原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

skills Skill

代码仓库 ↗

作者:open-mercato★ 279 (whole repo)42 个 skill

★ Stars are for the whole repo, not each skill

Pick the skill to install

What it does

This repo is a collection of 42 skills

  • Connects Instruction files the AI reads
  • Account or key Not confirmed (README mentions a key or .env file)
  • Category 写代码
Maker’s original description
Enterprise AI Engineering skills we coined at Open Mercato (1.2M+ lines of code ERP built with AI)
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。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/skill/open-mercato-skills.svg)](https://mcp.popnx.com/en/skills/open-mercato-skills)

可搭配使用

在同一工作中把 AI 连到服务的 MCP

REA

Reverse engineer anything from your terminal or agent with one CLI and MCP server.

作者:morluto广泛使用↓ 38.9万/周★ 46.9万7天前更新

MCP · 连接服务在你的电脑上运行

Fallow

Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.

作者:fallow-rs广泛使用↓ 244.1万/周★ 5383今天更新

MCP · 连接服务在你的电脑上运行

相似的 Skill

同类工作,排序与 Skill 列表相同

与相似项目对比
本项
skills
reaandrej-karpathy-skillsgraphifyMoneyPrinterTurbo
作者open-mercatomorlutomultica-aiGraphify-Labsharry0703
Skill 数421111
GitHub 星标279468,733234,332150,287144,566
最近代码更新2026年11月19日2026年11月19日2026年4月20日2026年11月18日2026年11月18日
许可证MITMIT–Apache-2.0MIT

open-mercato 提供的 42 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

This set has 42 skills, too many to install at once: every installed skill’s description loads into every chat, so the AI picks the wrong one more easily. Pick only the ones you use from the list below

  • om-apply-upgrade-notes

    Use when upgrading the skills collection, e.g. 'apply the upgrade notes'. Sync installed tracker and browser descriptors while preserving local edits, check pipeline config and installed artifacts, and report custom-provider gaps and changes.

  • om-approve-merge-pr

    Approve (submit an approving review) and squash-merge a PR given only its number, refusing when the QA gate or a blocking label forbids it. Routes fixable blockers to om-auto-fix-pr (red CI via its --ci-only mode, or conflicts and review problems via the full loop). Optionally file a follow-up issu…

  • om-auto-continue-pr

    Use when an open PR needs unfinished work resumed, e.g. 'continue PR 123'. Claim it and continue its execution plan in an isolated worktree, or reconstruct a plan from the PR context when none exists. Validate and update the same PR; long plans hand off to om-auto-continue-pr-loop.

  • om-auto-continue-pr-loop

    Use when resuming a long om-auto-create-pr-loop run, e.g. 'resume PR 123 from its next step'. Claim the PR, resume its PLAN.md Tasks in an isolated worktree, preserve per-step commits and checkpoint tests with UI screenshots, then run the full gate. Keep spec-only PRs design-only; use om-auto-conti…

  • om-auto-create-pr

    Use when a task should be implemented autonomously and delivered as a PR, e.g. 'build this and open a PR'. Write a tracked execution plan, implement in an isolated worktree, run configured validation, and apply pipeline labels. Long plans hand off to om-auto-create-pr-loop; resume via om-auto-conti…

  • om-auto-create-pr-loop

    Use for long, multi-step tasks needing strict tracking and resumability, e.g. 'implement this spec step by step'. Create a run folder, commit each Step, verify checkpoints with integration tests and UI screenshots, then run the full gate and open a ready labeled PR. Resume via om-auto-continue-pr-l…

  • om-auto-fix-issue

    Fix or implement a tracker issue end to end from a single command — takes an issue id or a plain problem description (filed first via om-prepare-issue), classifies, then drives the bug autofix chain (om-verify-in-repo, om-root-cause, om-fix, om-open-pr, om-auto-review-pr, om-auto-qa-pr for UI fixes…

  • om-auto-fix-pr

    Drive an open PR to merge-ready from its number — merges the latest base, then loops review-autofix (om-auto-review-pr), built-in CI stabilization, and UI verification (om-auto-qa-pr) until approvable, green, and QA-evidenced. A --ci-only mode drives just CI green on a PR or a plain branch. Files f…

  • om-auto-implement-spec

    Implement an existing spec and ship a verified, reviewed, ready PR. Resolves the spec by path, name, issue, or spec-PR number (clean stop with candidates when not found). A spec PR stays design-only — implementation ships on its own PR referencing it. Delegates to om-auto-create-pr (om-auto-continu…

  • om-auto-manage-issues

    Use when existing issues need triage or clearer requirements, e.g. 'clean up these issues'. Apply SDLC labels, clarify issues and screenshots, post prep analysis, check Definition of Ready, and flag missing feature specs; optionally write them with --write-missing-specs. Handle one issue or a batch…

  • om-auto-qa-pr

    Use when a PR's UI needs browser QA, e.g. 'test PR 123 in the browser'. Ensure review first, capture screenshots and a pass/fail report through the configured browser provider, and optionally post evidence or self-QA labels without changing source. Also supports local QA without a tracker.

