LLM Mart Basic
@llm-mart · Joined Jun 2026
Use Cursor's browser aria snapshots to audit a page for accessibility issues — missing labels, broken tab order, contrast, and ARIA misuse.
Capture recurring agent-development friction as a local, privacy-safe Markdown report. Use only when the user explicitly requests a friction review of blockers, misleading errors, missing documentation, incompatible tools, or manual workarounds that should improve a doc, tool, sk
Answer in the ADHD-friendly Attention-kind style for the rest of this chat.
Build, review, refactor, or architect ASP.NET Core web applications using current official guidance for .NET web development. Use when working on Blazor Web Apps, Razor Pages, MVC, Minimal APIs, controller-based Web APIs, SignalR, gRPC, middleware, dependency injection, configura
Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or CSP or domain settin
Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stab
Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.
Help the user define a concrete, measurable goal before starting work, especially when they ask to use the goal tool, create a goal, set an objective, clarify success criteria, or turn a fuzzy intention into a quantitative outcome. Use this skill for goal creation and goal refine
Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.
Connects Figma design components to code components using Code Connect mapping tools. Use when user says "code connect", "connect this component to code", "map this component", "link component to code", "create code connect mapping", or wants to establish mappings between Figma d
Generates custom design system rules for the user's codebase. Use when user says "create design system rules", "generate rules for my project", "set up design rules", "customize design system guidelines", or wants to establish project-specific conventions for Figma-to-code workfl
Create a new blank Figma file. Use when the user wants to create a new Figma design or FigJam file, or when you need a new file before calling use_figma. Handles plan resolution via whoami if needed. Usage — /figma-create-new-file [editorType] [fileName] (e.g. /figma-create-new-f
Use this skill alongside figma-use when the task involves translating an application page, view, or multi-section layout into Figma. Triggers: 'write to Figma', 'create in Figma from code', 'push page to Figma', 'take this app/page and build it in Figma', 'create a screen', 'buil
Build or update a professional-grade design system in Figma from a codebase. Use when the user wants to create variables/tokens, build component libraries, set up theming (light/dark modes), document foundations, or reconcile gaps between code and Figma. This skill teaches WHAT t
Translates Figma designs into production-ready application code with 1:1 visual fidelity. Use when implementing UI code from Figma files, when user mentions "implement design", "generate code", "implement component", provides Figma URLs, or asks to build components matching Figma
**MANDATORY prerequisite** — you MUST invoke this skill BEFORE every `use_figma` tool call. NEVER call `use_figma` directly without loading this skill first. Skipping it causes common, hard-to-debug failures. Trigger whenever the user wants to perform a write action or a unique r
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.
Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope
Create, repair, validate, visually QA, and package Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual references. Use when a user wants a lightweight-worker Codex pet workflow, a non-pixel custom pet
Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.
We ran six popular prompting techniques against developer tasks on three models and scored every answer with code. Three helped everywhere, one did nothing, two depended on the model. Here are the prompts, the numbers, and a script to test your own.
How a transformer works out that 'it' means the cat: dot products, softmax and a weighted sum, built in about a dozen lines of NumPy and worked by hand, number by number.
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.
/lineage-discovery
Lineage discovery
Discover testnet↔mainnet subnet lineage from repo configs and open a PR for review (pass --dry-run to report only)
/capture
capture
Triage raw inbox notes into reviewed repository destinations without deleting their sources.
/clean-ai-writing
clean-ai-writing
Audit and rewrite content to remove AI writing patterns
/content-shipped
content-shipped
Log a completed piece of content to content/log.md after the user confirms it was published.
/dream-apply
dream-apply
Validate a dream artifact, review each proposal, and apply only individually accepted changes.
/dream
dream
Run a curator pass against the validated memory directory and produce a proposal artifact.
/end
end
End a session — log what happened, update state and the decision log, propose memory updates, and check for uncommitted or unpushed work
/find-context
find-context
Find relevant context files by topic. Use when you need to load files for a topic without a slash command, or when a task spans multiple domains.
/migrate-gemini
migrate-gemini
Inventory and migrate selected Gemini CLI workflows with dry-run review and parity checks.
/mine-gemini-workflows
mine-gemini-workflows
Find repeated workflows in selected Gemini CLI sessions and draft portable skills after review.
/reconcile
reconcile
Scan multi-session drift and offer individually reviewed fixes only after explicit approval.
/recover
recover
Scan orphaned worktrees and stale branches, then offer explicit approval-gated cleanup.
/setup
setup
Guided onboarding or import for durable workspace context
/start
start
Start a session — load state files, flag staleness, and give a briefing on current priorities, deadlines, and blockers
/today
today
Create a morning heartbeat from repository state and update the local heartbeat log.
