docs: improve prompt engineering roadmap with verified free resources#9863
Open
nehaturov-hue wants to merge 1 commit intokamranahmedse:masterfrom
Open
docs: improve prompt engineering roadmap with verified free resources#9863nehaturov-hue wants to merge 1 commit intokamranahmedse:masterfrom
nehaturov-hue wants to merge 1 commit intokamranahmedse:masterfrom
Conversation
Author
|
Closing for now -- will reopen after further review. |
nehaturov-hue
changed the title
Improves all 46 topics in the Prompt Engineering roadmap. Previously 80% of topics had zero links, and the few that existed pointed to a single reused YouTube video. - 95 links across 46 topics (up from ~10) - Every URL verified in live browser before inclusion - No link reuse across topics - Provider texts updated to April 2026 (GPT-5.4, Claude Opus 4.7, Gemini 3, Llama 4, Grok 4.20) - Original upstream text preserved for non-provider topics - Original video links kept, no new videos added - Fixed: removed incorrectly added regular files, now only edits blob files
nehaturov-hue
force-pushed
the
improve-prompt-engineering-content
branch
from
884fd7a to
c0f344a
Compare
n3xtb1te
reviewed
Apr 18, 2026
| Visit the following resources to learn more: | ||
|
|
||
| - [@official@Context windows - Anthropic](https://platform.claude.com/docs/en/build-with-claude/context-windows) | ||
| - [@article@What is a context window? - IBM](https://www.ibm.com/think/topics/context-window) |
There was a problem hiding this comment.
[@video@What is a Context Window? Unlocking LLM Secrets](https://youtu.be/-QVoIxEpFkM?si=Ut-ScxhUdS0JjRmb)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This PR improves all 46 topics in the Prompt Engineering roadmap by adding fresh, free, verified resource links. Previously, 80% of topics had zero links, and the few that existed pointed to a single reused YouTube video.
Approach
Every resource link was:
Changes
Total: 46 topics, 95 links (up from ~10)
Text Updates
Provider descriptions updated to reflect April 2026 state:
All other topic descriptions unchanged from upstream.
Sources Used
AI Disclosure
This contribution was produced with the assistance of Hermes Agent, an AI coding assistant. To minimize hallucinations and ensure quality:
Every URL was opened and verified in a live browser before being included — no link was added based on assumed knowledge of what a URL should contain.
Each article was read and evaluated for relevance, accuracy, and freshness before inclusion. Links that referenced outdated models (e.g., "Google Bard", "Claude 3.5", "GPT-4o") were identified and excluded.
A strict no-reuse rule was enforced: every link appears in exactly one topic, forcing diverse sourcing across all 46 topics rather than recycling the same handful of pages.
Search engines (DuckDuckGo) were used to discover resources, not just rely on training data knowledge.
The AI agent output was iteratively corrected by the human contributor — initial drafts were reviewed, pruned, and refined across multiple rounds.
The human contributor reviewed all content and made final decisions on what to include.