Skip to content
store
review-delta

Self-hosted alternatives to review-delta

5 self-hosted AI Skills apps to use instead, best rated first.

Top picks

  1. C

    claude-to-deerflow

    Launch

    claude-to-deerflow is an agent skill that lets an assistant send messages and questions to a running DeerFlow instance through its HTTP API. DeerFlow is an AI agent platform built on LangGraph that orchestrates sub-agents for research, code

    Self-hosted

  2. O

    open-notebook

    Launch

    open-notebook is an agent skill for organising research with Open Notebook, a self-hosted alternative to NotebookLM. It arranges sources, notes and AI conversations into research notebooks. Sources can be PDFs, web pages, audio, video and O

    Self-hosted

  3. R

    Reactive Resume

    Launch

    Reactive Resume is a free and open-source resume builder for writing resumes and cover letters, checking the work, and tracking job applications. You create a free account, import an existing resume or start from scratch, and see the finish

    Open sourceSelf-hosted

  4. S

    self-hosted-funnel-launch

    Launch

    Self-hosted funnel launch is an agent skill that takes a funnel from an empty install to published on infrastructure you control, using the Autonnel funnel builder, which is licensed Apache-2.0. The result covers a landing page, checkout, a

    Self-hosted

  5. G

    get-convex/convex-backend

    Launch

    Convex is an open-source reactive database for web app developers. It combines a database, a place to write server functions in pure TypeScript, and client libraries that keep the app's data live, so screens update as the data changes. Beca

    Self-hosted

About review-delta

R

review-delta

Review only changes since last commit using impact analysis

review-delta is an agent skill from the tirth8205 code-review-graph project, listed on skills.sh. It reviews only the code that has changed since the last commit, together with the code those changes can affect, which the skill calls the blast radius. The steps are set out in order. The agent first asks for a minimal context, and if the graph is not ready it builds or updates it. It then detects changes against the previous commit, HEAD~1, scoring each changed function by risk and listing test gaps and affected flows. If a file is named, the skill limits the check to that file. For the changed areas it fetches source snippets and review guidance, which flags untested functions, wide blast radius and inheritance changes. Each untested high-risk function is confirmed by querying the graph for its tests. The report gives a one-line summary, a risk level of low, medium or high, the issues found in bugs, missing tests and style, the blast radius in files and functions, and recommendations. The skill avoids loading whole files unless a snippet is not enough, which keeps the review token-efficient. It suits developers who want a focused review of a change before it is committed.

View review-deltaAll AI Skills apps
Price
Free
Made by
tirth8205
Category
AI Skills
Website
github.com/tirth8205/code-review-graph/review-delta