REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
This repo is a collection of 79 skills
Ship changes of any size with confidence. An agentic software factory for Claude Code and Codex.Wenn du das gebaut hast, füge diesen Code in dein README ein. Das Badge verlinkt auf diese Seite.
[](https://mcp.popnx.com/en/skills/tobihagemann-turbo)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 turbo | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| Anbieter | tobihagemann | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skills | 79 | 1 | 1 | 1 | 1 |
| GitHub-Sterne | 423 | 468.733 | 234.332 | 150.287 | 144.566 |
| Letzte Codeänderung | 18. Nov. 2026 | 19. Nov. 2026 | 20. Apr. 2026 | 18. Nov. 2026 | 18. Nov. 2026 |
| Lizenz | MIT | MIT | – | Apache-2.0 | MIT |
79 Skills (Anweisungssammlungen) von tobihagemann, 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 79 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
No description from the maker
Apply accepted review findings as code changes, escalating ambiguous ones to the user. Use when the user asks to "apply findings", "apply fixes", or "apply the review results".
Assess project-wide technical debt (hotspots, deprecated APIs, duplication, low-value tests) into a ranked report. Use when the user asks to "assess technical debt" or "what should we refactor".
No description from the maker
Shared changelog conventions and formatting rules. Not typically invoked directly.
Run a non-interactive Claude Code print-mode call, including as a peer reviewer. Use when the user asks to "claude print" or "run claude".
Enforce existence, reuse, mirror, and symmetry principles so new code stays minimal and consistent. Use when writing, changing, or refactoring code in an existing codebase.
Run autonomous task execution using the codex CLI. Use when the user asks to "codex exec", "run codex exec", "execute a task with codex", or "delegate to codex".
No description from the maker
Shared commit message rules and technical constraints for skills that write commits. Not typically invoked directly.
Commit already-staged changes with a message matching existing commit style. Use when the user asks to "commit staged changes" or "commit what's staged".
Commit already-staged changes and push in one step. Use when the user asks to "commit and push staged changes", "commit and push what's staged", or "commit staged and push".
Consult Claude Code for second opinions, brainstorming, or hard debugging. Use when the user asks to "consult claude", "ask claude", "get claude's opinion", or "brainstorm with claude".
Multi-turn consultation with Codex CLI for second opinions or brainstorming. Use when the user asks to "consult codex", "ask codex", "get codex's opinion", or "brainstorm with codex".
Consult ChatGPT Pro through browser automation on a problem standard approaches failed to crack. Use when stuck, or when the user asks to "ask the oracle" or "consult chatgpt".
No description from the maker
Create a keepachangelog CHANGELOG.md backfilled from GitHub releases or git tags. Use when the user asks to "create a changelog", "add a changelog", "set up changelog", or "backfill changelog".
No description from the maker
Create a GitHub issue with a drafted title and body. Use when the user asks to "create an issue", "file an issue", "open an issue", "report a bug", or "file a feature request".
No description from the maker
Scan a codebase and generate project skills capturing its inferred conventions. Use when the user asks to "create project skills", "extract skills from the codebase", or "codify patterns as skills".
No description from the maker
Generate a four-level test plan at .turbo/test-plans/[slug].md from what changed. Use when the user asks to "create a test plan", "what should I test", "list test cases", or "test plan for this PR".
Write .turbo/threat-model.md: assets, trust boundaries, attack surfaces, severity. Use when the user asks to "create a threat model", "analyze the attack surface", or "identify security risks".
Align on the shape of a change through an interview, then implement it. Use when the user asks to "discuss this change", "ask me questions first", or "agree on the approach before coding".
Produce an implementation plan at .turbo/plans/[slug].md. Use when the user asks to "draft a plan", "write an implementation plan", "plan this change", or needs a first-draft plan file.
Assess review feedback with adversarial verification and decide which suggestions to apply. Use when the user asks to "evaluate findings", "triage review feedback", or "filter false positives".
Explain what the user is pointing at in plain language: a question, code, an error, output, or a plan. Use when the user asks to "explain this", "what does this mean", or "what am I being asked".
Run multi-level exploratory testing of the app, deeper than a smoke test, with usability notes. Use when the user asks to "exploratory test", "test thoroughly", "test edge cases", or "break it".
Fetch and summarize unresolved review threads and conversation on a GitHub PR without changing anything. Use when the user asks to "fetch PR comments" or "show unresolved threads".
Run the post-implementation QA workflow: tests, code polishing, review, and commit. Use when the user asks to "finalize changes", "wrap up implementation", "finish up", or "ready to commit".
No description from the maker
No description from the maker
Shared writing style for GitHub-facing text (PRs, comments, issues), with insider vs outsider voice. Not typically invoked directly.
Make an ad-hoc change no plan file governs, then run post-implementation QA. Use when the user asks to "just implement", "implement directly", "implement without a plan", or "apply the change".
No description from the maker
Execute an implementation plan file from .turbo/plans/. Use when the user asks to "implement the plan", "execute the plan", "implement plans/[slug].md", or starts a fresh session to implement one.
