# Prompt Engineering · Tech watch

[Canonical source](<https://sebastien.rigaux.be/en/tech-watch/tags/prompt-engineering>)

Designing instructions and context to guide model responses and actions.

## [prompts.chat: AI prompts integrated with developer tools](<https://sebastien.rigaux.be/en/tech-watch/links/promptschat-ai-prompts-integrated-with-developer-tools>)

prompts.chat brings together community prompts for ChatGPT, Claude, Gemini, and other assistants, alongside an interactive book on prompt engineering. The repository also provides a CLI, a Claude Code plugin, and an MCP server for using prompts across different tools.

For a team, self-hosting provides a private prompt library with custom branding and authentication configured by the setup wizard. The integration examples range from `npx prompts.chat` to a remote MCP connection, without requiring a single access method.

2026-10-28 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/promptschat-ai-prompts-integrated-with-developer-tools.md>) · [Original resource](<https://github.com/f/prompts.chat>)

## [Agent skills: preserve flexibility while supplying context](<https://sebastien.rigaux.be/en/tech-watch/links/agent-skills-preserve-flexibility-while-supplying-context>)

PostHog shares practical guidance for writing skills that help agents without locking them into a brittle workflow. The core idea is to load context progressively, define the goal and constraints, then let the agent choose steps that fit the repository and runtime environment.

The article also addresses maintenance: separate durable structure from fast-changing details, point to a single source of truth, and regenerate skills instead of patching them indefinitely. Skills carry context and upkeep costs, so they make most sense for recurring tasks where agents lack essential context or perform poorly by default.

2026-10-23 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/agent-skills-preserve-flexibility-while-supplying-context.md>) · [Original resource](<https://newsletter.posthog.com/p/what-nobody-tells-you-about-writing?utm_source=convertkit&utm_campaign=%E2%9A%9B%EF%B8%8F+This+Week+In+React+%23302%3A+Next.js%2C+React+Router%2C+DevTools%2C+Security%2C+shadcn%2C+Hydrogen%2C+Vinext%2C+Mutative%2C+R3F+%7C+RN+0.88%2C+Expo+58%2C+Navigation%2C+FastImage%2C+Screens%2C+Device+Hub%2C+Edge+to+Edge+%7C+TypeScript%2C+PHP%2C+CrUX%2C+Rsdoctor%2C+Astro+-+23823401&ck_subscriber_id=2550494205&utm_medium=email>)

## [Refero Styles: AI-ready design system library](<https://sebastien.rigaux.be/en/tech-watch/links/refero-styles-ai-ready-design-system-library>)

Refero Styles offers a browsable collection of over 2,000 design systems from well-known product sites, each paired with a DESIGN.md file readable by AIs like Cursor, Claude, or ChatGPT. The tool lets you inspect colors, typography, spacing, and components, then reuse these styles in your own projects or AI prompts. It’s a practical resource to give visual context to an assistant or speed up interface design inspired by market references.

2026-10-16 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/refero-styles-ai-ready-design-system-library.md>) · [Original resource](<https://styles.refero.design/>)

## [Prompt Motion: explore AI-generated motion examples](<https://sebastien.rigaux.be/en/tech-watch/links/prompt-motion-explore-ai-generated-motion-examples>)

Prompt Motion is a gallery of motion videos accompanied by the prompts and skills used to create them with Claude Opus 5.5. Examples can be browsed by type, from product UI and charts to kinetic typography and particles, then adapted to a project as a starting point for AI-assisted motion design.

2026-10-08 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/prompt-motion-explore-ai-generated-motion-examples.md>) · [Original resource](<https://prompt-motion.com/>)

## [JevAI Community playbooks and demos for developers](<https://sebastien.rigaux.be/en/tech-watch/links/jevai-community-playbooks-and-demos-for-developers>)

JevAI Community brings together playbooks, small tools, and demos built around the Jev model. Some examples run in the browser, where users can adjust inputs and share variants; the site positions itself as a community resource alongside the official API and infrastructure.

2026-09-18 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/jevai-community-playbooks-and-demos-for-developers.md>) · [Original resource](<https://www.jevai.org/>)

## [A library of specialized agents for software teams](<https://sebastien.rigaux.be/en/tech-watch/links/a-library-of-specialized-agents-for-software-teams>)

Agency Agents collects specialized agents with defined personalities, processes, and deliverables across design, engineering, product, security, and marketing. The repository explains several ways to use them, including Claude Code and other AI-assisted development tools.

2026-09-06 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/a-library-of-specialized-agents-for-software-teams.md>) · [Original resource](<https://github.com/msitarzewski/agency-agents>)

## [SkillOpt: optimize agent skills through trials and evaluation](<https://sebastien.rigaux.be/en/tech-watch/links/skillopt-optimize-agent-skills-through-trials-and-evaluation>)

SkillOpt treats the skill itself as an artifact to improve: an agent runs tasks, receives evaluation, and its procedure is revised. Keeping the model and harness fixed makes instruction changes comparable.

2026-07-14 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/skillopt-optimize-agent-skills-through-trials-and-evaluation.md>) · [Original resource](<https://microsoft.github.io/SkillOpt/>)

## [Anthropic’s interactive prompt engineering tutorial](<https://sebastien.rigaux.be/en/tech-watch/links/anthropic-s-interactive-prompt-engineering-tutorial>)

This repository offers hands-on prompt-writing lessons with exercises and Claude examples. Its sections also cover tool use and response structure.

2026-02-10 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/anthropic-s-interactive-prompt-engineering-tutorial.md>) · [Original resource](<https://github.com/anthropics/prompt-eng-interactive-tutorial>)

## [GPT-5 guide: design prompts for coding tasks](<https://sebastien.rigaux.be/en/tech-watch/links/gpt-5-guide-design-prompts-for-coding-tasks>)

This archived OpenAI guide collects prompting advice for coding, agents and instruction following. It provides a GPT-5-specific reference that should be read in its publication context.

2025-08-13 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/gpt-5-guide-design-prompts-for-coding-tasks.md>) · [Original resource](<https://developers.openai.com/cookbook/examples/gpt-5/gpt-5_prompting_guide>)

## [Share AI prompts and apps with FlowGPT](<https://sebastien.rigaux.be/en/tech-watch/links/share-ai-prompts-and-apps-with-flowgpt>)

FlowGPT collects community-published prompts and AI apps, with categories for programming, work, and creative tasks. Users can browse examples or publish their own creations.

2023-07-20 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/share-ai-prompts-and-apps-with-flowgpt.md>) · [Original resource](<https://flowgpt.com/>)
