⚖️
AI EngineeringShell

Approach Evaluation

by Fr-e-d

Approach Evaluation is an AI Engineering skill for Claude Code, published by Fr-e-d in GAAI-framework.

161 stars27 forkson Fr-e-d/GAAI-frameworkAdded 2026/09/08Repository updated 2026/09/04
agentic-codingai-agentsai-codingai-developer-toolsai-governanceai-memory-systemautonomous-agentsclaude-codecodex-clicontext-engineeringcursordevtoolsgemini-cliopencodevibe-codingwindsurf
Install in seconds
Install Approach Evaluation
Copy Approach Evaluation into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/digipulse-engineering/GAAI-framework/tree/main/.gaai/core/skills/cross/approach-evaluation ~/.claude/skills/approach-evaluation

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/digipulse-engineering/GAAI-framework.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
.gaai/core/skills/cross/approach-evaluation/SKILL.md in Fr-e-d/GAAI-framework
Installs to
~/.claude/skills/approach-evaluation
Collection
One of 25 skills cataloged from this repository
Category
AI Engineering3670 skills

What Approach Evaluation does

Approach Evaluation researches viable options for a technical or architectural decision and compares them against project constraints. Use it when multiple approaches exist and you need a factual, structured comparison without making the decision.

Approach Evaluation is cataloged under AI Engineering on DirSkills. Approach Evaluation comes from a repository tagged agentic-coding, ai-agents, ai-coding, ai-developer-tools and ai-governance.

Documentation

README

Approach Evaluation

Purpose / When to Activate

Activate when the invoking agent identifies a technical or architectural decision point where:

  • Multiple viable implementation approaches exist and the best choice is non-obvious
  • A technology, library, or service is being introduced for the first time in the project
  • No established convention exists in conventions.md for the problem domain
  • The problem touches a domain with well-known industry standards that should be considered
  • A prior approach failed or showed limitations (post-mortem driven re-evaluation)

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Approach Evaluation

  • What else does Fr-e-d publish alongside Approach Evaluation?

    Approach Evaluation is one of 25 skills that DirSkills catalogs from Fr-e-d/GAAI-framework, the repository it ships in. Its siblings there include Abort-Safe Handler, Ambiguity Detector and Architecture Extract. Each one is a separate skill with its own page in this directory, installs the same way Approach Evaluation does, and is maintained by Fr-e-d in that same repository. The rest of the collection is listed on the Fr-e-d/GAAI-framework page.

  • How does Approach Evaluation compare to other AI Engineering skills?

    Approach Evaluation ranks #3408 by stars among the 3670 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Approach Evaluation against them. Open each page to compare what they document and how they install.

More from Fr-e-d/GAAI-framework

Approach Evaluation is one of 25 skills cataloged on DirSkills from Fr-e-d/GAAI-framework.

See all 25 skills
🛑
1h ago

Abort-Safe Handler

Abort-Safe Handler decides whether `/gaai:bootstrap` enters the Q&A loop or skips it. It returns a unified abort-safe result with telemetry and prevents partial state when the user skips or aborts.
Automation
16127
🔎
1h ago

Ambiguity Detector

Ambiguity Detector scores project ambiguity from surface scans, optional open-question synthesis entries, and optional AST signals. It produces structured ambiguity_feed entries for the Q&A stage without making LLM calls.
AI Engineering
16127
🏗️
1h ago

Architecture Extract

Architecture Extract turns a scanned codebase into a concise view of module boundaries, data flows, service relationships, and the architectural pattern. Use it during bootstrap before memory ingestion.
AI Engineering
16127
🧠
1h ago

Bootstrap LLM Synthesis

Bootstrap LLM Synthesis constructs a prompt from project scans, optional tree-sitter context, and Q&A answers, then calls an LLM to produce validated memory entries. Use it in Stage 3 of the /gaai:bootstrap pipeline when raw project signals need to be distilled into structured, traceable notes.
AI Engineering
16127
🗂️
1h ago

Build Agents Index

Build Agents Index scans agent and sub-agent frontmatter plus specialists.registry.yaml, then writes a derived agents-index.yaml. Use it after adding, changing, or removing agent, sub-agent, or specialist entries.
Automation
16127
🗂️
1h ago

Build Skills Index

Build Skills Index scans SKILL.md frontmatter in core and project skill folders and regenerates separate YAML indices. Use it when skills are added, changed, removed, or the index may be stale.
Automation
16127