  • om-auto-review-pr

    Use when a PR needs review or re-review, e.g. 'review PR 123'. Review code or a spec-only design in an isolated worktree, submit approve/request-changes, and manage pipeline labels. Fix/test/re-review automatically for the automation's own PRs or with --autofix; hand other authors the findings.

  • om-auto-update-changelog

    Draft a CHANGELOG.md release entry in an emoji-driven format for every PR merged since the last release, then delegate to om-auto-create-pr so it lands as a docs PR against the configured base branch. Honors the Supersede Credit Rule and verifies every credit against commit authorship, so carry-for…

  • om-auto-write-spec

    Autonomously turn a brief or FR issue into a spec landed on a ready PR — runs om-spec-writing --autonomous (defaults posted for override), attaches UI mockups and current-app screenshots as PR evidence when a browser provider exists, applies full SDLC labels, and emits PR/spec markers for chaining…

  • om-backlog

    Turns a product brief (its Scope and Key flows) or a spec's Phasing into a tracker backlog — epics, stories with acceptance criteria, tasks — with stable ids in titles, epic checklists, and Epic links, filing every issue through om-prepare-issue so dedupe, SDLC labels, and rationale come for free.…

  • om-brainstorm

    Divergent conversation before any artifact exists — open questions one at a time, alternatives including building nothing, converging on a routing decision and a handoff brief for the next skill. Runs before om-spec-writing and om-prepare-issue. Use when the user says "should we build this", "let's…

  • om-check-and-commit

    Verify that the current branch is ready to publish by running every configured validation command in order, fix straightforward failures (including locale-file drift when the repo checks it), and once everything passes commit and push the current branch. Use when the user asks to check the branch,…

  • om-close-fixed-issues

    Close the tracker issues that recently merged PRs authoritatively fixed — via `fixes`/`closes`/`resolves` keywords or `closingIssuesReferences` — and post informational comments on issues whose PRs were closed without merging or merged into a non-base branch. Use for post-merge housekeeping and rel…

  • om-code-review

    Use when a diff, branch, or PR needs a correctness and security review, e.g. 'review this diff'. Run validation and the built-in plus repository checklist, check breaking changes and quality, and return severity-ranked findings with an approve/request-changes verdict. Powers om-auto-review-pr and o…

  • om-create-skill

    Author a new OM skill from a brief, or split an oversized SKILL.md into layered references/ files — conservatively, behind the lint + completeness gate. Knows the layering philosophy, lint invariants, tracker abstraction, and the cross-skill contract, so output matches house conventions. Use for "c…

  • om-discover

    Guide a product discovery conversation and write product-brief.md with the problem, evidence, scope, decisions, and the next uncertainty to resolve. Use for product discovery, defining a product, or refreshing its brief. Supports existing products, client ideas, and own ideas.

  • om-fix

    Use when a confirmed issue has an om-root-cause brief ready to implement, e.g. 'apply this issue fix'. Used by om-auto-fix-issue. Claim the issue, make the minimal change, add regression tests, and run configured validation. Leave commit, push, and PR creation to om-open-pr.

  • om-followup-issue-from-pr

    Turn a PR into tracked follow-up work — paste a PR or PR-comment link to extract the actionable ask and open a follow-up issue assigned to the @-mention or PR author; for a PR adding a design doc, it opens the missing `Implement:` tracking issue instead. Use for "make a follow-up issue", "create an…

  • om-integration-tests

    Use when live-app integration or E2E tests need running, creating, or debugging, e.g. 'add browser coverage for this flow'. Explore with the configured browser provider, preserve repository-native runners, reuse the shared test environment, and diagnose failures from concrete artifacts.

  • om-merge-buddy

    Use when you need a read-only view of which PRs can merge, e.g. 'what is ready to merge?'. Scan open PRs through the configured tracker, assess labels, reviews, CI, and mergeability, then report ready PRs and those close but blocked.

  • om-mockup-prototype

    Build a neutral clickable low-fi prototype from a product brief during discovery, after the first synthetic panel and before refreshing the brief or drafting a backlog. Preserve business rules and explicit assumptions, simulate the chosen flow locally, and verify navigation and relevant states in a…

  • om-open-pr

    Use when validated changes must ship as a PR, e.g. 'open a PR for this'. Commit and push, reuse an existing PR or open a ready PR against the configured base branch, apply SDLC labels and rationale, and hand back issue-driven claims. Emit PR and Issue chaining references.

