude helps them construct a 4-part GAP prompt using the appropriate domain…

Grade
D
Quality
66 / 100
Safety
Passed
GitHub stars
23

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Our review

Architecture
84 / 100
Maturity
Structured: ships references or scripts
Security scan
No issues found
License
MIT
Adoption
Adopted by 0 other repositories, in 0 collections

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.