/update
update
Mid-session checkpoint — append progress to today's session log and update state files if a priority shifted, without ending the session
/gaia-debt
gaia-debt
Fixes the tech-debt backlog, a single issue, a recommended related batch, or an optional batch of small unrelated issues, highest severity then oldest first, on a fresh isolated branch through the audit gate, closing the issue(s) on merge. With no argument it drains the top of the backlog, and also offers a batch of small unrelated issues when two or more unrelated issues or groups fit at offer time; one issue number fixes that issue directly, and several issue numbers name the operator's own batch, budgeted. An optional trailing `[use] worktree|branch` picks the isolation mode. A named number that cannot be drained stops with a reason. Use when the user asks to drain, fix, or work the tech-debt backlog or a named tech-debt issue.
/gaia-fitness
gaia-fitness
Lints this project's Claude integration (skills, commands, agents, rules, hooks, settings, CLAUDE.md files, wiki) with a deterministic rule catalog and reports an F-to-A+ grade, plus Claude Code built-in results and an advisory model judgment of descriptions, trigger overlap, rule scope and terminology. Proposes fixes for project-owned files only and applies each one only on a per-file yes, then offers to publish. Use when the user asks to check, grade or tidy their Claude setup.
/gaia-forensics
gaia-forensics
Turns a GAIA workflow misfire into a redacted, classified, filing-ready bug report in one read-only pass. Self-diagnoses config issues inline and files probable bugs upstream on confirmation.
/gaia-init
gaia-init
Initializes a new project from the GAIA harness. Renames, strips GAIA branding, configures i18n, installs the React Doctor skill, then continues into /setup-gaia in the same session.
MCP server for reusable prompt templates, multi-step workflow chains, and quality gates. Compose agentic workflows with an operator syntax; export as native ski…
17 views中国股票数据基础设施,覆盖行情、研报、资金面、筹码、公告、龙虎榜、ETF/期权、舆情互动、基本面、行业板块、宏观与风险事件等核心数据。42+A股数据集,日更、自托管、MCP 原生,零注册、零 API Token
17 viewsOKF (Open Knowledge Format): Durable, structured memory for AI agents. Author, validate, consume, and maintain portable knowledge bundles through an ecosystem o…
37 views토스증권을 AI 에이전트와 터미널에서 다루는 도구. CLI 와 MCP 서버로 계좌·시세·주문은 물론 웹앱 전용 기능(수급·AI 시그널·스크리너·배당)까지, JSON·CSV 구조화 출력으로 AI 도구·자동화에 바로 연동.
34 viewsClaude skills for LinkedIn. 11 Claude Code and Codex skills that write human-sounding LinkedIn posts, craft comments that get noticed, analyze your feed, and bu…
29 viewsMCP server connecting AI agents to ITASCA engines (PFC, FLAC, 3DEC, MPoint, MassFlow) — run geotechnical & geomechanics simulations through natural conversation
20 viewsA curated list of amazingly awesome articles, people, applications, software libraries and projects related to the knowledge management space
18 viewsOne local dashboard for every Claude Code, Codex, Cursor, Antigravity, and Kilo Code session on your Mac. Spawn in parallel, ship in parallel. Open source, MIT.
36 viewsBuilding blocks for frontier OpenAI agents in Rust. Nanocodex empowers you with Codex-level performance anywhere.
33 viewsThe AI agent that lives in your framework/browser
31 viewsSelf-Programming AI Assistant. Capture, automate, and refine all your workflows.
24 viewsConsider it done. The open-source AI agent that works out of the box · 想到,就能做到。开源、开箱即用的 AI Agent。
19 viewsMake Any Website into CLI & Use your logged-in browser by AI agent.
39 viewsISO 24495 Plain Language skills and Claude Code plugin
19 viewsDeterministic, fail-open tool routing for Hermes Agent with an optional local-model fallback.
18 views1인 사업가 생산성 키트 — 직원 없이 49개를 자동화했고, 그중 바로 쓸 수 있는 AI 에이전트 스킬 26개(+실행 스크립트)를 공개합니다
17 viewsAI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agent…
32 viewsThe open-source, self-hosted video conferencing software. Scalable, customizable, and with a powerful AI Meeting Agent.
34 viewsBusiness operating system for Claude Code — 57 skills, 21 agents, smart daemon. Unified inbox (WhatsApp/Email/Slack/Telegram), autonomous PR merge, full-AWS mon…
22 viewsA local-first, cross-platform Electron desktop workspace for Pi Coding Agent, with sessions, project files, browser tools, skills, plugins, and messaging integr…
19 views