LLM Mart Basic
@llm-mart · Joined Jun 2026
Quick-reference card for Chisle commands. One-shot display, not a persistent mode. Use when the user says "chisle help", "how do I use chisle", "what chisle commands", or invokes /chisle-help.
Review a diff or file through the Chisle lens: flag over-engineering, speculative abstractions, reinvented stdlib, and verbose code that a lazier approach would shrink. One finding per line, no praise. Use when the user says "chisle review", "review this for bloat", or invokes /c
REST API design, versioning, error responses, pagination, OpenAPI conventions. Use when designing new API endpoints, reviewing API contracts, or setting up Swagger/OpenAPI documentation.
JWT access/refresh tokens, Passport.js strategies, session management, OAuth. Use when implementing authentication, authorization, or setting up OAuth providers in a NestJS + Next.js app.
Backend architecture principles, layering, error handling, logging patterns for NestJS. Use when designing NestJS modules, writing service logic, structuring error handling, or setting up structured logging.
Structured brainstorming techniques, idea generation, trade-off analysis. Use when exploring design options, choosing between architectural approaches, generating feature ideas, or making technology decisions.
Code review checklist, what to look for, how to give feedback, PR review flow. Use when reviewing a pull request, or when preparing code for review.
Vercel frontend + Railway/Fly.io backend deployment, env vars, health checks. Use when deploying a Next.js frontend to Vercel or a NestJS backend to Railway or Fly.io, or troubleshooting a deployment issue.
Generating Word documents programmatically with docx library in Node.js. Use when generating .docx reports, contracts, invoices, or any structured Word document from data.
UI component design principles, visual hierarchy, spacing, typography for Next.js apps. Use when building or reviewing React/Next.js components, setting up design tokens, or establishing visual consistency.
Git branching strategy, commit messages, PR workflow, conflict resolution. Use when setting up a branching strategy, writing commit messages, creating pull requests, or resolving merge conflicts.
CI/CD workflow patterns, testing pipelines, deployment automation. Use when setting up GitHub Actions workflows for testing, building, linting, or deploying a fullstack app.
NestJS best practices, module architecture, DTOs, Guards, Interceptors, and common patterns. Use when building or reviewing NestJS backend services.
Next.js App Router best practices, Server Components, Server Actions, routing patterns, and data fetching strategies. Use when building Next.js applications with the App Router.
Generating PDFs with pdfkit or puppeteer in Node.js. Use when generating PDF reports, invoices, certificates, or any printable document from data or HTML templates.
Generating PowerPoint presentations with pptxgenjs in Node.js. Use when creating automated presentations, slide decks, pitch decks, or reports in .pptx format from data.
Prisma ORM best practices, schema design, migrations, seeding, and query optimization for PostgreSQL. Use when working with database schemas, migrations, or Prisma queries.
Comprehensive prompt engineering framework for designing, optimizing, and iterating LLM prompts. Use when creating prompts, optimizing existing prompts, or improving AI instructions.
React component patterns, hooks, state management, and performance best practices. Use when building or reviewing React components.
OWASP Top 10, input validation, SQL injection prevention, rate limiting, CORS. Use when reviewing code for security issues, setting up a new API, or doing a pre-deploy security audit.
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.
/afst
Afst
Show current AutoFile policy and settings
/allow
Allow
Allow all file creation - full permission to create and modify files
/autoproc
Autoproc
Start autoproc - procedural autonomous workflow (legacy command)
/autorun
Autorun
Start autorun - autonomous task execution (legacy command)
/blocks
Blocks
Show active session-level pattern blocks and allows
/cache
Cache
Cache-miss / compaction protection gate (disabled by default)
/claude-code-plugin-help
Claude code plugin help
Reference the supported Claude Code command, skill, plugin, and hook surfaces
/clear
Clear
Clear all session-level pattern blocks and allows
/estop
Estop
Emergency stop - immediately halt all autonomous operations
/f
F
Find existing files only - no new file creation (short for /ar:find)
/find
Find
Find existing files only - prevents new file creation (strictest mode)
/gc
Gc
Git commit requirements - the 17-step process, short for /ar:commit
/gemini
gemini
Use gemini CLI for any combination of: superior vision for analysis of images, diagrams, screenshots, PDFs, documents, video, and audio; code review with detailed citations and cross-referencing patterns; Google search; and multi-model workflows; all for planning, feedback, and getting unstuck.
/globalclear
Globalclear
Clear all global pattern blocks and allows
/globalno
Globalno
Block a command pattern globally (persists across sessions)
/globalok
Globalok
Allow a blocked pattern globally (persists across sessions)
/globalstatus
Globalstatus
Show active global pattern blocks and allows
/go
Go
Start autorun - autonomous task execution (short for /ar:run)
/gp
Gp
Start autoproc - procedural autonomous workflow (short for /ar:proc)
/help
Help
List every autorun command with what it does, in this harness's spelling
Okou connects to the tools your team already uses and does the work — across marketing, sales, engineering, and operations, under your control.
4 views 0 likesAn open-source Digital Worker platform for reliable execution, continuous co-evolution, and building Enterprise AI assets.
5 views 0 likesA curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects. | evomap.ai
4 views 0 likesA governance harness for AI coding.
3 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
1 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
3 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.
5 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…
4 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…
4 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.
2 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,…
2 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。
2 views 0 likesOpen-source, local-first AI agent for coding and real work. BYOK models, MCP, skills, plugins, workflows, and private knowledge bases.
4 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…
4 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…
5 views 0 likes