Interpret third-party feedback with parallel internal and peer readings to surface intent, soundness, and ambiguities. Use when the user asks to "interpret feedback" or "what does this feedback mean".
Find the root cause of bugs, test failures, build errors, or performance issues by testing hypotheses. Use when the user asks to "investigate this bug", "debug this", or "find the root cause".
No description from the maker
No description from the maker
No description from the maker
Run an independent peer review via Claude. Use when the user asks to "peer review", "peer review my code", "peer review my plan", "get a second opinion", or "independent review".
Rank open GitHub issues by engagement, present the top 3, and plan the selected one. Use when the user asks to "pick next issue", "which issue should I work on", or "what should I work on next".
Stage, format, lint, test, review, smoke test, and re-run until stable. Use when the user asks to "polish code", "refine code", "iterate on code quality", "review loop", or "run the polish loop".
Stand up the live app for the user to try a change firsthand, then act on their verdict. Use when the user asks to "preview the change", "let me try it", or "spin up the app so I can test it".
Build a local prototype at .turbo/prototypes/ to settle unknowns prose cannot answer. Use when the user asks to "prototype this", "mock this up", or "show me what it would look like".
Close out a change without the deep review loop: simplify, run checks, smoke test, changelog, and ship. Use when the user asks to "quick finalize" or "wrap this up quickly".
No description from the maker
Iteratively review and revise a plan until no new findings survive evaluation. Use when the user asks to "refine the plan", "iterate on the plan", "tighten the plan", or "improve the plan".
Draft, confirm, and post one conversational reply to GitHub PR conversation comments. Use when the user asks to "reply to PR conversation" or "post PR conversation replies".
Draft, confirm, and post replies to GitHub PR review threads, resolving those whose entry carries a resolution reason. Use when the user asks to "reply to PR threads" or "post PR thread replies".
No description from the maker
No description from the maker
No description from the maker
Review code for bugs, security, API misuse, consistency, simplicity, or test coverage, with peer review in parallel. Use when the user asks to "review my code", "check for bugs", or "security audit".
Find outdated or vulnerable dependencies and GitHub Actions pins without upgrading them. Use when the user asks to "review dependencies", "check for outdated packages", or "scan dependencies".
Review a plan with internal and peer reviews in parallel and return combined findings. Use when the user asks to "review my plan", "check my plan", or "critique my plan".
Review a pull request: run a full code review of its diff, evaluate findings, and implement them. Use when the user asks to "review PR", "review this PR", or "check PR before merging".
No description from the maker
Run the project's verification gate, built from its CI config, check scripts, and tools. Use when the user asks to "run checks", "run lint and tests", "run the test suite", or "does this pass CI".
Extract lessons from sessions or auto memory and route them to instructions, memory, or skills. Use when the user asks to "self-improve", "what did we learn", or "move memory into the repo".
Commit, push, and optionally create or update a PR for the current staged changes. Use when the user asks to "ship", "ship it", "ship changes", "commit push and PR", or "ship this".
Run the code and documentation simplification passes together over one scope. Use when the user asks to "simplify all", "simplify everything", "simplify code and docs", or "clean up code and docs".
Review changed code for scope, reuse, quality, efficiency, clarity, and altitude issues, then fix them. Use when the user asks to "simplify code", "clean up code", or "run simplify".
Review code comments and markdown docs for noise, misdescriptions, and stale content, then fix them. Use when the user asks to "simplify docs", "clean up comments", or "fix stale comments".
Launch the app and verify hands-on that it works, falling back to an existing integration suite. Use when the user asks to "smoke test", "verify it works", "try it out", or "check it in the browser".
Ship an approved split plan as one branch and PR per change group, or as sequential commits. Use when the user asks to "split and ship" or "create separate PRs".
Stage implementation changes for commit with precise file selection. Use when the user asks to "stage changes", "stage files", "add files to staging", or "prepare changes for commit".
Stage files and commit with a message matching existing commit style. Use when the user asks to "stage and commit", "add and commit", "commit my changes", or "commit these changes".
Stage files, create a commit, and push in one step. Use when the user asks to "stage commit and push", "add commit and push", "commit and push", or "commit and push my changes".
Survey the codebase for analogous features, reusable utilities, and existing patterns before a change. Use when the user asks to "survey patterns", "find existing patterns", or "find prior art".
No description from the maker
No description from the maker
Update the Unreleased section of an existing CHANGELOG.md from current changes. Use when the user asks to "update changelog", "add changelog entry", or "log this change".
Upgrade project dependencies, researching breaking changes in major updates. Use when the user asks to "update dependencies", "upgrade packages", "update deps", or "update GitHub Actions".
No description from the maker
No description from the maker
Apply a UX lens to a user-facing change: whether it serves the user's real goal and whether the path holds together. Use when scoping, planning, or assessing a change to what users see or do.
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 CodeCodex
Laut README des Anbieters und den Ordnern im Repo
This repo has 79 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP
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.