learnship 2.1.1 → 2.1.2
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.
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "learnship",
|
|
3
3
|
"description": "Agentic engineering done right — 57 structured workflows, persistent memory across sessions, integrated learning partner, and impeccable UI design system. Works with Claude Code, Windsurf, Cursor, Gemini CLI, OpenCode, and Codex.",
|
|
4
|
-
"version": "2.1.
|
|
4
|
+
"version": "2.1.2",
|
|
5
5
|
"author": {
|
|
6
6
|
"name": "Favio Vazquez",
|
|
7
7
|
"email": "favio.vazquezp@gmail.com"
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
"name": "learnship",
|
|
3
3
|
"displayName": "learnship",
|
|
4
4
|
"description": "Agentic engineering done right — 57 structured workflows, persistent memory across sessions, integrated learning partner, and impeccable UI design system.",
|
|
5
|
-
"version": "2.1.
|
|
5
|
+
"version": "2.1.2",
|
|
6
6
|
"logo": "assets/logo.png",
|
|
7
7
|
"author": {
|
|
8
8
|
"name": "Favio Vazquez",
|
package/SKILL.md
CHANGED
|
@@ -128,7 +128,7 @@ When running `/new-project`, these are non-negotiable hard gates. Violating any
|
|
|
128
128
|
|
|
129
129
|
1. **Research decision = always ask the user.** After PROJECT.md is confirmed, you MUST ask: "Do you want me to research the domain ecosystem first?" and WAIT for a reply. You are FORBIDDEN from deciding this yourself — even if the tech stack is defined in PROJECT.md, the domain seems trivial, or the user gave detailed answers. Never say "no research needed" or "skipping research" on your own.
|
|
130
130
|
|
|
131
|
-
2. **Research = 5
|
|
131
|
+
2. **Research = WRITE 5 FILES TO DISK.** "Research" means creating files, not thinking. If the user chooses research, you MUST write exactly 5 files to `.planning/research/`: `STACK.md`, `FEATURES.md`, `ARCHITECTURE.md`, `PITFALLS.md`, `SUMMARY.md`. Do NOT do web searches or domain analysis and then skip the file writes — that is a workflow failure. Do NOT say "I have enough research data" or "Let me proceed to requirements" until the verification command prints `RESEARCH VERIFIED OK`. The sequence is: mkdir → write 5 files → run verification → present findings → get user confirmation → THEN requirements.
|
|
132
132
|
|
|
133
133
|
3. **AGENTS.md = copy from template.** Read `@./templates/agents.md` BEFORE writing AGENTS.md. Sections marked "copy VERBATIM" must be copied word-for-word — do not rewrite, summarize, or rephrase them. After writing, run the `node -e` verification command. If it fails, fix AGENTS.md before proceeding.
|
|
134
134
|
|
|
@@ -47,7 +47,7 @@ When the user runs `/new-project`, execute these **9 mandatory steps in order**.
|
|
|
47
47
|
|
|
48
48
|
2. **Research decision = always ask the user.** After PROJECT.md is confirmed, ask: "Do you want me to research the domain ecosystem first?" and WAIT for the user's reply. You are FORBIDDEN from deciding this yourself — even if the tech stack is defined in PROJECT.md, the domain seems trivial, or the user gave detailed answers. Never say "no research needed" or "skipping research" on your own.
|
|
49
49
|
|
|
50
|
-
3. **Research = 5
|
|
50
|
+
3. **Research = WRITE 5 FILES TO DISK.** "Research" means creating files on the filesystem, not thinking or browsing. If the user chooses research, write exactly 5 files to `.planning/research/`: `STACK.md`, `FEATURES.md`, `ARCHITECTURE.md`, `PITFALLS.md`, `SUMMARY.md`. Do NOT do web searches or domain analysis and then say "I have enough research data" without writing the files — that is a workflow failure. Run the `node -e` verification command — it must print `RESEARCH VERIFIED OK` before proceeding to requirements.
|
|
51
51
|
|
|
52
52
|
4. **After Step 7 (roadmap approved):** Do NOT display the done banner or suggest next steps. Generate AGENTS.md (Step 8) first.
|
|
53
53
|
|
package/gemini-extension.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "learnship",
|
|
3
|
-
"version": "2.1.
|
|
3
|
+
"version": "2.1.2",
|
|
4
4
|
"description": "Agentic engineering done right — 57 structured workflows, persistent memory across sessions, integrated learning partner, and impeccable UI design system.",
|
|
5
5
|
"author": "Favio Vazquez",
|
|
6
6
|
"homepage": "https://faviovazquez.github.io/learnship/",
|
|
@@ -355,62 +355,79 @@ Reply 1 or 2.
