omnilearn-workflow 1.0.9 → 1.0.10
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.
- package/commands/omnilearn-start.md +64 -15
- package/package.json +1 -1
|
@@ -265,10 +265,11 @@ task(category="deep", run_in_background=false, timeout=600000, prompt="
|
|
|
265
265
|
|
|
266
266
|
### 2. ...
|
|
267
267
|
|
|
268
|
-
## Assignment Structure
|
|
269
|
-
-
|
|
270
|
-
-
|
|
271
|
-
-
|
|
268
|
+
## Assignment Structure (Adaptive — Determined During Learning)
|
|
269
|
+
- **Assignments are NOT pre-defined.** They are generated on-demand based on the user's performance, ZPD, and pace.
|
|
270
|
+
- The general trajectory is: Baseline → Stretch → Real-World, but the number of assignments and their specific difficulty is determined adaptively.
|
|
271
|
+
- If the user breezes through, they get fewer, harder assignments. If they struggle, they get more scaffolding and intermediate bridging exercises.
|
|
272
|
+
- The final assignment will be a real-world scenario that integrates this topic with other skills the user knows.
|
|
272
273
|
|
|
273
274
|
STEP 3 — Create topic-explanation.md at:
|
|
274
275
|
{TOPICS_DIR}/{topic}/topic-explanation.md
|
|
@@ -334,10 +335,28 @@ task(category="deep", run_in_background=false, timeout=600000, prompt="
|
|
|
334
335
|
- Use the simplest possible test setup
|
|
335
336
|
|
|
336
337
|
c) scaffold/ directory with starter files:
|
|
337
|
-
|
|
338
|
-
|
|
339
|
-
|
|
340
|
-
|
|
338
|
+
|
|
339
|
+
GOLDEN RULE: The user must be able to go from `cd scaffold/` to `running the test` in ONE command.
|
|
340
|
+
If the assignment isn't testing setup/environment skills, automate ALL of that.
|
|
341
|
+
|
|
342
|
+
- Include a setup script (`setup.sh` for Unix, `setup.ps1` for Windows) that:
|
|
343
|
+
* Creates virtual environment (Python: `python -m venv .venv`), or installs deps (Node: `npm install`)
|
|
344
|
+
* Installs required packages
|
|
345
|
+
* Prints "Environment ready! Run this command to start: ..."
|
|
346
|
+
- OR include a one-liner in the scaffold README: `python -m venv .venv && source .venv/bin/activate && pip install -r requirements.txt`
|
|
347
|
+
- Include `requirements.txt` / `package.json` with ALL needed deps pre-listed
|
|
348
|
+
- Minimal code structure — only the files the user needs to touch
|
|
349
|
+
- Comments marking where to write code // TODO: or # TODO:
|
|
350
|
+
- Import/require statements already in place
|
|
351
|
+
- Cross-skill integration: if the user knows {related_skill}, structure the scaffold to use familiar patterns from it
|
|
352
|
+
- If the topic is NOT a programming topic (e.g., system design), provide templates or worksheets instead
|
|
353
|
+
|
|
354
|
+
ANNOYING THINGS TO NEVER DO:
|
|
355
|
+
- Do NOT make the user manually create a venv or install packages unless the assignment is specifically about that
|
|
356
|
+
- Do NOT leave unlisted imports — if a package is needed, it must be in requirements.txt / package.json
|
|
357
|
+
- Do NOT require the user to set up databases, API keys, or external services without providing clear instructions or a docker-compose.yml
|
|
358
|
+
- Do NOT leave configuration files empty or incomplete — provide working defaults
|
|
359
|
+
- Do NOT make the user hunt for the right Python/Node version — specify it in the scaffold or use `.nvmrc`/`.python-version`
|
|
341
360
|
|
|
342
361
|
d) solution-guide.md — CRITICAL: Must be researched, accurate, and complete.
|
|
343
362
|
|
|
@@ -425,6 +444,7 @@ STEP 5 — Create topic-progress.md at:
|
|
|
425
444
|
- User experience level: {from preferences}
|
|
426
445
|
- User learning style: {from preferences}
|
|
427
446
|
- Skill conventions (package manager, project structure, deps, testing setup): {from SkillConventions.md — read before generating scaffold}
|
|
447
|
+
- Cross-skill context (other skills user knows, so scaffold can use familiar patterns): {from cross-skill inventory}
|
|
428
448
|
")
|
|
429
449
|
```
|
|
430
450
|
|
|
@@ -434,9 +454,28 @@ After completion, verify:
|
|
|
434
454
|
- Assignment 1 exists with all 4 files (question.md, test, scaffold, solution-guide.md)
|
|
435
455
|
- Test script is syntactically valid (run a quick check)
|
|
436
456
|
|
|
437
|
-
If anything is missing, fix via session continuation: `task(task_id="<session_id>", prompt="Fix: {missing element}")
|
|
457
|
+
If anything is missing, fix via session continuation: `task(task_id="<session_id>", prompt="Fix: {missing element}")"
