LLM Mart Basic

@llm-mart · Joined Jun 2026

0 Followers 0 Reputation 13630 Contributions
Claude Skill eo-fix

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)。

0
Claude Skill eo-handoff

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)。

0
Claude Skill eo-implement

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)。

0
Claude Skill eo-loop

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)。

0
Claude Skill eo-project-init

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。

0
Claude Skill eo-project-record

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

0
Claude Skill eo-recall

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)。

0
Claude Skill eo-review

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)。

0
Claude Skill eo-test

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)。

0
Claude Skill api-testing

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)。

0
Claude Skill automated-e2e-testing

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)。

0
Claude Skill 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)。

0
Claude Skill core

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。

0
Claude Skill exploratory-testing

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)。

0
Claude Skill qa

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。

0
Claude Skill regression-testing

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)。

0
Claude Skill requirement-analysis

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)。

0
Claude Skill test-case-review

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)。

0
Claude Skill test-case-writing

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)。

0
Claude Skill test-strategy

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)。

0
/show-ticket Show ticket

Display comprehensive ticket information including history, actions, and related entities

0
/sla-dashboard Sla dashboard

View SLA status across tickets, including approaching breaches and at-risk tickets

0
/update-ticket Update ticket

Update fields on an existing HaloPSA ticket including status, priority, and assignment

0
/create-deal Create deal

Create a new deal in HubSpot with company association

0
/log-activity Log activity

Log a note or create a task on a HubSpot contact, company, or deal

0
/lookup-company Lookup company

Find a HubSpot company by name or domain and show associated contacts and deals

0
/pipeline-summary Pipeline summary

Summarize the HubSpot deal pipeline - deals per stage, total value, and expected close dates

0
/search-contacts Search contacts

Search HubSpot contacts by name, email, or company

0
/search-deals Search deals

Search HubSpot deals by name, stage, or company

0
/find-company Find company

Find a company in Hudu by name

0
/get-password Get password

Retrieve a password from Hudu (with security logging)

0
/lookup-asset Lookup asset

Find an asset in Hudu by name, hostname, serial number, or IP address

0
/search-articles Search articles

Search Hudu knowledge base articles by keyword or phrase

0
/agent-inventory Agent inventory

List and filter Huntress agents across organizations

0
/billing-report Billing report

Generate a Huntress billing summary for a period

0
/incident-triage Incident triage

Triage open Huntress incidents by severity

0
/investigate-incident Investigate incident

Deep dive investigation into a specific Huntress incident with remediations

0
/org-health Org health

Organization health check covering agents, incidents, and escalations

0
/resolve-escalation Resolve escalation

Review and resolve a Huntress escalation

0
/compliance-report Compliance report

Generate an ImmyBot software-compliance scorecard for a tenant or the whole fleet

0
Suno

Make any song you can imagine

39 views 0 likes
HeyGen

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

37 views 0 likes
Hermes Agent

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

36 views 0 likes
Kilo Code

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

34 views 0 likes
Coddy Agent

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…

20 views 0 likes
Boucle Framework

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

20 views 0 likes
Tick Stock Panel

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

15 views 0 likes
Skills

Curated, verified Agent Skills powered by ModelStudio.

18 views 0 likes
Claw Orchestrator

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

17 views 0 likes
Senpi

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…

14 views 0 likes
KiroCrew

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

35 views 0 likes
Remnic

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

20 views 0 likes
MisakaNet

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

28 views 0 likes
OpenLore

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

31 views 0 likes
Pi Task

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

20 views 0 likes
Safari Mcp

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

34 views 0 likes
Agentlas OS

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

15 views 0 likes
Amfs

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

35 views 0 likes
Model Hotel

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

16 views 0 likes
MikroMCP

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

31 views 0 likes