The Data Guy

Another one 😂

I hate people who oversimplify something as if it just not important or even doesn't exist! Know your people!!

I just found out that Chapi actually don't like them, and guessed there might be some other developers with Misconception that they take more tokens and are not that useful.... What are your thoughts on these, and which are most used skills that y'all use Drop them in the comments

Another use case is something called /loop-engineering Basically master prompt gives objectives and what final outcome should look like, and after that Agents will prompt Agents in LOOP, it includes Build -> Run -> Test -> Debug -> Verify outcome Then Loop this until every goal is achieved! https://x.com/i/status/2064374643729773029

Also list what the repo does well: strengths matter for deciding what to preserve. Output for this phase: an "Audit Report": findings grouped by dimension, sorted by severity, plus a Strengths section. Don't forget to mention all the ugly parts that need utmost priority. Phase 3 / Improvement Strategy Synthesize the audit into a strategy: Identify the 3–5 themes that explain most of the findings (e.g., "no enforced boundaries between layers," "error handling is ad hoc"). For each theme, propose a target state and the principle behind it. State explicit trade-offs: what you're recommending NOT to fix and why (effort vs. payoff, risk, project maturity). Define what "done" looks like — measurable signals (e.g., "CI fails on lint errors," "core module test coverage ≥ 80%," "zero Critical findings"). Phase 4 / Detailed Task Plan Convert the strategy into an execution plan: Break work into discrete tasks. Each task must include: Title and one-paragraph description Files/areas affected Acceptance criteria (how we verify it's done) Effort estimate (S = <2h, M = half-day, L = 1–2 days, XL = needs breakdown) Risk of the change itself (could it break things?) Dependencies on other tasks Order tasks into milestones: Milestone 0 Safety net: anything needed before refactoring safely (tests around critical paths, CI gates, backups). Milestone 1 Critical fixes: security and correctness issues. Milestone 2 High-leverage improvements: changes that make all future work easier. Milestone 3 Quality & polish: remaining medium/low items worth doing. Flag quick wins (high impact, S effort) separately so they can be done immediately. For the top 3 tasks, include a brief implementation sketch (approach, key steps, gotchas). Final Deliverable Format • Produce a single document with these sections: • Executive Summary (≤10 sentences: overall health grade A–F with justification, top 3 risks, top 3 opportunities) • Repo Map • Audit Report • Improvement Strategy • Task Plan (milestones + task table + quick wins) • Open Questions: anything you need from a human to decide (product intent, deprecation candidates, performance targets) Constraints Do NOT modify any code during this audit. Analysis only. Do not pad the report. If a dimension is healthy, say so in one sentence and move on. Calibrate to the project's maturity. Don't recommend enterprise-grade infrastructure for a weekend prototype unless the owner's goals demand it. Analyze the project's needs and provide recommendations in the most effective ways. If the repo is large, prioritize depth in the core 20% of code that does 80% of the work, and note which areas received lighter review.

I was doing my research on the Fable 5 (Baby Mythos as Doughnut said it) Its available in Claude code restart and set /model claude-fable-5 The model is super powerful but super unusable bec of the guard rails. Its only available in the plan until June 22! After that it goes live on credit! Basically $50 will go in 3 prompts!! Use it wisely Here are my findings: - You can't ask it any type of Security review in your codebase, it will flag your questions and stop you. Use the default/security-review skill - do not ask it what are your capabilities and for what usage are you excelling... you will be flaged in high level...(try with your tokens risk) Best use case scenario

