A process for comparing several possible answers to a design or decision problem through different expert viewpoints. It has multiple reviewers examine the options and then selects and combines the strongest ideas.
A search tool for recalling facts, decisions, and past solutions stored in a project's engineering memory. It searches by meaning and keywords and returns matching sources with confidence information.
A deep research workflow that breaks a broad question into several viewpoints, gathers sources, checks for missing evidence, and combines the findings into a grounded report. The report includes source material and records what each research round added.
A structured review of code changes that looks for correctness, security, missing requirements, and edge cases. It can review everything changed in the current branch or a selected part of the codebase.
A pipeline that turns instructional videos into structured notes using both their visuals and audio. It is intended for videos such as lectures, tutorials, and courses where slides, diagrams, prompts, or code appear on screen.
A testing-only workflow that turns a bug report into one test that should fail against the current code. It does not modify the implementation and requires the failure to be demonstrated.
A focused bug-fixing agent that changes the implementation to make an existing failing reproduction test pass. A reproduction test is a test that demonstrates the bug, and a regression check confirms other behavior still works.
A method for locating the cause of a bug before changing code, using a minimal reproduction and step-by-step narrowing of the failing input and code path.
A way to turn agreed design decisions into a formal software design document. The document gives coding agents or other implementers goals, decisions, rules, dependencies, non-goals, and open questions.
An adversarial design discussion that challenges a plan before it becomes an implementation contract. It separates facts that can be checked in the code from technical choices and decisions that require the owner's judgment.
A structured root-cause investigation method for software bugs. It moves from history and reproduction through tested hypotheses, a focused fix, verification, and a report.
A lightweight decision log that appends settled decisions and references to a repository file. It records why a decision was made without copying the full source document.
A post-run review process for a batch of coding tasks merged into the main branch. It collects repeated failures and turns them into proposed checks, review standards, or task templates.
A Semgrep-based static security scanner that checks source code against known rules and produces a structured report. It uses fixed rules rather than an AI model.
Review rendered UI screenshots for hierarchy, spacing, readability, states, consistency, and visual slop.
★not rated 43▲
+1 5d agoA24 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: