LLM Mart Basic
@llm-mart · Joined Jun 2026
Suede Labs Graph-of-Thoughts shipping search for a multi-file repo change. Use when competing implementation plans need one evidence-gated selection before any build. Halts on hazards, collisions, budget exhaustion, or no safe winner. Reads production; never deploys. NOT FOR: bul
Suede-owned marketing image production for generation prompts, hero and social graphics, product mockups, export sizing, compression, and preview assets. Use when the user needs a general-purpose marketing image or an image-production workflow. NOT FOR: paid-ad creative systems (
Suede-owned Instagram growth operating system for account-specific audits, Reels, carousels, Stories, conversion mapping, calendars, and daily candidate-production loops. Use when the user names Instagram, IG, Reels, Stories, asks to analyze recent posts, grow a handle, run a dai
Suede-owned launch packaging and install verification. Use when finished software work needs a clean public package — README, docs page, install command, release note, GitHub Pages update, skill-pack release, MCP server, or launch/social copy — or when a release needs handoff not
Suede-affiliated lead-magnet strategy for choosing a downloadable format, defining useful depth, setting honest gating, planning delivery, and measuring qualified capture. Use when the user needs an ebook, checklist, template, content upgrade, or resource exchanged for contact de
Suede-affiliated marketing deliberation that applies documented public frameworks through clearly labeled simulated advisors, surfaces disagreements, and synthesizes a decision. Use when the user wants multiple expert lenses on one bounded marketing question. NOT FOR: factual cla
Suede-affiliated marketing ideation using a structured tactic library organized by stage, budget, and timeline. Use when the user is stuck, wants options, or needs a shortlist of growth tactics before committing to a plan. NOT FOR: a comprehensive roadmap (use suede-marketing-pla
Suede-affiliated recurring marketing workflow design for cadence, inputs, decision rules, checkpoints, failure states, and measurable outputs. Use when the user wants repeatable ad-fatigue, content-refresh, churn-watch, ranking-drop, or weekly-review loops. NOT FOR: one-off tacti
Suede-affiliated comprehensive marketing planning across acquisition, activation, retention, referral, and revenue, sized to the actual team, budget, evidence, and stage. Use when the user needs a 90-day plan, 12-month roadmap, growth plan, or go-to-market operating document. NOT
Suede-affiliated ethical application of behavioral science to marketing decisions, including framing, anchoring, social proof, loss aversion, choice architecture, and friction. Use when the user needs a named psychological model, an evidence-aware application, and a testable hypo
Suede Labs AI MCP release QA, scoped to this pack's own server (mcp/suede-skills-mcp.mjs) and its catalog, install, and docs surface. Runs the full JSON-RPC lifecycle against a live server — initialize, notifications/initialized, ping, tools/list, tools/call, resources/list, reso
Suede-affiliated offer design for value framing, bonuses, guarantees, risk reversal, honest scarcity, naming, and payment structure. Use when the user is building or diagnosing a service, course, coaching, information-product, agency, or high-ticket B2B offer. NOT FOR: SaaS tier
Suede-affiliated onboarding and activation strategy for first-run sequencing, empty states, setup checklists, activation milestones, time to value, and retention-linked measurement. Use when users sign up but fail to reach first value or the product needs a new first-session flow
Suede-affiliated in-product monetization design for paywall screens, feature gates, trial-expiry states, usage-limit prompts, and free-to-paid upgrade moments. Use when the user needs trigger timing, message structure, plan presentation, or experiment design after users have expe
Suede-owned pricing and packaging discipline. Use when deciding what to charge, structuring tiers, choosing a value metric, comparing free trials with freemium, researching willingness to pay, planning a price increase, or tearing down a pricing page for clarity and AI-readabilit
Suede-owned product-marketing context discipline. Use when a project needs a shared record of product, audience, ICP, positioning, objections, customer language, proof, and goals, or when that record needs updating. NOT FOR: writing a campaign (use suede-campaign-in-a-box), condu
Suede-owned programmatic SEO discipline. Use when designing data-backed keyword, location, directory, integration, or comparison pages at scale, including templates, index-worthiness gates, internal links, and rollout checks. NOT FOR: auditing an existing site (use suede-seo-audi
Suede-owned prospecting and qualification discipline. Use when defining an ICP, sourcing and enriching a bounded lead list, finding early adopters or design partners, scoring account fit, or documenting disqualification evidence. NOT FOR: sending outreach (use suede-cold-email),
Suede-owned earned-media discipline. Use when building a media list, validating a story angle, drafting a journalist pitch, preparing a press kit, evaluating newsjacking, or answering a reporter request. NOT FOR: directory submissions (use suede-directory-submissions), launch pac
Next-action selector for the Suede pack: inspects current repo, terminal, plan, or handoff state read-only and returns one recommended next move plus a short, self-contained copy/paste prompt for it. Use when the user asks 'what's next', 'what should I do next', 'recommend the ne
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.
