LLM Mart Basic

缺陷修复方法论唯一入口：口喷 bug 定位直修；implement-test-review 循环内的反馈修复也走本 skill（循环内分支，原 impl worker 执行）。触发：修 bug / 有个 bug / 报错了 / 行为不对 / fix / /eo-fix。 NOT FOR: 明确的业务变更（走 /eo-change）。

在 /clear 之前生成最小可恢复快照到 tmp/eo/handoff/<topic>.md，让下一个会话载入这一个文件就能从当前节点继续。优先记录任务状态、关键口径、下一步分叉，主动丢弃探索过程。触发：handoff / 存一下进度 / 我要 clear / /eo-handoff。 NOT FOR: 机械压缩对话流（用内置 /compact）。

按 change.md 的 TODO 分批落地代码，批末自验对应 AC。触发：实现 / 写代码 / implement / /eo-implement。 NOT FOR: bug 与反馈修复（口喷 bug 与 test/review/acceptance 循环内反馈一律走 /eo-fix）；变更起草（走 /eo-change）。

eo 流程总控：按用户意图圈一段（入口节点 → 出口节点 → 收敛标准），把 eo-change / eo-implement / eo-archive 及可选闸门（eo-change-review / eo-test / eo-review）派发到可插拔执行基底上推进至收敛，窗口化汇报进度。触发：eo-loop / 串起来跑 / 循环推进到收敛 / 总控调度 / /eo-loop。 NOT FOR: 单点动作（直接调对应 eo-* skill）；派出去不再监督的完全交接（orca-cli full handoff）；bug 口喷（/eo-fix）。

eo-skills 在当前仓库的总入口：生成 .eo-project.json、初始化项目管理侧（roadmap）和代码侧最小骨架（eo-doc/），以及 agent 配置注入。触发：启动项目 / 初始化项目 / 新建项目 / /eo-project-init。

项目记忆的统一写入口：经验教训（lessons/）与关键决策（decisions/），带 INDEX 与检索锚点，供 eo-change / eo-fix / eo-recall 消费。通过 .eo-project.json 定位。触发（仅用户明确要求记录时）：把这个坑记下来 / 记条经验 / lesson learned / 把这个决策记下来 / 记录决策 / reindex lessons / reindex decisions / /eo-project-record。NOT FOR: 对话提到踩坑或决策但用户未要求记录；待办类（走 /eo-bac

只读的回忆与解释入口，分层作答带出处。触发：这个功能当时怎么设计的 / 这段逻辑怎么实现的 / 当初为什么这么定 / 帮我回忆 / recall / /eo-recall。 NOT FOR: 修 bug（/eo-fix）、发起变更（/eo-change）、维护文档（/eo-doc-manager）。

按需代码审查：风险信号命中或用户点名时，对已实施代码做 AC 逐条核对 + 代码质量审查，产简版 review.md（P0/P1/P2）。触发：review / 代码审查 / 再找双眼睛看看 / /eo-review。 NOT FOR: change 方案审查（/eo-change-review，代码还没写时用）；默认主路（无信号时不强制）。

按需独立测试视角：风险信号命中或用户点名时，对已实现 change 做测试审计、补缺与重验证，产简版 test.md。严禁修改业务代码。触发：找双新眼睛跑测试 / 独立验证 / 给这个 change 补测试 / /eo-test。 NOT FOR: 与 change 无关的日常跑测试或补单测（直接做即可，不产报告）；默认主路的自验（归 eo-implement）。

接口级测试时使用——从 OpenAPI/Swagger 文档或用例 Schema 中可自动化的接口用例出发，覆盖参数、边界、鉴权、幂等、并发、错误响应与数据一致性，产出可执行的 API 测试脚本与运行结果；含接口压测承接（k6，类型矩阵轴 1 执行层）。不用于：Web UI 流程（automated-e2e-testing）、手动用例编写（test-case-writing）。

将手动测试用例转为 Playwright E2E 测试并执行时使用；含写自动化前的业务熟悉踩点、Page Object/Helper 编写、执行中的 Bug 证据收集与报告条目记录。不用于：纯 API 接口测试（api-testing）、以理解系统为目的的独立探索会话（exploratory-testing）、已确认 Bug 的根因分析（bug-analysis）。