|
|
|
355
355
|
|
|
356
356
|
```
|
|
357
357
|
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
|
358
|
-
learnship ►
|
|
358
|
+
learnship ► WRITING RESEARCH FILES
|
|
359
359
|
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
|
360
360
|
```
|
|
361
361
|
|
|
362
|
-
**
|
|
362
|
+
> 🔴 **CRITICAL — "Research" in this step means WRITING 5 FILES to disk. It does NOT mean thinking, browsing the web, or analyzing in your head. The deliverable is 5 markdown files on the filesystem. You are not done with research until all 5 files exist and pass verification.**
|
|
363
|
+
>
|
|
364
|
+
> **Forbidden behaviors (if you do any of these, the research step has FAILED):**
|
|
365
|
+
> - Doing web searches or thinking about the domain and then saying "I have enough research data" WITHOUT writing the 5 files
|
|
366
|
+
> - Writing research findings only in your response text instead of to files
|
|
367
|
+
> - Writing fewer than 5 files (e.g., one combined file)
|
|
368
|
+
> - Moving to Step 6 or writing REQUIREMENTS.md before the verification command below prints `RESEARCH VERIFIED OK`
|
|
369
|
+
> - Saying "Let me proceed to requirements" or "Moving to requirements" before verification passes
|
|
370
|
+
>
|
|
371
|
+
> **The ONLY acceptable sequence is:** mkdir → write file 1 → write file 2 → write file 3 → write file 4 → write file 5 → run verification → see `RESEARCH VERIFIED OK` → present findings → get user confirmation.
|
|
363
372
|
|
|
364
|
-
Create the research directory
|
|
373
|
+
**Step 5a — Create the research directory.** Run this command now:
|
|
365
374
|
|
|
366
375
|
```bash
|
|
367
376
|
node -e "require('fs').mkdirSync('.planning/research',{recursive:true})"
|
|
368
377
|
```
|
|
369
378
|
|
|
370
|
-
|
|
379
|
+
> 🛑 Did the mkdir command run? If not, run it now before continuing.
|
|
371
380
|
|
|
372
|
-
**
|
|
373
|
-
|
|
381
|
+
**Step 5b — Write all 5 files.** Create each file one at a time using your file write tool. Each file is a separate write operation. Do NOT combine files. Do NOT skip files.
|
|
382
|
+
|
|
383
|
+
**File 1 of 5 — Write `.planning/research/STACK.md` to disk now.**
|
|
384
|
+
Research the standard tech stack for this domain and write the results to this file. The file MUST contain these exact `##` headers:
|
|
374
385
|
- `## Recommended Stack`
|
|
375
386
|
- `## Alternatives Considered`
|
|
376
387
|
- `## What NOT to Use` (with reasons)
|
|
377
388
|
- `## Versions`
|
|
378
389
|
|
|
379
|
-
|
|
380
|
-
|
|
390
|
+
> 🛑 STOP. Confirm: did you write `.planning/research/STACK.md` to the filesystem? If you only thought about the stack but did not create the file, go back and create it now.
|
|
391
|
+
|
|
392
|
+
**File 2 of 5 — Write `.planning/research/FEATURES.md` to disk now.**
|
|
393
|
+
Research what features users expect in this domain. Write the results to this file. The file MUST contain these exact `##` headers:
|
|
381
394
|
- `## Table Stakes` (must-haves)
|
|
382
395
|
- `## Differentiators` (nice-to-haves)
|
|
383
396
|
- `## Anti-Features` (what to avoid)
|
|
384
397
|
|
|
385
|
-
**File 3 of 5 — Write `.planning/research/ARCHITECTURE.md` now
|
|
386
|
-
Research how systems in this domain are typically structured. The file MUST contain these exact `##` headers:
|
|
398
|
+
**File 3 of 5 — Write `.planning/research/ARCHITECTURE.md` to disk now.**
|
|
399
|
+
Research how systems in this domain are typically structured. Write the results to this file. The file MUST contain these exact `##` headers:
|
|
387
400
|
- `## Component Boundaries`
|
|
388
401
|
- `## Data Flow`
|
|
389
402
|
- `## Build Order` (suggested sequence)
|
|
390
403
|
- `## Integration Points`
|
|
391
404
|
|
|
392
|
-
**File 4 of 5 — Write `.planning/research/PITFALLS.md` now
|
|
393
|
-
Research common mistakes and prevention strategies. The file MUST contain these exact `##` headers:
|
|
405
|
+
**File 4 of 5 — Write `.planning/research/PITFALLS.md` to disk now.**
|
|
406
|
+
Research common mistakes and prevention strategies. Write the results to this file. The file MUST contain these exact `##` headers:
|
|
394
407
|
- `## Common Mistakes`
|
|
395
408
|
- `## Warning Signs`
|
|
396
409
|
- `## Prevention Strategies`
|
|
397
410
|
|
|
398
|
-
**File 5 of 5 — Write `.planning/research/SUMMARY.md` now
|
|
399
|
-
Synthesize the 4 files above into a summary. The file MUST contain these exact `##` headers:
|
|
411
|
+
**File 5 of 5 — Write `.planning/research/SUMMARY.md` to disk now.**
|
|
412
|
+
Synthesize the 4 files above into a summary. Write the results to this file. The file MUST contain these exact `##` headers:
|
|
400
413
|
- `## Recommended Stack`
|
|
401
414
|
- `## Table Stakes Features`
|
|
402
415
|
- `## Key Architecture Decisions`
|
|
403
416
|
- `## Top Pitfalls`
|
|
404
417
|
|
|
405
|
-
|
|
418
|
+
**Step 5c — Verify all 5 files exist on disk.** Run this verification command now. Do not skip it.
|
|
419
|
+
|
|
420
|
+
> 🔴 **HARD GATE — You MUST run this command. If you skip it and proceed to Step 6, the workflow has FAILED.**
|
|
406
421
|
|
|
407
422
|
```bash
|
|
408
|
-
node -e "const fs=require('fs'),path=require('path');const dir='.planning/research/';const checks={'STACK.md':['Recommended Stack','What NOT to Use'],'FEATURES.md':['Table Stakes','Differentiators'],'ARCHITECTURE.md':['Component Boundaries','Data Flow'],'PITFALLS.md':['Common Mistakes','Prevention Strategies'],'SUMMARY.md':['Recommended Stack','Top Pitfalls']};const missing=[];for(const[file,sections]of Object.entries(checks)){const fp=path.join(dir,file);if(!fs.existsSync(fp)){missing.push(file+' MISSING');continue;}const c=fs.readFileSync(fp,'utf8');for(const s of sections){if(!c.includes('## '+s))missing.push(file+': missing ## '+s);}}if(missing.length){console.log('RESEARCH
|
|
423
|
+
node -e "const fs=require('fs'),path=require('path');const dir='.planning/research/';const checks={'STACK.md':['Recommended Stack','What NOT to Use'],'FEATURES.md':['Table Stakes','Differentiators'],'ARCHITECTURE.md':['Component Boundaries','Data Flow'],'PITFALLS.md':['Common Mistakes','Prevention Strategies'],'SUMMARY.md':['Recommended Stack','Top Pitfalls']};const missing=[];for(const[file,sections]of Object.entries(checks)){const fp=path.join(dir,file);if(!fs.existsSync(fp)){missing.push(file+' MISSING');continue;}const c=fs.readFileSync(fp,'utf8');for(const s of sections){if(!c.includes('## '+s))missing.push(file+': missing ## '+s);}}if(missing.length){console.log('RESEARCH FAILED — files missing or incomplete:\\n'+missing.join('\\n'));console.log('\\nGo back and create the missing files. Do NOT proceed to requirements.');process.exit(1);}console.log('RESEARCH VERIFIED OK — all 5 files present with required sections');"
|
|
409
424
|
```
|
|
410
425
|
|
|
411
|
-
> 🛑 **If the command prints `RESEARCH
|
|
426
|
+
> 🛑 **If the command prints `RESEARCH FAILED` or exits with code 1:** Go back and create or fix the missing files. Run the verification again. You MUST see `RESEARCH VERIFIED OK` before continuing.
|
|
427
|
+
>
|
|
428
|
+
> **If you did not run the command at all:** You have skipped verification. Go back and run it now. You cannot proceed to Step 5d without a passing verification.
|
|
412
429
|
|
|
413
|
-
**Read all 5 research files now
|
|
430
|
+
**Step 5d — Present findings.** Read all 5 research files from disk now and present their findings in full. Do NOT summarize into 3 bullets — display the actual content from the files you wrote. Display this exact structure, populated from the actual file contents:
|
|
414
431
|
|
|
415
432
|
```
|
|
416
433
|
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "learnship",
|
|
3
|
-
"version": "2.1.
|
|
3
|
+
"version": "2.1.2",
|
|
4
4
|
"description": "Learn as you build. Build with intent. — A multi-platform agentic engineering system for Windsurf, Claude Code, Cursor, OpenCode, Gemini CLI, and Codex: spec-driven workflows, integrated learning, and production-grade design.",
|
|
5
5
|
"keywords": [
|
|
6
6
|
"agentic",
|