omnilearn-workflow 1.0.8 → 1.0.9

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -339,13 +339,46 @@ task(category="deep", run_in_background=false, timeout=600000, prompt="
339
339
  - Import/require statements already in place
340
340
  - Can be empty scaffold if topic is conceptual
341
341
 
342
- d) solution-guide.md:
343
- - Complete reference solution (code)
344
- - Explanation of the solution approach
345
- - Why certain choices were made
346
- - Alternative approaches
347
- - Common mistakes and how to avoid them
348
- - Real-world connections
342
+ d) solution-guide.md — CRITICAL: Must be researched, accurate, and complete.
343
+
344
+ BEFORE writing the solution:
345
+ 1. Use google_search / context7_query-docs to research the CORRECT approach for this specific problem.
346
+ 2. Verify your solution compiles/runs correctly — test it mentally or note any assumptions.
347
+ 3. Cross-reference with topic-explanation.md to ensure consistency.
348
+ 4. If the topic involves a library/framework, check official docs via context7 to confirm API accuracy.
349
+
350
+ The solution-guide.md must have this structure:
351
+
352
+ ## Solution Overview
353
+ - What approach was taken and why (1 paragraph)
354
+ - Key decisions made and the tradeoffs considered
355
+
356
+ ## Complete Solution
357
+ ```{language}
358
+ # The full, working solution code
359
+ # Each section commented with WHY, not just WHAT
360
+ ```
361
+
362
+ ## Step-by-Step Explanation
363
+ - Break the solution into logical steps
364
+ - For each step: what it does, why it's done this way, what would happen if you did it differently
365
+ - Reference the topic-explanation.md concepts being applied
366
+
367
+ ## Edge Cases Handled
368
+ - List edge cases the solution handles
369
+ - What would break if not handled
370
+
371
+ ## Alternative Approaches
372
+ - At least one alternative solution approach
373
+ - Why the main approach was chosen over alternatives
374
+
375
+ ## Common Mistakes
376
+ - 3-5 specific mistakes learners make on this type of problem
377
+ - How to identify and fix each one
378
+
379
+ ## Real-World Notes
380
+ - How this solution would differ in a production codebase
381
+ - Performance, security, or maintainability considerations
349
382
 
350
383
  STEP 5 — Create topic-progress.md at:
351
384
  {TOPICS_DIR}/{topic}/topic-progress.md
@@ -382,6 +415,8 @@ STEP 5 — Create topic-progress.md at:
382
415
  - Do NOT use any external packages that aren't standard library without noting it
383
416
  - Do NOT create assignments that are too easy (basic concept application) or too hard (leaps without foundation)
384
417
  - Do NOT leave TODOs in scaffold that require making unrelated architectural decisions
418
+ - **Do NOT write solutions without researching first** — use google_search or context7 to verify API syntax, library behavior, and best practices before writing solution-guide.md
419
+ - **Do NOT guess** — if you're unsure how a library function works, look it up via context7. Guesses lead to inaccurate solutions.
385
420
 
386
421
  6. CONTEXT:
387
422
  - Skill: {skill}
@@ -654,17 +689,50 @@ task(category="unspecified-high", run_in_background=false, timeout=300000, promp
654
689
  - TODO markers for user implementation
655
690
  - All necessary imports/includes set up
656
691
 
657
- d) solution-guide.md:
658
- - Complete solution
659
- - Explanation of approach
660
- - Alternative solutions' discussion
661
- - Real-world production considerations
662
- - Common mistakes
663
-
664
- 5. MUST NOT DO:
692
+ d) solution-guide.md — CRITICAL: Must be researched and accurate.
693
+
694
+ BEFORE writing:
695
+ 1. Use google_search / context7_query-docs to research the correct approach.
696
+ 2. Verify the solution works — test mentally or note assumptions.
697
+ 3. Cross-reference with previous solution-guide.md files to maintain consistency.
698
+
699
+ Structure:
700
+
701
+ ## Solution Overview
702
+ - Approach taken, key decisions, tradeoffs
703
+
704
+ ## Complete Solution
705
+ ```{language}
706
+ # Full working code with WHY comments, not just WHAT
707
+ ```
708
+
709
+ ## Step-by-Step Explanation
710
+ - Logical steps with reasoning for each
711
+ - What changes at this difficulty level vs previous assignments
712
+
713
+ ## Edge Cases Handled
714
+ - What was considered and why
715
+
716
+ ## Alternative Approaches
717
+ - Other valid solutions and when to use them
718
+
719
+ ## Common Mistakes
720
+ - Specific errors learners make at this difficulty level
721
+
722
+ ## Production Notes
723
+ - How this scales, performs, or differs in real codebases
724
+
725
+ 5. MUST DO (research before generation):
726
+ - **Research FIRST** — Use context7 or google_search to verify your solution approach before writing
727
+ - **Cross-reference** with topic-explanation.md and prior solution-guide.md files
728
+ - **Verify accuracy** — If you're unsure about API syntax or behavior, look it up. Do not guess.
729
+
730
+ 6. MUST NOT DO:
665
731
  - Do NOT make the next assignment a repetition of the previous one
666
732
  - Do NOT skip difficulty progression
733
+ - Do NOT write solutions without researching first
667
734
  - Do NOT use external non-standard dependencies without noting it in scaffold setup
735
+ - Do NOT guess API signatures — use context7 to verify
668
736
 
669
737
  6. CONTEXT:
670
738
  - Skill: {skill}
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "omnilearn-workflow",
3
- "version": "1.0.8",
3
+ "version": "1.0.9",
4
4
  "description": "OmniLearn — AI-powered adaptive learning workflow for OpenCode. Multi-agent orchestration that creates personalized roadmaps, hands-on assignments, and tracks progress across any skill.",
5
5
  "keywords": [
6
6
  "opencode",