LLM Mart Basic
@llm-mart · Joined Jun 2026
Audit and govern Alibaba Cloud KMS key lifecycles, Certificate Manager, SSM (Secrets Manager), and HSM key operations. Ensure encryption-at-rest coverage and rotation compliance across CMKs, envelope encryption, and certificate lifecycle.
Design Alibaba Cloud landing zone — Resource Management org tree, Cloud SSO, Control Policy (SCP equivalent), multi-account governance baseline, billing account structure, and ActionTrail centralization.
Gate ACK deployment mutations, node pool scaling, and cluster version upgrades against rollback posture and workload disruption budget. Prevents irreversible cluster version upgrades from proceeding without PodDisruptionBudget verification, node drain confirmation, and explicit o
Gate live financial authority actions — budget threshold changes, Savings Plan purchases, and Reserved Instance commitments. These are committed spend or can trigger immediate service suspension.
Gate KMS key deletion and disable operations. All data encrypted with a deleted CMK (OSS SSE-KMS, ECS encrypted disks, RDS/PolarDB TDE) becomes permanently and irrecoverably inaccessible. This guard enforces complete CMK dependency audits, deletion window confirmation, and explic
Gate OSS bucket ACL and policy mutations — public-read/write ACL exposes data to internet crawlers within seconds; CN-* cross-border replication requires DSL Article 31 assessment.
Gate RAM policy/role mutations against the Alibaba Cloud account hierarchy. RAM AdministratorAccess assignment, policy deletion with active STS tokens, and Resource Directory Control Policy changes carry account-wide or org-wide blast radius. This guard enforces blast-radius asse
Gate RDS/PolarDB instance deletion, spec downgrade, and backup policy removal — database deletion without verified backup is permanently destructive.
Traffic engineering for Alibaba Cloud load balancers — CLB (Classic, legacy), ALB (Application Load Balancer, Layer 7 advanced routing), NLB (Network Load Balancer, Layer 4 high throughput), and GA (Global Accelerator) — type selection, health check design, WAF integration, and t
Alibaba Cloud Maestro routing skill. Classify the user's Alibaba Cloud task, select the narrowest specialist agent or the right team of specialists from the catalog, and dispatch them — single specialist for focused tasks, parallel team (max 4) for multi-domain tasks. Never auto-
Manage MaxCompute CU package governance, DataWorks scheduling, Quick BI reporting, and PAI ML platform. Optimize query cost and job scheduling efficiency for big data workloads.
Plan Alibaba Cloud migrations using SMC (Server Migration Center), DTS (Data Transmission Service) for data sync, OSSImport for object storage migration, and design cutover sequencing with rollback paths.
Configure and operate Alibaba MSE (Microservice Engine) — Nacos service discovery and configuration management, Sentinel rate limiting and circuit breaking, Seata distributed transactions, and ARMS APM for microservices observability.
Design Alibaba Cloud network topology — VPC peering, CEN for multi-VPC/multi-region connectivity, Express Connect for private circuits, SLB/ALB/NLB/CLB load balancer selection, and Smart Access Gateway for branch offices.
Respond to Alibaba Cloud incidents using CloudMonitor alarms, SLS log analytics, ARMS APM distributed tracing, and alert governance for ECS, RDS, ACK, and network services.
Govern Alibaba Cloud OSS data perimeters — bucket ACL and policy conflict resolution, Block Public Access configuration, cross-account access via RAM role, VPC endpoint binding for private access, WORM (Object Lock), and MLPS 2.0 data residency compliance.
Manage OSS lifecycle policies, bucket policy and ACL governance, NAS/CPFS shared file storage, cross-region replication, and access control hardening for Alibaba Cloud object and file storage.
Operate PolarDB (MySQL/PG/Oracle) clusters and RDS instances — DAS diagnostics, database proxy, Global Database Network, backup strategy, and performance tuning.
Audit Alibaba Cloud RAM users, groups, roles, and policies; review STS token lifecycle and scope; assess Resource Directory permission boundaries; review Control Policy statements for org-wide gaps or over-privilege.
Govern Alibaba Cloud Container Registry (ACR) — Enterprise Edition vs Personal Edition selection, image vulnerability scanning, namespace IAM least privilege, image retention policies, cross-region replication, and supply chain security posture.
Fourteen posts of being wrong in production, compressed to checkboxes
Healthy nodes, a quiet network, 300 restarts in three days, and a latency budget measured in milliseconds
Discovery worked. Ping worked. Every TCP connection timed out, and later the tunnel only worked when someone had a terminal open.
Every VM came back. The cluster did not. Declarative systems converge on config, and the datapath isn't config.
A surprising share of AI-in-the-terminal failures aren't the AI. They're zsh, and a version of bash from 2006.
A Claude Code plugin turns standalone project configuration into a namespaced, installable extension that teams and communities can update as one unit.
None of the safety came from the model. It came from six boring habits.
Skills package instructions and references. Subagents run work in a separate context and return results. They solve different problems and can be composed deliberately.
Six hours in, one step left, everything green, and the incident that didn't happen
CLAUDE.md carries persistent project context. Skills load reusable procedures when relevant. Separating stable facts from task-specific workflows keeps both easier to maintain.
