REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
This repo is a collection of 44 skills
45 agent skills from shipping three live products: decide what to build, build it with Claude Code or Codex, have a second model review it, release it.Wenn du das gebaut hast, füge diesen Code in dein README ein. Das Badge verlinkt auf diese Seite.
[](https://mcp.popnx.com/en/skills/phuryn-product-engineering)MCP-Server, die die KI für dieselbe Arbeit mit Diensten verbinden
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
Gleiche Art Arbeit, sortiert wie die Skill-Liste
| Dieser product-engineering | rea | graphify | archify | security-audit-skill | |
|---|---|---|---|---|---|
| Anbieter | phuryn | morluto | Graphify-Labs | tt-a1i | cloudflare |
| Skills | 44 | 1 | 1 | 1 | 1 |
| GitHub-Sterne | 606 | 461.751 | 148.352 | 96.757 | 73.156 |
| Letzte Codeänderung | 15. Nov. 2026 | 16. Nov. 2026 | 16. Nov. 2026 | 15. Nov. 2026 | 15. Sept. 2026 |
| Lizenz | MIT | MIT | Apache-2.0 | Apache-2.0 | MIT |
44 Skills (Anweisungssammlungen) von phuryn, die eine KI liest und befolgt · kein MCP-Server
Install only the ones you use. Open a skill to see how to install it
This set has 44 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
Showing 30 of 44 See all on GitHub
Writing or restructuring AGENTS.md or CLAUDE.md, adding a rule ('remember this'), or after an agent ignored a rule it had: make each rule get met when it applies.
Planning a SaaS stage, 'what's next', 'where are we', calling a stage done: the detailed path from an idea to production, each stage with its done-when.
Before building, submitting or changing a ChatGPT plugin or Apps SDK app: get it through OpenAI's directory review (auth, package, OAuth, data rules, portal).
'Ask Claude', 'have Claude build or review this': drive Claude Code headless (claude -p) from another agent as a peer, builder or fresh reviewer.
Setting up or changing Clerk sign-in, organizations, roles or billing on Next.js, or sign-in that does nothing or lands wrong: Clerk in production.
'Review this', 'find bugs', 'is this fix safe': review code for defects that matter, correctness first, each finding refuted before it's reported.
'Ask Codex', 'check with Codex', handing Codex a build or review, or stuck between two framings: the Codex CLI as peer, builder or fresh reviewer.
Before spawning a subagent or dispatching a build, review or research, and before trusting its report: the brief, the delegate, parallel runs, the handoff.
'What should we test' or a coverage map: derive the coverage map and missing tests from docs and code; check mode reports staleness.
'Document the app': write or refresh an app's system docs from its code. 'Are the docs right?': check mode, which only reports where docs and code disagree.
Only when the Agent SDK is asked for, an agent needs Claude Code's own tools, or the app already runs it: embed Claude agents in a Next.js app with the Agent SDK.
Building, adding or wiring up an agent or an agent chat inside a Next.js app: embed Claude agents on the Messages API, the default way.
Adding a variable or secret, 'set up production', a domain or a provider token, 'which database is this', a leaked key: dev and production for an AI-built app, backups, incidents.
'What's the status', 'where were we', a progress report or status deck; long work that must survive compaction: multi-hour runs, background jobs, waiting on a decision.
'Ask Grok', 'have Grok build or review this': drive the Grok CLI headless from another agent as a peer, builder or fresh reviewer.
An agent keeps breaking a rule ('it did it again', 'make this impossible', 'add a hook', 'my hook didn't fire'): make it a hook, permission rule or script.
Write the handover a fresh session starts from: the objective, what is true now, the evidence actually obtained, what is left, the open decisions and the next concrete action, reconciled with the disk first. Started by name only: /agent-harness:handover in Claude Code, $agent-harness:handover in Co…
Before 'ship it', a deploy or release, for 'an independent review', and after each fix until a round is clean: a fresh reviewer that never saw the build.