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.
/audit
Audit
Assemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint findings — into one dated audit packet. Read-only.
/btw
Btw
Lightweight Q&A about the project — answer from context and return, no routing, no state change.
/checkpoint
Checkpoint
Periodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint report.
/chore
Chore
Sanctioned lane for non-behavioral work — docs-only edits, dependency bumps, reverts. Type-scaled gates; no TDD demanded of prose.
/cleanup
Cleanup
Clean up an already-merged local branch after proving containment. Confirm each discard and preserve unique work.
/commands
Commands
Show the codeArbiter command catalog — the public command list and what each routes to.
/commit
Commit
Create a verified local Git commit when committing changes is requested. Not for explaining commit history, drafting a message only, or postponing a commit. Applies every commit gate and never implies a push or PR.
/conflict
Conflict
Stop everything and surface a rule conflict — persona vs. docs vs. code. Present both sides and the conflict-hierarchy level; the user resolves. No silent reconciliation.
/context-check
Context check
Audit stale provenance-tracked docs on request. Report first; re-scout or re-baseline only for selected docs.
/create-context
Create context
Build project context from an existing codebase through isolated scouts, resolve gaps, and preserve initialization gates.
/debug
Debug
Investigate an unexplained defect or unexpected behavior without changing application code. Use for root-cause diagnosis and an evidence-backed handoff. A no-action close records a board note. Not for implementing a known fix, new features, or explanation-only questions.
/decompose
Decompose
Develop greenfield project context through a layered interview, preserve decisions, and initialize only after the required gates.
/doctor
Doctor
Verify the active host install, package, command ownership, enforcement, and harmless live-fire probe. Read-only.
/feature
Feature
Start a feature: brainstorm a spec, get it approved, then drive it test-first through the pipeline. The one entry to implementation.
/fix
Fix
Fix a confirmed bug: a failing regression test first, then a minimal fix, then the rest of the tdd gates.
/init
Init
Opt this repo into codeArbiter — scaffold the root-level .codearbiter/ state store.
/metrics
Metrics
Read-only 3-metric governance glance — override rate, small-lane rate, sprint low-confidence ratio — each with a trend arrow vs. the prior 20-commit window.
/override
Override
Sanctioned, logged bypass of a gate or hard rule — one audit line, then proceed.
/pr
Pr
Open a PR or finish branch disposition; route CI watching and post-merge cleanup to their owners. Merge and discard need explicit authority.
/preview
Preview
Zero-onboarding, read-only dry-run of the reviewer fleet against the current uncommitted diff. Predicts reviewers, runs the state-free secret scan, writes nothing.
Atom Agent, Open-Source Governed AI Agent Platform for Self-Hosted Automation
11 views 0 likesThe agent engineering intelligence harness, optimized tools, memory system, subagents and mixture of models packages ⚚
15 views 0 likesSesori iOS/Android app and the Sesori Bridge CLI — drive Claude, Codex, OpenCode, Cursor, Pi, OMP, Hermes coding sessions from your phone
13 views 0 likes🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.
13 views 0 likesUse ChatGPT (Codex), Claude, and Grok (X Premium) subscriptions as DeepSeek Harness LLM providers — OAuth login in the web UI, no API keys
14 views 0 likesLatitude is the open-source AI monitoring platform.
15 views 0 likesOpen-source AI browser agent for Chrome and Firefox (monorepo) 🧠
15 views 0 likesOfficial Model Studio CLI(阿里云百炼 CLI)built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls.
14 views 0 likesCurated DeepSeek Harness (DSH) plugins, extensions, tools, skills, clients, runtimes, integrations, and verified references — English and Chinese.
15 views 0 likesTurn papers, code, and docs into presentation-ready, natively editable PPTX in Codex / Claude Code. Native charts and equations, speaker notes, click-build anim…
13 views 0 likesGrix : Work with agents like talking to people.
24 views 0 likesLocal First Ai Agent. Optimized for Local Ai models. Long context window. Proper tools callings. Runs privately on your device.
25 views 0 likesModel Context Protocol server that integrates AgentQL's data extraction capabilities.
14 views 0 likesAI that ships your tickets.
13 views 0 likesMetadata-driven CLI for AI Agent Bots — 48 operations across 7 domains, structured JSON envelope I/O, zero interactive prompts.
12 views 0 likesAn open-source, extensible, self-hosted agent workspace with multi-runtime support for Codex, Claude Code, and more, plus reusable local apps for custom interfa…
13 views 0 likesOpen-source Windows desktop client and GUI for DeepSeek Harness — zero-setup installer with Codex, plugins, skills, SSH, mobile remote access, and 11 skins.
12 views 0 likesThe open-source AI workbench for scientific research
14 views 0 likesDeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
14 views 0 likesA Fully free agentic browser driver for AI , few tools, full control, real stealth, top-tier token efficiency.
12 views 0 likes