|
|
458
|
+
|
|
459
|
+
## Phase 1.5: READINESS GATE — Teach Before Test
|
|
460
|
+
|
|
461
|
+
**The user MUST read the theory before touching assignments.** This is non-negotiable.
|
|
462
|
+
|
|
463
|
+
1. Present the topic-explanation.md to the user:
|
|
464
|
+
> "Before we jump into coding, let's cover the concepts you need.
|
|
465
|
+
>
|
|
466
|
+
> 📖 **{SKILL_DIR}/topics/{topic}/topic-explanation.md**
|
|
467
|
+
>
|
|
468
|
+
> This covers: TL;DR → Core Concepts → Examples → Pitfalls → Best Practices
|
|
469
|
+
> It should take about 5-10 minutes to read.
|
|
470
|
+
>
|
|
471
|
+
> Let me know when you've finished reading, or ask me questions about anything that's unclear."
|
|
472
|
+
|
|
473
|
+
2. **Wait for the user to confirm they've read it.** Do NOT skip this step.
|
|
474
|
+
- If they ask questions → answer them (using diagnostic task pattern from Phase 3 if needed)
|
|
475
|
+
- If they say "I already know this" → ask 2 quick concept-checking questions to verify. If they pass, skip. If they fail, tell them to read it.
|
|
476
|
+
- If they say "ready" → proceed.
|
|
438
477
|
|
|
439
|
-
**
|
|
478
|
+
3. **Only after confirmation** → proceed to Phase 2.
|
|
440
479
|
|
|
441
480
|
## Phase 2: ASSIGNMENT PRESENTATION
|
|
442
481
|
|
|
@@ -685,9 +724,18 @@ task(category="unspecified-high", run_in_background=false, timeout=300000, promp
|
|
|
685
724
|
- Self-contained and runnable
|
|
686
725
|
|
|
687
726
|
c) scaffold/ — Starter code:
|
|
688
|
-
|
|
689
|
-
|
|
690
|
-
|
|
727
|
+
|
|
728
|
+
GOLDEN RULE: The user must go from `cd scaffold/` to running tests in ONE command.
|
|
729
|
+
|
|
730
|
+
- Include setup script (`setup.sh` + `setup.ps1`) that auto-creates env + installs deps
|
|
731
|
+
- OR one-liner setup instructions in a README
|
|
732
|
+
- `requirements.txt` / `package.json` with ALL deps pre-listed
|
|
733
|
+
- Minimal boilerplate — only what the user needs to touch
|
|
734
|
+
- TODO markers for user implementation
|
|
735
|
+
- All necessary imports/includes set up
|
|
736
|
+
- If the user knows {related_skill} from SkillConventions.md, use familiar patterns
|
|
737
|
+
- Auto-setup: `python -m venv .venv && source .venv/bin/activate && pip install -r requirements.txt`
|
|
738
|
+
- NEVER make the user manually install packages (unless assignment tests that skill)
|
|
691
739
|
|
|
692
740
|
d) solution-guide.md — CRITICAL: Must be researched and accurate.
|
|
693
741
|
|
|
@@ -737,11 +785,12 @@ task(category="unspecified-high", run_in_background=false, timeout=300000, promp
|
|
|
737
785
|
6. CONTEXT:
|
|
738
786
|
- Skill: {skill}
|
|
739
787
|
- Topic: {topic}
|
|
740
|
-
- Assignment number: {n}
|
|
741
|
-
- Difficulty: {
|
|
788
|
+
- Assignment number: {n}
|
|
789
|
+
- Difficulty: {current difficulty level}
|
|
742
790
|
- Previous assignment concepts: {summary}
|
|
743
791
|
- User performance on previous assignment: {observations}
|
|
744
792
|
- Skill conventions (package manager, project structure, deps, testing setup): {from SkillConventions.md — MUST follow these when generating scaffold}
|
|
793
|
+
- Cross-skill context (other skills the user knows): {from cross-skill inventory — integrate these patterns into the scaffold if relevant}
|
|
745
794
|
")
|
|
746
795
|
```
|
|
747
796
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "omnilearn-workflow",
|
|
3
|
-
"version": "1.0.
|
|
3
|
+
"version": "1.0.10",
|
|
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",
|