What it does
This repo is a collection of 24 skills
- Connects Instruction files the AI reads
- Account or key Not confirmed yet (README not read yet)
- Category 其他
Maker’s original description
MCP server for GitLab: 288 tools for projects, MRs, issues, pipelines, wikis and more via the GitLab REST/GraphQL API给作者:在 README 中加徽章
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/zereight-gitlab-mcp)相似的 Skill
同类工作,排序与 Skill 列表相同
| 本项 gitlab-mcp | llmfit | claude-video | VideoCaptioner | claude-cookbooks | |
|---|---|---|---|---|---|
| 作者 | zereight | AlexsJones | bradautomates | WEIFENG2333 | anthropics |
| Skill 数 | 24 | 1 | 1 | 1 | 4 |
| GitHub 星标 | 2,109 | 39,018 | 20,999 | 16,544 | 54,763 |
| 最近代码更新 | 2026年11月16日 | 2026年11月16日 | 2026年9月25日 | 2026年9月12日 | 2026年11月5日 |
| 许可证 | MIT | MIT | MIT | GPL-3.0 | MIT |
zereight 提供的 24 个 Skill(指令集),AI 读取后照做 · 不是 MCP server
Pick the skill to install
Install only the ones you use. Open a skill to see how to install it
Install the whole set (24)
If you want every one, let the AI install them in one go. Know 2 things first
- Every installed skill’s description is loaded into every chat. The more you install, the easier it is for the AI to pick the wrong one
- Some skills duplicate tools the AI already has built in. Installing only the ones you use works better
Uploading to Claude on the web and apps: you need 24 uploads, one ZIP per skill. Open each skill in the list below to download it
Checked against official docs 2026年11月12日 · Source: support.claude.com, code.claude.com, learn.chatgpt.com, cursor.com
- ai-slop-cleaner
Clean AI-generated code slop with regression-safe workflow. Activate when user says: deslop, anti-slop, AI slop, cleanup slop, clean up this code, remove bloat.
- cancel
Cancel any active OMG mode and clean up state. Activate when user says: cancel, stop, cancelomg, stopomg, abort, kill it, stop everything.
- ccg
Claude-Codex-Gemini tri-model orchestration for multi-perspective analysis. Activate when user says: ccg, tri-model, three models, multi-model, cross-validate, get multiple opinions, compare models.
- coding-standards
Canonical cross-language coding standards reference. Shared rules embedded by reviewer agents. Activate when: viewing coding standards, checking naming rules, reviewing style baseline, consulting style guide, what are the rules.
- deep-dive
2-stage pipeline: trace (causal investigation) then deep-interview (requirements). Activate when user says: deep dive, deep-dive, investigate deeply, trace and interview.
- deep-interview
Socratic deep interview with mathematical ambiguity gating. Activate when user says: deep interview, interview me, ask me everything, don't assume, make sure you understand, ouroboros, socratic, I have a vague idea, not sure exactly what I want.
- gitlab-mcp
Use this skill when working with the GitLab MCP server tools for merge requests, issues, repositories, pipelines, work items, variables, dependency proxy, vulnerabilities, webhooks, search, CI catalog, and related GitLab workflows.
- gl-cli
Use GitLab from the terminal without registering an MCP server. Covers authenticating the zereight-mcp-gitlab CLI (PAT or OAuth device flow) and reading merge requests, diffs, discussions, issues, and pipelines. Use when the user asks about a GitLab MR/issue/pipeline and no GitLab MCP tools are ava…
- omg-autopilot
Full autonomous execution from idea to working code. Activate when user says: autopilot, auto-pilot, autonomous, build me, create me, make me, full auto, handle it all, or "I want a/an..."
- plan
Strategic planning with optional interview workflow. Activate when user says: plan this, plan the, let's plan, make a plan, how should we approach.
- ralph
PRD-driven persistence loop until task completion with verification. Activate when user says: ralph, don't stop, must complete, finish this, keep going until done.
- ralplan
Consensus planning with Planner/Architect/Critic iterative loop. Activate when user says: ralplan, consensus plan, consensus planning.
- remember
Promote reusable project knowledge to the right memory surface. Activate when user says: remember this, save this, store this, remember, memorize, keep this for later.
- review
Code review with spec compliance and quality checks. Activate when user says: review this, code review, review my changes.
- security-scan
Rapid security scanning workflow for code changes. Activates a focused security sweep. Activate when: security scan, scan for vulnerabilities, check for secrets, security check, run security audit, check deps.
- self-improve
Autonomous evolutionary code improvement engine with tournament selection. Activate when user says: self-improve, self improve, evolve code, improve iteratively, tournament, benchmark loop, optimize code.
- skill-stocktake
Audit the skill inventory for quality, coverage, and staleness. Detect overlapping, incomplete, or outdated skills and produce a health report. Activate when: skill audit, stocktake, skill inventory, check skills, which skills exist, audit skills, skill quality, skill coverage.
- status
Show current OMG mode status, active agents, and progress. Activate when user says: status, what's running, show progress, current state, active modes, where are we.
- tdd
Test-Driven Development enforcement skill. Activates full TDD mode. Activate when: TDD, test-driven, test first, red-green-refactor, write tests first.
- team
N coordinated agents on shared task list with staged pipeline. Activate when user says: team, spawn agents, parallel agents, coordinate agents, multi-agent, swarm, work together.
- trace
Evidence-driven tracing with competing hypotheses in parallel. Activate when user says: trace this, trace, why did this happen, root cause analysis, investigate why.
- ultraqa
QA cycling workflow - test, verify, fix, repeat until goal met. Activate when user says: ultraqa, qa cycle, fix all tests, make tests pass.
- ultrawork
Parallel execution engine for high-throughput task completion. Activate when user says: ulw, ultrawork, parallel execution, run these in parallel.
- verify
Verify that a change really works before claiming completion. Activate when user says: verify this, check if it works, prove it works.
Skill 和 MCP 有什么不同
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
适用的应用
Claude CodeClaude (เว็บ/แอป)CodexCursorGitHub CopilotOpenCode
依据开发者 README 和 repo 中的文件夹
安装
Pick a skill first
This repo has 24 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP
讨论
提问、分享技巧或报告无法使用。按“有帮助”数量排序。
来自 GitHub
- GitHub 星标
- 2,109
Stars are for the whole repo, not each skill - 开发者
- zereight
- 许可证
- MIT
- 最近代码更新
- 2026年11月16日
- repo 中的 SKILL.md 文件(含译本和模板)
- 24
- 主题
- ai, claude, cursor, devtools, gitlab, gitlab-api, llm, mcp, mcp-server, model-context-protocol