LLM Mart Basic

Live debugging workflow - reproduce first, DebugMCP breakpoints, conversational state questions, isolated repair branch, before/after tests, repair report. Use for /debug and hard production bugs.

Multi-source web research with comparison, source quality checks, and a cited report. Use for market scans, tech decisions, due diligence, or “what do sources say about X”.

Audit the software supply chain - vulnerable and outdated dependencies, CVEs, lockfile integrity, license risks, typosquatting, and SBOM generation. Use for /lineage, dependency reviews, or "are our packages safe?" questions.

Full-funnel marketing orchestrator - strategy, content, SEO, social, email, paid, and measurement. Use as the entry point for any broad marketing request, then delegate to specialist skills.

Prepare discovery call questions, live-call structure, and post-call summaries that feed qualification and proposals. Use before and after prospect meetings.

Income / dividend tilt for the Trading Agent OS. Favor durable cash return over narrative growth.

Build, run, inspect, and diagnose Docker containers and Compose stacks safely. Use when debugging images, ports, volumes, or container logs.

Visual theme catalog and template handling for generated documents (PPTX, DOCX, PDF, XLSX). Use whenever a document request names a theme, or provides a template file to adapt.

Create, read, and edit Word (.docx) files - styles, tables, images, headers, and templates - using python-docx. Use whenever a deliverable must be a Word document.

Earnings-event skill for the Trading Agent OS. Fade or follow only with a thesis and a hard stop.

Design newsletters, nurture sequences, and lifecycle emails - structure, cadence, deliverability, and measurement. Use for any recurring or automated email program.

Write professional emails - commercial, administrative, follow-ups, difficult messages - with the right tone in FR/EN/AR. Use for any one-to-one email that matters.

Research companies and people - leadership, revenue signals, tech stack, contacts, and sources. Use for sales intel, partner diligence, or competitive briefs.

Verify claims, statistics, quotes, and citations before publication - with sources and confidence levels. Use before publishing anything containing factual assertions.

Write J+3 and J+7 recruiter follow-ups from the Career inbox and pipeline. Use when an application is silent or the user asks for a relance.

Build or defend a freelance daily rate (TJM) from the Career profile, market, and mission scope. Use for freelance pricing, rate cards, and counter-offers.

Build, run, and debug frontend, backend, and database projects end to end in the workspace (plan, investigate, code, execute, verify). Use for Dev mode sessions, scaffolding apps, fixing bugs, and running dev servers.

Optimize content to be cited by ChatGPT, Gemini, Perplexity, and AI Overviews (GEO). Use when the user wants visibility in generative answers, not just blue links.

Full git workflow for developers: status, staging, commits, branches, push/pull, merge/rebase, conflict resolution, stash, history (log/blame/bisect), remotes, tags, worktrees, cherry-pick, and recovery with reflog. The everyday operations live in the git tool; this skill covers

Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.

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.

Periodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint report.

Sanctioned lane for non-behavioral work — docs-only edits, dependency bumps, reverts. Type-scaled gates; no TDD demanded of prose.

{{SKILL_ENTRY:post-merge-cleanup}}

Show the codeArbiter command catalog — the public command list and what each routes to.

{{SKILL_ENTRY:commit-gate}}

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.

{{SKILL_ENTRY:context-check}}

{{SKILL_ENTRY:context-creation}}

{{SKILL_ENTRY:debug}}

{{SKILL_ENTRY:decompose}}

Verify the active host install, package, command ownership, enforcement{{IF:pi}}, wrapper self-test, and active-dispatch coverage gap{{ELSE}}, and harmless live-fire probe{{END}}. Read-only.

Start a feature: brainstorm a spec, get it approved, then drive it test-first through the pipeline. The one entry to implementation.

Fix a confirmed bug: a failing regression test first, then a minimal fix, then the rest of the tdd gates.

Opt this repo into codeArbiter — scaffold the root-level .codearbiter/ state store.

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.

Sanctioned, logged bypass of a gate or hard rule — one audit line, then proceed.

{{SKILL_ENTRY:finishing-a-development-branch}}

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.

Trim transcript clutter to extend session lifetime — analyze, prune a copy, or toggle the after-each-turn service. Dry-run by default; gains land at resume/compaction, not the current turn.

{{SKILL_ENTRY:decision-variance}}

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

Agent OS: the agent gets smarter on its own. We just hold the line: the grading command and expected result never make it into the success contract we hand it.…

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

:memo: Vimlike Modal Text Editor in Rust

CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.

Hermes Agent memory plugin/provider for scope-aware recall, SQLite truth, LanceDB semantic search, and hybrid retrieval.

For You Agent——AI 时代的个人随身数字人格。把你的模型、AI 账号、技能、提示词和工作方式，带到每一个 AI 工具里。

A coding agent: give it a prompt and it reads, writes, runs commands, and searches code in a loop until the work is done, using native tool-calling across OpenA…

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and…

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

DeepSeek Harness Desktop (dsh-desktop). EAC: Embracing All Creation (揽尽万象). Bundled Node.js runtime with full dsh-CLI kernel, one-click startup, 10 built-in UI…

See your agent think. Zero-config observability & governance for 26 AI agent runtimes: Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Gemini CLI, Cline, Ope…

Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP…

Yet another coding agent harness, lightweight and written in go.

a coding Agent from pi. ∞ providers, sub-agents, hashline edits, and a permission gate

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting…

🧠 Leon is your open-source personal assistant.

The Station, an open-world multi-agent environment that models a miniature scientific ecosystem.

The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol

VelaTerm = iTerm2 + Codex, The Best Terminal for AI Coding