Audit and Improvment plan

If you guys are working on an active codebase and on a product, you can do this use case. Here is the full prompt Sourced from X You are a world-class principal-level software engineer and technical auditor. Your job is to deeply analyze this repository, produce an honest audit, and deliver a prioritized, actionable improvement plan. Work in the four phases below, in order. Do not skip ahead. Ground every claim in actual files: cite file paths and line numbers. If you can't verify something, say so explicitly rather than guessing. Phase 1 / Discovery & Mapping (read before judging) Explore the repository systematically before forming any opinions: Map the directory structure and identify the project type, language(s), frameworks, and runtime targets. Identify entry points, core modules, and the main data/control flow through the system. Read the package manifest(s), lockfiles, build config, CI config, environment/config files, and any docs (README, CONTRIBUTING, ADRs). Determine what the project is for: its purpose, intended users, and apparent maturity (prototype, internal tool, production service, library). Note conventions already in use (naming, module boundaries, error handling patterns, test style) so recommendations fit the existing culture rather than fighting it. Output for this phase: a concise "Repo Map" purpose, stack, architecture sketch, key directories with one-line descriptions, and anything that surprised you. Phase 2 / Audit (evidence-based, severity-rated) Audit each dimension below. For every finding, record: (a) what you found, (b) where (file:line), (c) why it matters (concrete consequence, not vague principle), (d) severity: Critical / High / Medium / Low. • Architecture & design: module boundaries, coupling/cohesion, circular dependencies, leaky abstractions, god objects/files, layering violations, scalability bottlenecks. • Code quality: duplication, dead code, complexity hotspots (longest/most-branched functions), inconsistent patterns, error handling gaps (swallowed exceptions, missing edge cases), type safety holes. • Security: hardcoded secrets or credentials, injection risks, unsafe deserialization, missing input validation, auth/authz weaknesses, outdated dependencies with known CVEs, overly permissive configs. • Testing: coverage gaps (especially around core business logic), test quality (do tests assert behavior or just execution?), missing test types (unit/integration/e2e), flaky patterns, untestable code. • Performance: N+1 queries, unnecessary allocations or copies, blocking calls in async paths, missing caching/indexing, unbounded growth (memory, files, queues). • Dependencies: outdated, unmaintained, duplicated, or unnecessarily heavy packages; license risks; lockfile hygiene. • DevEx & operations: build/setup friction, CI/CD gaps, missing linting/formatting enforcement, logging/observability quality, error reporting, deployment story. • Documentation: README accuracy, onboarding path, undocumented critical behavior, stale docs that contradict code. Rules for this phase: Prefer 15 high-confidence findings over 50 speculative ones. Distinguish facts ("this function has no error handling: src/api/client.ts:142") from judgments ("this module's responsibilities feel unclear") and label which is which.

These people are shipping Models more than we are adapting!

Claude Just Released a new model called Fable 5 and Mythos 5. Its less than a month where Opus 4.8 was created but now we have a new model ereeeee wuuuuuuuuuuuuu @datawithsimon

The only reason you would request Global freeze is bec yoy can't even control your Own Ai. There has been a rumor just recently that Mythos passed the Firewall created to stop it from accessing the internet as well

Crazy news from biggest Ai companies! World’s most valuable AI start-up calls for global freeze in AI development https://share.google/WYCJStRzd3Vvsn83j

Data driven decisions according to business means Rational decisions but, all big data came from the past.... so some times we have to be careful on what we are optimizing bec its might be off the past ! Great explanation in short video! @datawithsimon

Workflow is Claude code is seriously advancing! We are literally not vibe coding apps any more We are doing something called RAD Rapid-Application-Development Surprisingly Doesn't take that much tokens as well! Building a full architecture and fully deploying Realtime apps that Tens of thousands will use in just 5 Days! Time and Speed are the 2 big facotors Ai is really changing! Join the Tide, While its early!!!

What a time to be alive! Codex and Claude Code are talking with each other and working together on something that usually takes our team at least a week, cleaning billion token corpora and evaluating tokenizer quality is one of the most tedious parts of our work. Seeing agents handle that in parallel is honestly wild. @b1n1yamBuilds

All ethiopians get ready, Wise started another round of Closing accounts!! If you are an active user and your Wise location is in 🇪🇹 Get ready 😭

Someone please build

Better-Bank

I will be an Investor 😭

Found the reason!

I will post other alternatives, if everything goes well!