Auditing AI-built code against its docs: where it does what the docs or permissions don't say, access control against documented roles, cited both sides.
Privacy policy, terms, a cookie banner, consent at sign-up, a public front door: legal pages drafted from what the code does, held to it by a test, with the owner's facts and sign-off.
Before adding a remote MCP server or tool to a web product, adding OAuth to it, or listing it in a directory: ship it right the first time, tests included.
Only when a performance audit is asked for (ship-check asks by name; a release proposes, never runs it): static audit of N+1 queries, over-fetching, indexes, caching.
'I have an idea', 'is this worth building', 'what next': research it and propose what to build, with sources and key screens to review. Not for agreed changes or bugs.
Before 'push it', 'ship it', a deploy, release or go-live, or calling a stage done: the gate, the owner's preview, go/no-go, promote, prove it serves, roll back.
Build a session's learnings into the setup: its friction, what went wrong and why, then an improved instruction, route, hook or script, verified, or 'no setup change warranted'. Started by name only: /agent-harness:retro in Claude Code, $agent-harness:retro in Codex.
Only when a security audit is asked for (ship-check asks by name; a release proposes one, never runs it): a static audit of AI-built code against its documented trust boundaries.
Is this safe to ship? Documents the app, wires the agent's context, runs the correctness, security and performance reviews and an independent unsteered pass, maps test coverage, and compiles one reviewer-ready shipping packet. Started by name only: /ai-shipping:ship-check in Claude Code, $ai-shippi…
Documenting an AI-built app for handoff, review or audit: the docs that make it reviewable (architecture, flows, permissions, variables, coverage).
Writing or running tests, proving a fix, a red or flaky run, a fix that didn't land, 'is it verified', 'run the gate': tests where green means something.
A coding agent on Windows: Git Bash path rewriting, PowerShell quoting and encoding, CRLF. Use when output comes back garbled, or it works here and breaks there.
MCP = die Hände
Verbindet die KI mit einem externen Dienst oder Daten, etwa Notion lesen oder eine Rechnung erstellen. Ein Programm oder Server muss laufen.
Skill = das Handbuch
Eine Textdatei, die der KI zeigt, wie eine Aufgabe geht. Sie verbindet sich mit nichts.
Manches überschneidet sich: Einige Skills starten Skripte mit Werkzeugen, einige MCP-Server liefern nur Wissen. Geh von der Aufgabe aus.
Claude CodeClaude (เว็บ/แอป)CodexCursorGemini CLIGitHub CopilotWindsurfOpenCode
Laut README des Anbieters und den Ordnern im Repo
This repo has 44 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP
Schon installiert? Zuerst prüfen · Öffne das Terminal, gib diesen Befehl ein und drücke Enter
node -vMac: ⌘ + Leertaste drücken, Terminal eingeben, Enter
Windows: Start öffnen, Windows PowerShell eingeben, dann Öffnen
Noch nicht installiert: Öffne die offizielle Download-Seite, wähle die LTS-Version und den Klick-Installer: .pkg auf dem Mac · .msi unter Windows. Doppelklicken und bis zum Ende durchklicken. Kein curl-Befehl nötig
Download-Seite von Node.js öffnen ↗
Danach das Terminal schließen, neu öffnen und denselben Befehl erneut ausführen. Es muss eine Versionsnummer erscheinen: node -v
Einmal installieren, gilt für alles, was Node.js braucht
Befehle werden geprüft · Kopier-Buttons erscheinen, sobald sie bestanden sind
Aus dem README des Anbieters; lädt den Code des Anbieters herunter und führt ihn aus
Fragen, Tipps teilen oder melden, dass etwas nicht geht. Sortiert nach „hilfreich“.
Noch keine Beiträge. Stell die erste Frage oder teile einen Tipp.
Beiträge hier stammen von Nutzern, nicht vom PopNx-Team.