对已确认的 Bug 做根因定位、影响分析、回归建议时使用——复现 → 读代码定位根因 → 影响五面分析 → 回归建议，条目（根因/影响/Severity 依据/修复建议）追加进测试报告。不用于：仅收集 Bug 证据（automated-e2e-testing / api-testing）、疑似未定性缺陷（test-case-writing 的 Cx 记录）。

qa-skills 共享知识库，安装依赖单元（非触发 skill）：承载被其余 10 个 skill 以相对路径引用的方法、规则、模板与脚本（可执行性标准、证据分级、风险模型、类型决策矩阵等）。仅在 qa-skills 系列 skill 工作流中被引用读取；任何具体测试任务都不要独立触发本 skill，独立使用无意义。通过 npx skills 等安装器单独安装其他 qa-skills skill 时，必须同时安装本 skill，否则引用路径断裂。

需求不完整、系统陌生、文档不足时，发起以理解系统/发现风险为目的的独立探索式测试会话时使用——charter 驱动（目标 → 探索 → 记录），产出探索笔记（系统理解/风险清单/测试想法）作为需求建模输入或独立交付。不用于：为写自动化踩点的小规模探索（automated-e2e-testing 工作流零）、按既有用例执行（执行类 skill）。

端到端测试的唯一入口：用户说"帮我测试这个需求/功能"、"把这个功能完整测一遍"时，编排需求理解→测试策略（风险与类型决策）→用例→审查→执行→Bug 分析→回归→报告的完整流水线，产出落盘、可断点续跑。只要单阶段产出（如"帮我审一下这份用例"）→ 直接用对应阶段 skill，不用本 skill。

代码变更（diff/Bug 修复/需求变更）后判断应回归哪些测试时使用——沿"改动文件 → 改动函数 → 受影响功能 → 受影响用例"分析链，基于用例 Schema 的追溯映射产出分级回归清单。不用于：用例文件本身的增量修改（test-case-writing）、长期回归策略（test-strategy）。

系统性建模某个需求/系统时使用——从 PRD、设计/API 文档、Bug、Issue、代码中提炼目标、范围、角色、规则、异常、依赖与不明确项，产出结构化需求模型（含澄清记录与用户裁决）。不用于：已有需求模型直接写用例（test-case-writing）、"怎么测"的策略决策（test-strategy）、端到端流水线（qa）。

审查已有测试用例（存量资产、他人编写、AI 产出）的覆盖与可执行性时使用——先建可测点基准，再独立评估覆盖、可执行性与正确性，直接修订用例文件并留审查记录。不用于：从零写用例（test-case-writing）、写时自审（其阶段四）、端到端流水线（qa）。

从需求文档、API 文档、Bug 报告或代码仓库产出可执行的手动测试用例（markmap）时使用——代码优先：索取仓库、先代码审查找潜在 bug 再写用例，并抽取机器可读 Schema。不用于：需求建模（requirement-analysis）、测试策略（test-strategy）、独立审查（test-case-review）、自动化脚本（automated-e2e-testing / api-testing）。

回答"这个功能应该怎么测"时使用——风险评级挂证据（Risk Map），翻译成功能域+类型域两域范围与深度：类型域十轴全轴必答（脚本扫描信号+预填修订），include挂信号、exclude挂理由、full有预算上限。不用于：已有策略直接写用例（test-case-writing）、需求建模（requirement-analysis）、端到端流水线（qa）。

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.

Run autonomous hunt loop on a target — scope check → recon → rank surface → hunt → validate → report with configurable checkpoints. Usage: /autopilot target.com [--paranoid|--normal|--yolo]

Build an exploit chain — given bug A, finds B and C to combine for higher severity and payout. Knows common chain patterns: IDOR→ATO, SSRF→cloud metadata, XSS→ATO, open redirect→OAuth theft, S3→bundle→secret→OAuth. Usage: /chain

Active vulnerability hunting. Two-track dispatcher — asks Red Team vs WAPT, hands off to hunt-dispatch skill and sibling commands. Usage: /hunt target.com | /hunt *.target.com | /hunt targets.txt [--vuln-class X] [--source-code P] [--chrome]

On-demand intelligence fetch for a target — CVEs, disclosed reports, new features. Pulls NVD/GitHub-Advisory CVEs + bundled disclosed reports + hunt memory context. Usage: /intel target.com

Inspect or rotate the autopilot ledger JSONL files (findings.jsonl, negatives.jsonl). Caps file size and keeps N rotated backups so memory does not grow unbounded.

