SShortSingh.
TopTechnologyAI & MLStartupsProgrammingScienceBusinessFinanceCrypto & Web3World
Back to feed
Programming

Developer Builds Stateful AI Image-Editing Skill for Kiro Using Google Gemini API

0
·1 views

A developer has released nb2lite-skill-kiro, an open-source project that integrates Google's Gemini gemini-3.1-flash-lite-image model into Kiro, an AI coding assistant, as a reusable skill. The project leverages Google's Interactions API, which maintains visual context server-side across multiple conversational turns, allowing users to iteratively edit an image without re-describing the entire scene each time. It is packaged as a FastMCP server exposing four tools, using the Model Context Protocol (MCP) so any compatible AI client can access the capability without custom integration work. The skill handles practical edge cases such as chaining the correct interaction ID per turn, enforcing aspect ratio consistency, and filtering unsupported thinking-level parameters that the live API rejects. The project was announced on DEV Community and notably used its own image-generation tool to produce the article's cover image.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Log in to join the discussion and vote.

Log in

Related stories

0
ProgrammingDEV Community ·

Two-stage image pipeline offers reliable character consistency without LoRA training

Developers building AI apps that generate the same character across multiple scenes often struggle with face drift when using seeds or prompt-only methods. A two-stage pipeline addresses this by first generating one canonical base image, then using an image-edit model with that base as a reference for every subsequent scene. Unlike seeds, which only reproduce identical inputs, or LoRA fine-tuning, which requires curating dozens of images and running training jobs per character, this approach conditions each new generation on the actual reference pixels. The edit model is instructed only on what should change — pose, setting, lighting — while identity is preserved through the input image itself. This method is described as scalable for production apps where users create characters on demand, and works for non-human subjects such as animals, robots, or animated characters as well.

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

Developer builds 28-rule prompt injection firewall to protect AI agents from MCP threats

Edison Flores of AliceLabs LLC has released L1.9, a prompt injection defense layer designed to scan AI agent inputs before potentially malicious content enters a large language model's context window. The tool targets a known vulnerability in MCP (Model Context Protocol) servers, where tool descriptions can carry hidden instructions to override agent behavior or exfiltrate sensitive data. L1.9 applies 28 detection rules across skill names, descriptions, system prompts, and capability schemas, flagging threats at critical, high, or medium severity levels and quarantining dangerous skills automatically. Each detected finding is mapped to a MITRE ATT&CK technique ID and includes a snippet of the offending text for transparency. Flores claims L1.9 is part of a broader 10-layer security stack, which he says is unmatched by most existing MCP directories that offer no such protections.

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

How to Accurately Convert Bank Statement PDFs to CSV: Methods Compared

Converting bank statement PDFs to CSV is error-prone due to structural issues like merged cells, multi-line transactions, and inconsistent debit/credit column formats that vary by bank. A basic manual copy-paste method works but is slow and unreliable, taking 20–40 minutes per statement with high risk of errors. Developers can use Python's pdfplumber library for a scriptable solution, though it fails on scanned or image-based PDFs and requires bank-specific customization. AI-powered converters offer the most reliable results across different banks and formats, including scanned documents, by interpreting document semantics rather than detecting table boundaries. Regardless of method used, output quality should be verified by checking row counts, amount reconciliation, sign consistency, and the handling of multi-line descriptions.

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

Manual Coolify Setup Guide for Unsupported Ubuntu Versions and Security-Hardened VPS

Coolify's automatic installation script currently supports only Ubuntu 20.04, 22.04, and 24.04 LTS, leaving users on newer versions such as Ubuntu 26.04 without a working one-line install option. A manual setup process is available as an alternative, requiring a VPS with at least 2 CPU cores, 2 GB RAM, and 30 GB of free storage. The walkthrough covers prerequisites including SSH access, CURL, and Docker Engine installation, with steps to remove conflicting packages before adding Docker's official GPG key and repository. Because Coolify's own documentation assumes root account usage, this security-focused guide instead creates a dedicated sudo user with passwordless privileges after disabling root login. The guide is designed to follow on from earlier Ansible playbook configurations, continuing a series aimed at a security-first VPS deployment workflow.

0 comments Read more at DEV Community
Developer Builds Stateful AI Image-Editing Skill for Kiro Using Google Gemini API · ShortSingh