lmammino
- 5 skills
- 0 followers
- 3 days ago last updated
- ▌ One By One · lmamminoWork through a list of items (review comments, findings, report points, open questions) one at a time. For each item, give context, a preview of the change, and an opinion, then reach agreement with the user before applying anything. Use when the user says "one by one", "iteratively", "discuss each point", or asks to go through a list of changes together.
- ▌ Implicit State Machines · lmammino bundleFind implicit state machines (groups of booleans, nullables or strings that together encode one state), check them for bugs with concrete failure scenarios, and triage each one (fix now, open an issue, or leave). Reports first; issues and fixes only on request. Use when the user asks to find implicit state machines, audit state handling, investigate flag soup or boolean explosion, or identify impossible or invalid state combinations.
- ▌ C4 Codebase Architecture · lmamminoHelps an agent inspect a repository and produce C4 architecture documentation. Use this when reverse engineering a codebase, documenting system context, containers, components, or clarifying architecture from code and infrastructure.
- ▌ Reconcile Review · lmamminoTriage and resolve review comments on a GitHub PR. Reads all comments, assesses each one, and presents a resolution table. The user can then approve, modify, or reject resolutions, and the agent applies the chosen changes.
- ▌ Adversarial Review · lmammino bundlePerform an adversarial code review on a GitHub PR. Reads the diff, description, and existing comments, then posts inline review comments with a unique agent prefix. Deduplicates against other agents' comments and replies in-thread when disagreeing.