LLM Mart Basic
@llm-mart · Joined Jun 2026
阶段内任务跟踪(创建/更新任务列表,附在工作流上)
TDD 测试先行(按设计文档生成失败的测试用例)
立测试地基(探测技术栈 → 验证并生成 test-commands.yml → 脚手架测试目录 → 接本地钩子)
UI/UX 设计
UI/UX 专业设计(PDLC 集成层,依赖 ui-ux-pro-max)
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have quest
Builds Python components using the compone framework for type-safe HTML/XML/RSS generation. Use when working with compone, creating Python components, generating markup in Python, or building framework-agnostic component libraries.
Use this when working in a project with devenv.nix, or when devenv.sh development environment setup, services, dependencies, or Nix packages are relevant.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Analyze Hacker News thread sentiment from a provided HN thread URL.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Write clean, readable Pythonic code. Use this skill any time you write or change a Python file.
Predict protein 3D structures with AlphaFold2 via ColabFold — MMseqs2-accelerated MSAs, monomer and AlphaFold2-Multimer complex folding, and confidence-based validation (pLDDT, pTM/ipTM, PAE). Use when folding a protein sequence or complex from FASTA, generating a predicted struc
Build, slice, concatenate, read, and write AnnData annotated data matrices (obs, var, X, layers, obsm, uns) — the scverse data STRUCTURE, not an analysis pipeline. Use when creating or wrangling .h5ad/zarr files, managing cell and gene annotations, concatenating batches, or handl
Infer gene regulatory networks (GRNs) from expression matrices using arboreto's scalable GRNBoost2 and GENIE3 tree-ensemble algorithms with Dask-distributed computation. Use when analyzing bulk or single-cell RNA-seq transcriptomics to map transcription-factor-to-target-gene regu
Manipulate biological sequences, parse FASTA/GenBank/PDB files, run phylogenetics, and access NCBI/PubMed programmatically via Biopython (Bio.SeqIO, Bio.Entrez, Bio.PDB, Bio.Blast). Use when scripting custom bioinformatics pipelines, batch-processing sequence files, automating BL
Query 40+ bioinformatics web services through one consistent Python API with bioservices (UniProt, KEGG, ChEMBL, Reactome, Ensembl, NCBI and more). Use when a workflow must hit multiple databases together, map identifiers across services, or run cross-database analyses — for quic
Runs NCBI BLAST+ 2.17.0 sequence searches from the command line: makeblastdb (with -parse_seqids), blastn/blastp/blastx/tblastn with tabular -outfmt 6/7 for parsing, correct -task choice (megablast vs blastn vs blastn-short), -taxids/-negative_taxids taxonomic scoping, and -mt_mo
Co-fold biomolecular complexes with Boltz-2, an open AlphaFold3-style model — predict protein + ligand (SMILES/CCD), protein + nucleic-acid, and multi-chain structures in one pass, with binding-affinity prediction. Use when folding a protein together with a small-molecule ligand,
Predict genome-wide functional genomics tracks from DNA sequence with Borzoi (Linder 2025) — a sequence-to-function model outputting RNA-seq, CAGE, ATAC, and ChIP coverage across long context, used to score non-coding and regulatory variant effects. Use when predicting functional
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.
Use MCP Inspector to connect to local or remote servers, inspect capabilities, call tools, read resources, test prompts, and diagnose failures before release.
Build an MCP server in TypeScript with focused tools, validated schemas, local and remote transports, Inspector tests, and production security controls.
An MCP server exposes tools, resources, or prompts through a standard protocol so an AI application can discover and use external capabilities.
Treat an AI agent skill as both an instruction package and a software dependency: inspect what it says, what it runs, what it can access, and how it updates.
Add remote HTTP or local stdio MCP servers to Claude Code, choose the right scope, protect credentials, verify the connection, and test with least privilege.
/inspect
Inspect
`crabbox inspect` prints the full record for a single lease: state, provider,
/job
Job
Run named, repo-local jobs defined in your Crabbox config.
/list
List
`crabbox list` shows the current Crabbox machines (leases) for a provider. It is
/login
Login
`crabbox login` authenticates the CLI against a coordinator, stores the
/logout
Logout
`crabbox logout` clears the stored broker token from your user config so the CLI
/logs
Logs
`crabbox logs` prints the retained command output for a recorded run.