Pick up a previous hunt on a target — shows hunt history and untested surface from the autopilot ledger. Usage: /pickup target.com

Run full recon pipeline on a target — subdomain enum (Chaos API + subfinder), live host discovery (dnsx + httpx), URL crawl (katana + waybackurls + gau), gf pattern classification, nuclei scan. Outputs to recon/<target>/ directory. Usage: /recon target.com

Optional manual note on a target or the last confirmed finding. Capture is automatic during autopilot; this is for extra context. Usage: /remember

Write a submission-ready bug bounty report. Generates H1/Bugcrowd/Intigriti/Immunefi format with CVSS 3.1 score, proof of concept, impact statement, and remediation. Run /validate first. Usage: /report

Mandatory pre-flight scope check — verify an asset is in scope BEFORE any HTTP touch. Deterministic (deny-wins, default-deny) via engine/scope.py against the engagement's scope.md. Blocks out-of-scope testing. Usage: /scope <asset> [<asset> ...]

Show ranked attack surface for a target from its recon manifest + hunt memory. Deterministic backing is `cbh surface <target>` (reads recon/<target>/manifest.json); LLM layer adds ledger signal. Usage: /surface target.com

Meme coin and token security scan — checks for rug pull vectors (hidden mint, honeypot, fee manipulation, LP lock bypass, authority retention, bonding curve exploits, fake renounce, sandwich amplification). Manual 8-class grep audit (with an optional automated scanner if present). Usage: /token-scan <contract_path_or_dir> [--chain solana]

Quick 7-Question Gate triage on a finding before writing a report. Kills N/A submissions before they happen. Faster than /validate — for quick go/no-go decisions. Usage: /triage

Validate a finding — runs 7-Question Gate + 4-gate checklist. Kills weak findings before report writing. Prevents N/A submissions that hurt validity ratio. Usage: /validate

Smart contract security audit — runs through 10 bug class checklist (accounting desync, access control, incomplete path, off-by-one, oracle errors, ERC4626, reentrancy, flash loan, signature replay, proxy/upgrade). Applies pre-dive kill signals first. Generates Foundry PoC template for confirmed findings. Usage: /web3-audit <contract.sol>

Crabbox is a single CLI (`crabbox`). Commands are top-level, not nested under a

`crabbox actions` prepares a leased box from your repository's own GitHub

See [Runtime adapter stack](../features/runtime-adapter-stack.md) for the

`crabbox admin` groups trusted operator controls for coordinator-backed leases and the cloud resources behind them. Use it to inspect every lease the broker tracks, reconcile expired leases against live cloud state, force-release or delete a backing server, print provider IAM pol

`crabbox artifacts` turns a desktop lease into durable QA evidence: it collects

Make any song you can imagine

Leading AI-powered video generation platform that specializes in creating hyper-realistic talking avatars

Hermes Agent is an open-source, self-improving autonomous AI agent developed by Nous Research

Kilo Code is a popular, open-source AI coding agent and "agentic engineering" platform designed to help developers build, refactor, and debug software faster

General-purpose agent in one static Go binary. ReAct loop, ACP server for IDEs, OpenAI-compatible REST API with embedded web UI, Telegram gateway, cron schedule…

Autonomous agent framework with structured memory, safety hooks, and loop management. Built by the agent that runs on it.

TSP自托管、零运维的 A 股「选股 + 监控 + 回测」量化工作台 | 基于 TickFlow 数据源 | LLM能力驱使策略定制+个股分析+复盘 | 自由接入第三方数据源与个性化扩展数据 | 个人开源 ,非TickFlow官方项目

Curated, verified Agent Skills powered by ModelStudio.

Run Claude Code, Codex, Antigravity, Cursor Agent and OpenCode as one runtime — persistent sessions, multi-agent councils, an OpenAI-compatible endpoint, an MCP…

pi had nothing (nothing), so I made something (something) — sorry mariozechner-senpai, I went ahead and lovingly soiled your pure pi for you. opinionated fork o…

A persistent workspace for development work that self-improves and continues beyond one session.

Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.

📚 A zero-dependency, git-backed micro-lesson library for AI Agents to asynchronously share and search verified debugging experience. Python stdlib only. | http…

Deterministic, local-first memory and guardrails for AI coding agents with no LLM in the hot path.

Deterministic spec-orchestration for local LLMs in the pi coding agent — drives prompts through refine→research→grill→compose→critique, with bundled web/docs/fe…

Native Safari browser automation for AI agents. 97 tools via AppleScript — zero overhead, keeps logins, runs silently in background. Drop-in alternative to Chro…

Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.

Git for agent memory. Branches, diffs, PRs, and rollback for what your agents know.

Multi-Provider AI Gateway - No personal logs by design. Model autodiscovery, Failover groups, High availability, Android companion app, and more - "Because we h…

Production-grade MCP server for MikroTik RouterOS with secure AI-native network automation.