Finding signal on Twitter is more difficult than it used to be. We curate the best tweets on topics like AI, startups, and product development every weekday so you can focus on what matters.

Coding Agents & IDEs

13 hand-picked coding agents & ides skills for your OpenClaw agent. Every entry reviewed and annotated.

Editor's Picks
All Coding Agents & IDEs Skills
Coding Agents & IDEs

debug-methodology

Systematic debugging that prevents patch-chaining and workaround addiction in AI agents.

Addresses one of the most common failure modes in AI coding: layering fixes on top of fixes. Enforces root-cause discipline.

Coding Agents & IDEs

env-setup

Scan codebase for environment variables, generate .env.example, validate .env, and ensure .gitignore safety.

Essential DevEx helper. Every project needs .env hygiene and this automates the boring but important parts.

Coding Agents & IDEs

readme-generator

Generate a production-quality README.md by analyzing project structure, framework, and code.

Generates real README files by reading actual code — not template-filled junk. Developers will use this constantly.

Coding Agents & IDEs

senior-python-developer

Senior Python Developer operating in strict mode.

A well-scoped persona skill that enforces professional coding standards. Useful when you need the agent to stop cutting corners.

Coding Agents & IDEs

haskell

Expert Haskell development skill.

Haskell expertise is rare and hard to approximate from base models. This specialized skill fills a real gap for functional programmers.

Coding Agents & IDEs

diagrams

Generate visual flow diagrams, architecture diagrams, and system maps as SVG/PNG.

Visual architecture documentation that outputs real image files. Pairs perfectly with README generation for complete project docs.

Coding Agents & IDEs

elitee-rfc-writer-safe

Write decision-oriented engineering RFCs with strict template enforcement.

Enforces proper RFC structure rather than producing freeform documents. Strict template mode is exactly what eng teams need.

Coding Agents & IDEs

verification-before-completion

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running actual verification.

Forces agents to actually verify claims before declaring done. Solves the hallucinated 'it works' problem that plagues AI coding sessions.

Coding Agents & IDEs

dispatching-parallel-agents

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies.

Concise, practical guidance on when and how to run agents in parallel. Reduces both time and cost on multi-file changes.

Coding Agents & IDEs

requesting-code-review

Use when completing tasks, implementing major features, or before merging to verify work meets requirements.

Structures the code review request process so agents surface the right context. Pairs well with other finishing-workflow skills.

Other Categories