/marketplace
Marketplace
`crabbox marketplace` previews the Crabbox credits gateway: one Crabbox billing
/media
Media
`crabbox media` turns a recorded desktop video into lightweight review
/open
Open
`crabbox open` prepares an existing SSH-capable lease for an external editor.
/pause
Pause
`crabbox pause` pauses a single lease, freeing the remote compute while
/pond
Pond
`crabbox pond` is the cross-provider peer-discovery and lifecycle surface for a
/pool
Pool
`crabbox pool` contains machine-pool helpers. `pool list` keeps the older
/ports
Ports
`crabbox ports` bridges provider-native port publishing for an existing Crabbox
/prewarm
Prewarm
`crabbox prewarm` leases a reusable box and prepares it for test runs. For
/providers
Providers
`crabbox providers` prints the provider capability matrix that the CLI compiles
/receipt
Receipt
`crabbox receipt <run-id>` retrieves a brokered run's committed terminal
/results
Results
`crabbox results` prints the structured test summary attached to a recorded
/resume
Resume
`crabbox resume` resumes a lease previously paused with [`pause`](pause.md),
/run
Run
`crabbox run` syncs the current dirty checkout to a box, runs a command there,
/screenshot
Screenshot
`crabbox screenshot` captures a single PNG from a desktop lease without opening a
Okou connects to the tools your team already uses and does the work — across marketing, sales, engineering, and operations, under your control.
3 views 0 likesAn open-source Digital Worker platform for reliable execution, continuous co-evolution, and building Enterprise AI assets.
3 views 0 likesA curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects. | evomap.ai
2 views 0 likesA governance harness for AI coding.
2 views 0 likesDeepSeek Harness 手机版:可直接安装的 Android APK,AI 免 Root 操作手机(Shizuku/root 可选),文件编辑只需所有文件访问权限,前台保活 + AI 通知
0 views 0 likesLocal-first, governed AI agent runtime for Python — embed it in your app, or run it as a CLI or ACP server. Permissions, MCP, memory and audit replay built in.
2 views 0 likesOrbi — the factory that builds and operates AI software factories. GitHub Issues in, releases and runnable system out
2 views 0 likesOpen-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.
1 views 0 likesThe SDK for browser agents. Interact, search, extract, and fetch any site reliably across the web
4 views 0 likesAgent-native shopping for extreme value: verifiable same-product price evidence, checkout, orders, delivery, and after-sales.
3 views 0 likesThe extensible power-user platform for Google Antigravity. Adds a native In-App Browser, animated Desktop Pets, revamped Gemini UI, and custom BYOK Gemini Pro k…
3 views 0 likesOpen-source, single-binary, self-hosted AI agent — your models and data stay on your machine. A coding agent on par with Claude Code and a personal assistant li…
2 views 0 likesYour pocket agent. Local-first AI agents on iOS and Android — real workspaces, tool execution with approvals, and your choice of model (DSH · Claude Code · Code…
3 views 0 likesBridge between QQ (SnowLuma OneBot v11) and DeepSeek Harness agents: social simulation, safe MCP tools, slang learning and more.
1 views 0 likesA 7×6 framework for agent architecture. 28 patterns, each placed at a coordinate, runnable Python code with verified engineering slices from Claude Code, Aider,…
1 views 0 likes针对 AI 自动化渗透 Agent 的新一代反制蜜罐,通过反向代理将API密饵载入真实业务、反向提示词注入等方式反制自动化渗透 Agent,实现多款主流通用Agent的反制上线控制。
1 views 0 likesOpen-source, local-first AI agent for coding and real work. BYOK models, MCP, skills, plugins, workflows, and private knowledge bases.
3 views 0 likesA free AI-agent toolbox for Android, 一站式安卓AI Agent工具箱
4 views 0 likesGoogle Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. I…
3 views 0 likesIndependent, unofficial CLI to edit CapCut and JianYing (剪映) projects — subtitles, timing, speed, volume, templates, cut long-form to shorts. No API needed, rea…
4 views 0 likes