Use when instrumenting code with runtime logs to test a hypothesis — @dxos/log debug lines captured to app.log (browser), test.log (node…
This publisher has an account here and has not listed a server yet.
Analytics & Monitoring · Security & Testing · Design & Media · Developer Tools & Repos · Productivity & Workflow · Communication & Collaboration · Learning & Documentation
12 agent skills — instructions the agent loads on demand. 12 of 12 are free. Median context cost 3.8k tokens.
Diagnosis loop for hard bugs and regressions.
UI branch of the diagnosing loop. Use when debugging any UI bug — wrong rendering, layout or scroll jumps, flicker, styling, interaction…
DXOS TypeScript authoring conventions. Use when writing or refactoring code — namespace-export packages, internal module imports, class…
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it.
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's…
Compact the current conversation into a handoff prompt the user pastes into another agent.
Use for \"how does X work\", code walkthroughs before changing something, and placement / ownership / layering questions (\"where should…
Use for \"interrogate\", \"adversarial review\", \"multi-model review\", \"challenge this\", \"stress test this code\", \"find blind…
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds.
Apply when writing anything a reader takes as truth: comments, docs, commit bodies, PR descriptions, design notes.
The rest either hold an API key issued by the publisher or ask for nothing.
Listed without a verification tick. Read the listing before installing.