  • om-pipeline-retro

    Classify finished pipeline runs from the configured tracker — clean single pass, hard recovery, loop checkpoints, or cause not recorded — and rank what the second passes cost in wall-clock hours. Read-only; hands the top cause to om-prepare-issue. Use for "pipeline retro", "why is our pipeline slow…

  • om-pr-autopilot

    Diagnose what state one open PR is actually in — unfinished plan steps, missing review, unresolved conversations, red CI, base conflicts, missing QA evidence, merge-ready — then run the matching chain of om-* skills in order and publish a status report. Use for "finish PR 123", "what is left on PR…

  • om-prepare-issue

    Create one well-formed tracker issue from a brief without implementing it — dedupes against existing issues and PRs, links a covering spec (authoring one via om-auto-write-spec on a design-only PR when a feature needs it), attaches user-provided images as tracker evidence, otherwise embeds step-by-…

  • om-prepare-test-env

    Use when tests or browser QA need a reusable local environment, e.g. 'set up the test app'. Discover the stack, generate cross-platform launch scripts, provision the configured browser provider autonomously, and write the shared test-env descriptor for UI and integration-test skills.

  • om-qa-buddy

    Runs a manual QA session for a PR, issue, or branch — publishes an interactive runbook the tester works through in parallel from the moment a plan exists, updated with AI verdicts and bugs at the end. Never touches the tracker itself. Unlike `om-auto-qa-pr`'s automated sign-off, this is human-in-th…

  • om-review-prs

    Use when open PRs need a review sweep, e.g. 'review the unreviewed PRs'. Review newest first through om-auto-review-pr, respecting claim locks. Run sequentially by default; --subagents selects a fresh reviewer per PR and --parallel N bounds concurrency.

  • om-root-cause

    Use when a confirmed tracker defect needs read-only diagnosis before implementation, e.g. 'find the cause of issue 123'. Used by om-auto-fix-issue after triage. Locate the bug and minimal change surface, then return a summary, files to change, approach, and risks for om-fix.

  • om-setup-agent-pipeline

    One-time pipeline configurator. Inspects the repo (default branch, validation scripts, labels), asks a few questions, writes .ai/agentic.config.json — the file every other skill reads — installs the tracker descriptor, and generates missing project docs (SDLC.md, CODE_REVIEW.md, BACKWARD_COMPATIBIL…

  • om-setup-discovery-pipeline

    Use when a repository needs product discovery gates alongside its delivery pipeline, e.g. 'set up discovery'. Configure product roles and settings, extend SDLC.md with readiness and protected-decision rules, and add the research directory and AGENTS.md routing. Set up delivery first if missing; re-…

  • om-spec-writing

    Write and review feature specifications to staff-engineer standards. Skeleton-first drafting with a hard Open Questions gate, research against market leaders, an implementation breakdown into phases and steps that feeds om-auto-create-pr, and a severity-ranked architectural review format. Use when…

  • om-synthetic-users

    Builds a panel of personas from real material, interviews them under decision pressure (never stated preference), and walks a flow through their eyes — on a brief, a spec, a prototype, or the running app. Fresh panels, repeated runs, believe only what repeats; saturation and a parity check against…

  • om-ux-review-pr

    Use when a PR's UI needs an evidence-backed design review, e.g. 'review the UX of PR 123'. Walk changed screens in a browser and rank findings by user impact with evidence, patterns, trade-offs, and acceptance criteria. Use --guard for static design-contract checks, or --guard --health for reposito…

  • om-ux-setup

    Use when a repository needs its design contract extracted or refreshed, e.g. 'set up UX checks' or after design-system changes. Write tokens, components, screen archetypes, and conventions to .uxproof/, including versioned dependency design systems, so UX skills assess against this repository's sys…

  • om-ux-shape

    Turn a vague product, UI/UX, or AI feature idea into a decided direction. Use when shaping a feature, simplifying an overcomplicated flow, deciding whether and how to use AI, defining screen states, planning validation, or preparing a design handoff for engineering.

  • om-verify-in-repo

    Use when a tracker issue needs read-only triage before autofixing, e.g. 'check whether issue 123 still needs a fix'. Used by om-auto-fix-issue. Confirm a real, still-unfixed defect on the current branch; stop with NO_ACTION_NEEDED if already fixed, claimed by someone else, covered by an open PR, or…

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 CodeCodexCursorOpenCode

依据开发者 README 和 repo 中的文件夹

安装

Pick a skill first

This repo has 42 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP

Let the AI install it
Upload to claude.ai

Go to the skill list ↑

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

来自 GitHub

GitHub 星标
279
Stars are for the whole repo, not each skill
开发者
open-mercato
许可证
MIT
最近代码更新
2026年11月19日
repo 中的 SKILL.md 文件(含译本和模板)
42
主题
ai-engineering, ai-skills