REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
This repo is a collection of 28 skills
28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible toolsWenn du das gebaut hast, füge diesen Code in dein README ein. Das Badge verlinkt auf diese Seite.
[](https://mcp.popnx.com/en/skills/tjboudreaux-cc-thinking-skills)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 cc-thinking-skills | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| Anbieter | tjboudreaux | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skills | 28 | 1 | 1 | 1 | 1 |
| GitHub-Sterne | 1.754 | 468.733 | 234.332 | 150.287 | 144.566 |
| Letzte Codeänderung | 8. Aug. 2026 | 19. Nov. 2026 | 20. Apr. 2026 | 18. Nov. 2026 | 18. Nov. 2026 |
| Lizenz | MIT | MIT | – | Apache-2.0 | MIT |
28 Skills (Anweisungssammlungen) von tjboudreaux, die eine KI liest und befolgt · kein MCP-Server
Install only the ones you use. Open a skill to see how to install it
If you want every one, let the AI install them in one go. Know 2 things first
Uploading to Claude on the web and apps: you need 28 uploads, one ZIP per skill. Open each skill in the list below to download it
Checked against official docs 12. Nov. 2026 · Source: support.claude.com, code.claude.com, learn.chatgpt.com, cursor.com
Use when search or investigation could run forever. Set an explicit good-enough threshold first, then stop at the first option that clears it.
Use when a specific claim may lack grounding. Check evidence boundary, size wrongness cost, then answer, fetch, or abstain — never confabulate.
When the right response mode is unclear, classify the cause-effect domain first; decompose disorder.
Under genuine uncertainty with no reliable forecast, inventory means, cap downside at affordable loss, act for commitments, and let goals emerge from controllable moves.
When a constraint is treated as fixed, separate physics from convention, keep only independently supported primitives, and rebuild the simplest solution that satisfies real constraints.
When a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.
Deciding what to build or why adoption fails. Recover the progress users hire a solution for under a circumstance, then rank by outcome and competing workarounds.
Use when a selective defect needs IS/IS-NOT difference analysis or a consequential option choice needs must/want weighting and adverse-consequence comparison.
Use when longevity of a non-perishable option matters. Treat survival duration as a remaining-life prior, then check domain drift before favoring the proven.
When a claim, doc, test, metric, or assumption conflicts with observed behavior, stop theorizing from the map and verify the live code or data; let territory overrule.
When provisioning, setting a limit, or committing an estimate under uncertainty, size a buffer to residual error and the cost of breach—not to the optimistic edge.
When one mental model leaves a material blind spot on a multi-domain or high-stakes problem, sequence complementary models with named roles and a conflict rule.
When unsure which thinking skill fits, map domain and problem type, then return NONE or one primary skill by default (at most three complementary).
Use under time pressure when the situation is still changing and you must act before certainty — cycle Observe→Orient→Decide→Act on ~70% confidence, then re-observe.
Before committing scarce time, people, or money, name the best forgone use of those resources and the value delta of the chosen path versus that alternative.
Before committing to a plan or launch, assume it already failed and reason backward through concrete causes — convert failure paths into mitigations, gates, and stop checks.
Use when forecasting, estimating, or sizing risk — anchor on base rates, give ranges, update prior→likelihood→posterior on evidence, and factor unmeasured quantities into order-of-magnitude bounds.
For authorized security review of code, auth, or APIs you control, model the attacker, map the attack surface, and report only findings with a reproducible exploit path and verified mitigation.
Before heavy deliberation, classify the decision as cheap or costly to undo; decide two-way doors fast and stage one-way doors to preserve options.
When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.
When a change has effects past the immediate fix—incentives, scale, feedback—trace consequence chains with timing and probability before committing.
When a request is vague, assumption-laden, or "obvious," ask the few load-bearing questions that expose hidden requirements before building or committing.
Before rejecting a proposal or reflexively agreeing, build the strongest faithful opposing case, state agreement conditions, then update or reaffirm.
When behavior is emergent across components—fixes elsewhere break, loops/delays dominate—map boundary, stocks/flows, feedback, archetypes, then rank leverage.
When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.
When a real test is too rare, large, or irreversible, run a controlled counterfactual: isolate one variable, fix conditions, trace the mechanistic chain, and bound what the result implies.
When two design requirements seem mutually exclusive, name the contradiction, separate conflicting states, then invent a concrete no-compromise resolution.
Use when the reflex is to add a feature, layer, or process. Prefer removing harmful or nonessential elements first, with an irreversibility guard before deletion.
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 CodeCodexCursorGitHub Copilot
Laut README des Anbieters und den Ordnern im Repo
This repo has 28 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
npx skills add tjboudreaux/cc-thinking-skillsAus 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.