Twenty minutes recovering secrets that never existed, and the one sentence from a human that ended it
An API request routing a model's tool call through an approval gate to a remote MCP server
31 config keys, two audits, and why the first one was wrong in both directions
The official MCP Registry stores standardized server metadata rather than package code. Publishers verify a namespace, describe installation or remote access, and submit immutable versions.
Everyone looks at the Dockerfile. The file that actually leaked the key was the project file.
Remote MCP authorization uses established OAuth standards, but secure integration still requires issuer validation, least-privilege scopes, protected token handling, and server-side enforcement.
"Copy it over and switch the reference" is two steps, and the outage lives in the one nobody checks
stdio fits local processes and prototypes. Streamable HTTP fits hosted services and shared integrations. The right choice follows where the capability runs and who must reach it.
The most important rule wasn't about what I could change. It was about what I was allowed to display.
Tools perform operations, resources expose readable context, and prompts provide reusable templates. Choosing the correct primitive makes an MCP server easier to understand and govern.
/close-out
Close out
Close a finished session: sweep for unfinished work, ask once, land, file the follow-ups, hand off, tell the sessions that depend on this one, then archive.
/handoff
Handoff
Write the repository handoff file for the next session, and record any durable learning.
/land
Land
Merge an approved pull request, clean up its worktree and branch, then check whether a release is due.
/plan
Plan
Turn a topic or issue into a plan the reviewer approves in the native plan pane.
/research
Research
Answer a research question with parallel read-only gatherers and one synthesized digest.
/review
Review
Review the branch's diff in two fresh contexts — scope against the spec, then quality — and report findings only.
/audit-infra
Audit infra
Audit infra security: secrets, deps, CI/CD, webhooks, AI/skill files
/audit-solana
Audit solana
Audit Solana program code for exploitable bugs and write a findings report
/benchmark
Benchmark
Compare per-instruction CU with the stored baseline to catch regressions
/build-app
Build app
Build the web client (Next.js, Vite, React) and check env, types and bundle
/build-program
Build program
Build Solana programs (Anchor, Pinocchio, native), incl. verifiable builds
/build-unity
Build unity
Build the Unity project in batchmode for WebGL, desktop, Android or PSG1
/cleanup
Cleanup
Turn a solana-ai-kit fork into a project: set up CLAUDE.md, remove kit files
/commit-claude-config
Commit claude config
Un-ignore and commit the kit config dir, instruction file, .mcp.json and .gitmodules
/debug-user-tx
Debug user tx
Replay a user's failing transaction on forked state and map the error to source
/deploy
Deploy
Deploy a program to devnet, or to mainnet after the user's explicit go-ahead
/diff-review
Diff review
Review the branch diff for Solana security issues, CU waste and AI slop
/doctor
Doctor
Read-only check of toolchain and kit config, with one fix-it command per failure
/dream
Dream
Consolidate MEMORY.md and Project Learnings: dedupe, resolve conflicts, prune
/explain-code
Explain code
Explain Solana code with a diagram and a step-by-step walkthrough
Your efficient agentic AI coding CLI assistant
2 views 0 likesAI coding with Aegis governance built into execution: baseline-aware changes, evidence-backed delivery. Free desktop client, your choice of model. 将哲科思维融入 AI 开发…
1 views 0 likesAndroid in docker solution with noVNC supported, video recording, mcp server and AI-agent
2 views 0 likesYour AI assistant, built for the agentic era. Open source and local: talk to it, and it runs your agents, your coding CLIs, your browser and your apps. Windows,…
0 views 0 likesVerifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions.
3 views 0 likesLet Claude Code and other coding agents drive and debug Chrome from the shell. DOM, network, console and raw CDP as short commands, no screenshots and no MCP ne…
3 views 0 likesUnofficial, agent-friendly Mercadona shopping CLI (Go) — search products, read prices, build a cart and prepare checkout from the terminal. BYO credentials.
3 views 0 likesLocal-first AI canvas for visual workflows, AI short drama, image/video generation, storyboarding and asset management. ComfyUI, AI agents, MCP & Blender. 本地优先…
3 views 0 likesLet any AI coding tool — Claude Code, Cursor, Codex — drive your real Chrome. One-prompt setup, muscle memory, local-first.
3 views 0 likesruns anywhere. uses anything
3 views 0 likesOpen-source dots for the web: an AI agent with its own browser, one that does not get blocked.
0 views 0 likesFree MIT AI coding agent — no API key needed. Built-in free model, or bring Claude, GPT, Gemini, DeepSeek, Ollama +50 more. Swarm mode, 40+ tools, browser & des…
0 views 0 likesOpen-source AI customer support system. AI-first support, human-ready operations.
0 views 0 likesA durable, multiplayer, mobile-first web app for Pi agents, built on Pi Durable
0 views 0 likesEmbedded Cypher knowledge graph for Python and Rust. Bundled MCP server, describe() schema, and code-graph parser for LLM agents.
0 views 0 likesTurn PDFs, books and papers into interactive learning webpages|将复杂材料转化为可追溯、可测验、可做笔记的学习网页
0 views 0 likesPhysicsOS 是一个面向初高中物理学习的公益可视化智能体,通过 AI 理解题目并结合物理引擎,将抽象物理过程转化为可交互、可观察、可计算、可验证的真实物理场景。
0 views 0 likes