matrixorigin

Memoria REST API endpoints, request/response formats, auth, rate limits. Use when calling or implementing API endpoints.

Use Memoria as OpenClaw's durable memory slot. Triggers: "remember this", "save to memory", "what do you remember", "continue from last time", "forget this", "correct memory", "take a snapshot", "rollback memory", "branch memory", "merge memory", "use…

Install Memoria and configure MCP for AI tools (Kiro, Cursor, Claude Code, Codex, Gemini CLI). Decision tree for Cloud vs self-hosted mode, database, embedding provider. Use when helping users set up Memoria.

Deploy Memoria with Docker Compose or Kubernetes. Environment variables, multi-instance setup, security. Use when deploying or configuring Memoria.

Memoria codebase structure, workspace layout, key traits, database tables, config patterns, and testing conventions. Use when navigating or modifying Memoria code.

Use Memoria for durable user/project memory in OpenClaw. Triggers: "remember this", "save to memory", "what do you remember", "forget this", "correct memory", "update memory", "use memoria".

Recover from accidental memory loss with snapshots and rollback. Triggers: "restore memory", "rollback memory", "undo deleted memory", "recover deleted memory", "take a memory snapshot".

Run embedding on-device with ONNX Runtime. Build from source, model selection, offline mode. Use when setting up local embedding without an API key.

Audit Astra edge/cloud synchronization using local journals/checkpoints and current MatrixOne projection tables. Use for event ingestion gaps, restore/checkpoint mismatch, Work projection drift, and skill/learning visibility issues.

Verify completed Astra work with evidence. Uses canonical Work criteria and checks when present; otherwise derives targeted gates from the diff and changed behavior.

Analyze a current or past Astra session from structured runtime observation, with journal digests and debug artifacts as targeted forensic fallbacks. Use for stalls, tool failures, compaction, token/context pressure, guard escalation, and error cascades.

Signal-driven code review of uncommitted changes, branch diffs, commits, or PR diffs. Findings first; focus on bugs, regressions, data loss, security, API breakage, and missing tests.

Signal-driven code review of uncommitted changes, branch diffs, commits, or PR diffs. Findings first; focus on bugs, regressions, data loss, security, API breakage, and missing tests.

Programmatic Astra engineering workflow for non-trivial code changes. Use when touching Rust crates under crates/, runtime/server lifecycle, turn/tool/prompt behavior, skills, delegation, session journal, MatrixOne state, CLI, deployment scripts, or when…

Analyze and reduce Astra prompt/context bloat across system prompt, tool surface, history, skills, and budget pressure using session digest plus prompt checkpoints.

Test-quality review skill for unhappy paths, real assertions, DB/E2E coverage, lifecycle edges, and production-grade verification gaps.

Develop and validate MatrixOne kernel changes with design-first gates, first-principles invariants, risk-proportional evidence, deterministic UT/BVT, and repository-specific CGo, operator/pipeline, planner, and index-plugin workflows. Use for MatrixOne…

MatrixOne database kernel development - first-principles, performance-aware change design; controlled local CGo build/test setup; complete test matrices; counterexample-driven white-box/black-box validation; hung-test diagnosis; GPU builds (MO_CL_CUDA=1 /…

Review MatrixOne changes before push or as an external PR reviewer using one complete change map, design-first gates, risk-routed first-principles analysis, functional/unhappy-path closure, and reusable validation evidence. Use for pre-push review, PR/deep…

Systematic MatrixOne kind/bug lifecycle triage — intake normalization with `needs-triage`, conservative promotion to active severity (`severity/s-1`, `severity/s0`, `severity/s1`), immediate downgrade to `deferred` with explanatory comments, optional…

Pre-push self-review gate for MatrixOne changes — systematic first-principles review of the complete diff, including functional closure, unhappy paths, state/ownership models, wait-for dependencies, restart/reuse generations, and derived test matrices. Use…

Systematic MatrixOne kind/bug lifecycle triage — intake normalization with `needs-triage`, conservative promotion to active severity (`severity/s-1`, `severity/s0`, `severity/s1`), immediate downgrade to `deferred` with explanatory comments, optional…

Full-codebase MatrixOne unhappy-path audit for leak, double cleanup, hung, and OOM risks using the Q1-Q3 framework plus ownership and wait-for graphs. Use for resource lifecycle, cancellation/close/fail-fast paths, goroutines, locks/channels/RPC waits,…

Run TPC-H or TPC-DS benchmarks on Super Sirius or DuckDB CPU baseline — generate data, execute queries, validate results, and compare timings. Trigger when the user mentions benchmarking, TPC-DS, TPC-H, performance testing, query runtimes, or wants to compare…

Use this skill to generate benchmark datasets (TPC-H, TPC-DS, etc.). Trigger when the user needs test data at a specific scale factor for benchmarking or testing. Supports parquet and duckdb output formats.

Discover and document a dependency library or submodule — analyzes all uses within the codebase, divides the library into logical modules, identifies which modules are used, and generates LLM-consumable API documentation for each module. Use when the user…

Use this skill to understand why a Sirius query is slow, identify GPU bottlenecks, or detect performance regressions. Generates reports with kernel occupancy, memory bandwidth, operator attribution, and cross-run comparisons. Trigger when the user mentions…

Use this skill when the build fails, compilation errors occur, or you see undefined references, linker errors, CUDA compilation issues, missing headers, or template instantiation failures. Analyzes errors, suggests fixes, and iteratively rebuilds until…

Use this skill to find exactly which source code to optimize for better GPU performance. Maps nsys profile hotspots to specific Sirius source files and functions, classifies bottlenecks as GPU-bound, CPU-bound, or sync-bound, and recommends actionable code…

Use when editing existing matrixorigin-blog articles, preserving frontmatter, changing dates or status, updating local image paths, keeping edits scoped to one article, and validating the result.

Use when creating a new article in matrixorigin-blog, choosing matrixorigin or memoria, creating the slug directory, setting frontmatter, adding local images or videos, validating content, and preparing a scoped PR.

Use when diagnosing why a matrixorigin-blog article is missing, not published, sorted unexpectedly, has broken media, or did not update on the downstream MatrixOrigin or Memoria website.

Use for matrixorigin-blog PR preparation, PR body drafting, review output, issue association wording, scope checks, generated-file checks, and choosing verification for content, docs, schema, or workflow changes.

Create structured BUG issue drafts for the MatrixOrigin matrixflow repository and, after explicit user confirmation, submit them as standalone GitHub issues or sub-issues. Use when the user wants to report, draft, refine, or submit a MatrixFlow/New MOI bug,…

创建、补全、审查或更新一个用于 MOI 客户业务 Storybook、产品用户旅程、端到端走查、生成式 AI、事件驱动、定时任务、人工审批或工作流验收的 GitHub 单 Issue。当用户要求整理 Storybook Issue、客户场景、User Journey、业务走查或验收故事时使用。所有 Scene、实际结果、证据、验收项和问题跟踪必须放在同一个 Issue 中。不要用于前端组件开发工具 Storybook。

生成工作周报。采集 GitHub 数据，根据岗位角色生成不同视角的周报，支持对话补充内容。说"周报"即可触发；说"团队周报"走团队模式。

Run and validate one reproducible 50-question Enron NL2SQL collection round for Chat2DB, Wren, or MOI. Use when the user asks to run, resume, monitor, or verify an Enron evaluation round; collect SQL, latency, token, session, error, and MOI MatrixOne-native…