LLM Mart Basic

发版前自动验证闸门——V 验证 + F 修复循环（verdict FAIL → F 改代码 → 跑 audit → V 重验），最大 3 轮直到 PASS。纯只读验证 + 最小修复。

一次挂载 sofagent 全套能力——6 项能力一次到位（注入 · 审计与验收 · 经验 · 回溯 · 巡检 · FDE 三域）（seam: non-seam:plugin-suite）——只编排不重实现——sofagent 约束层在 DSH（DeepSeek Harness）生态的插件形态。

变更机器审阅 + 验收硬门禁——24 规则 + git diff 硬证据 + Turn 停止验收判定（验收不过不放行，开关独立可关）（seam: tools/result + tools/pre-execute + fs/write-intent + agent/turn-stopping）——桥接 @sofagent/audit runRules——DSH（DeepSeek Harness）cordis plugin。sofagent 约束层在 DeepSeek Harness 生态的插件形态。

7×24 巡检 + 健康监测 + webhook 推送（seam: non-seam:host-process）——桥接 @sofagent/daemon startCron——DSH（DeepSeek Harness）cordis plugin。sofagent 约束层在 DeepSeek Harness 生态的插件形态。

经验沉淀——think.md 反思 + Dream Cycle + evolve + instinct→skill + refine（seam: turn/end）——桥接 @sofagent/think generateThinkEntry——DSH（DeepSeek Harness）cordis plugin。sofagent 约束层在 DeepSeek Harness 生态的插件形态。

FDE 进场与能力流通——把企业业务梳理成 AI 能力，并让这些能力在企业内被发布、发现、调用、评价、退役（seam: non-seam:tool-set）——桥接 @sofagent/orchestrator publishCapability / @sofagent/ontology generateOntologyView / @sofagent/core restoreSnapshot——DSH（DeepSeek Harness）cordis plugin。sofagent 约束层在 DeepSeek Harness 生态的插件形态。

启动注入企业约束——四层加载链（seam: agent/pre-step）——桥接 @sofagent/harness buildConstrainedSystemPrompt——DSH（DeepSeek Harness）cordis plugin。sofagent 约束层在 DeepSeek Harness 生态的插件形态。

出错逆序撤销——git snapshot → effect disposer（seam: agent/error）——桥接 @sofagent/core getHistoryFilePath——DSH（DeepSeek Harness）cordis plugin。sofagent 约束层在 DeepSeek Harness 生态的插件形态。

当 FDE 需要对工作流节点做 AI 分类判定时用这个 Skill—— 不是"它是干什么的"，是"什么时候用"。 写错 description = Skill 永远不会被触发。

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Build and configure Cecil static sites, with focused guidance for content, templates, and site generation.

Deliver a change through an approved design contract, sequential implementation, independent review and exact-HEAD release. Use for any Bounded or Architectural change — including a small, one-line behavioral fix, which is the canonical Bounded case — so it gets design approval a

**ANALYSIS SKILL** — Analyze any repository and generate AI-ready configuration — a canonical AGENTS.md, thin per-tool pointer files, skills, CI workflows, issue templates. WHEN: "make this repo ai-ready", "set up AI config", "add copilot instructions", "prepare this repo for AI

Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.

Create, track and update team goals via the Deeplake virtual filesystem at memory/goal/. Use whenever the user mentions a goal, objective, target, milestone, or asks to track progress on something measurable. ALSO use when the user says "task", "todo", "work item", "remind me to"

Query the local code graph (functions, classes, calls, imports) through the Deeplake mount at memory/graph/. Use when the user asks structural questions about the codebase — "what calls X?", "what does Y import?", "where is Z defined?", "what's the architecture / which subsystems

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.

Setup automated synchronization workflows

Resolve synchronization conflicts automatically

Sync GitHub issues to Linear workspace

Sync Linear tasks to GitHub issues

Link pull requests to Linear tasks

Monitor GitHub-Linear sync health status

Synchronize task status with git commits, ensuring consistency between version control and task tracking.

Simulate system performance under various loads with capacity planning, bottleneck identification, and optimization strategies.

Create Linear tasks from pull requests

Test-driven development workflow with Red-Green-Refactor process and branch management

Balance team workload distribution

Automate changelog testing workflow

Analyze and report test coverage

I need you to create an integration testing plan for $ARGUMENTS

Accelerate scenario testing with rapid iteration cycles, confidence intervals, and compressed decision timelines.

Manage project todos in a todos.md file with add, complete, remove, and list operations

Generate troubleshooting documentation

Deep analysis and problem solving mode

Sets up a professional Unity project with industry-standard structure and configurations

Update current git branch name based on analysis of changes made

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat ap…

Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evid…

Ultimate Multi-Agent OS for Autonomous AI NPCs 2026

Personal AI Agent Hub 2026 — Build Your 24/7 Autonomous Assistant

Proven 2026 Multi-Agent AI Review System – Verdict-Driven Quality Control

Slash API Batch: Cut AI Costs by 50% in 2026

Web dashboard for Hermes Agent — multi-platform AI chat, session management, scheduled jobs, usage analytics

Agent Skills for Solopreneurs

AirLLM dramatically reduces inference memory usage, letting 70B large language models run on a single 4GB GPU card

Zero, your trustworthy AI teammate for real work.

一套 DSH runtime，Desktop、Web 与 TUI 三种开发体验。

Open-source operational advisor for ClickHouse — real-time monitoring plus AI-driven index/partition/materialized-view recommendations.

⚙️ TypeScript Style Guide and Agent Skill. A concise set of conventions and best practices for consistent, maintainable code.

Framework for AI agents to build and maintain a digital brain through Obsidian wiki

Apache Maka (Incubating) is a local-first AI agent workspace. Model messages, tool calls, tool results, permission decisions, and termination events are recorde…

Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active H…

Agentic development harness for Claude Code — SPEC-driven plan/run/sync, TRUST 5 quality gates, model+effort routing, and Claude×GLM multi-LLM cost control. Sin…

NocoBase is an open-source AI + no-code platform for building business systems fast. Instead of generating everything from scratch, AI works on top of productio…

An open-source AI coding agent that lives in your terminal.

PawWork — free, open-source desktop AI agent for macOS and Windows. Alternative to Codex App and Claude Cowork. BYOK with 75+ providers, ChatGPT OAuth, local mo…