sg-flw

Name: sg-flw
Author: ezefranca

by ezefranca

Pending

0stars

0forks

HTML

Added 5/29/2026

View on GitHub Download ZIP

AI Agents

Installation

# Add to your Claude Code skills
git clone https://github.com/ezefranca/sg-flw

Getting Started

Guides for using ai agents skills like sg-flw.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

README.md

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

ECC

by affaan-m

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

196,387

scholar-sidekick-skills show-html

SG-FLW Web Tool

SG-FLW is an academic measurement framework for coding and planning evidence quality in serious games, games, and gamified interventions addressing food loss and waste. The tool profiles five dimensions:

B: Baseline measurement quality
K: Knowledge and attitudinal assessment
D: Direct behavior measurement
E: Environmental conversion
L: Persistence / longitudinal measurement

The tool evaluates measurement-chain strength, not intervention quality, game quality, or causal effectiveness. A low SG-FLW profile means that evidence is missing or weakly reported; it does not mean the intervention failed.

Suggested Citation

Santos, E.; Moreira, M.; Duque, D.; Sevivas, C.; Carvalho, V. (2026). A Measurement Framework for Serious Games Addressing Food Loss and Waste (SG-FLW). Published in the IEEE International Conference on Serious Games and Applications for Health (SeGAH 2026).

Supporting review:

Santos, E.; Sevivas, C.; Carvalho, V. (2025). Managing Food Waste Through Gamification and Serious Games: A Systematic Literature Review. Information, 16(3), 246. https://doi.org/10.3390/info16030246

Machine-Readable Metadata

llms.txt: AI-oriented summary, scope limits, keywords, and citation guidance.
llm.txt: compatibility copy for tools that look for the singular filename.
CITATION.cff: citation metadata for scholarly and software repositories.
codemeta.json: software/research-tool metadata.
skills.sh.json: skills.sh repository-page grouping for the classifier skill.
sitemap.xml and robots.txt: crawler discovery and access policy.

SG-FLW Classifier Skill

The repository hosts a Codex / SKILL.md-compatible classifier skill at skills/sg-flw-classifier/. It helps AI agents classify papers, protocols, and boundary cases in serious games and food waste research under SG-FLW without over-crediting awareness outcomes, in-game outputs, or modeled environmental indicators as measured food-waste reduction evidence.

The skill includes separate reference files for SG-FLW foundations, the detailed coding protocol, the published reference corpus, a source-linked corpus knowledge base, and prospective study/telemetry planning. Agents should read those files before assigning B/K/D/E/L scores.

Install with the skills CLI:

npx skills add https://github.com/ezefranca/sg-flw --skill sg-flw-classifier

Install globally for Codex:

npx skills add https://github.com/ezefranca/sg-flw \
  --skill sg-flw-classifier \
  -a codex \
  -g \
  -y

Installation instructions are available on skill.html.

The skill page documents installation for Codex/OpenAI agent setups, Claude Code, Cursor, GitHub Copilot, upload-based clients, and custom SKILL.md-compatible directories. A ZIP package is available at downloads/sg-flw-classifier-skill.zip for clients that support custom skill upload.