add trello mcp

.env.example

@@ -0,0 +1,2 @@
+TRELLO_API_KEY=your_trello_api_key_here
+TRELLO_TOKEN=your_trello_token_here

.mcp.json

@@ -7,6 +7,13 @@
         "chrome-devtools-mcp@latest",
         "--browserUrl=http://127.0.0.1:9222"
       ]
+    },
+    "trello": {
+      "command": "sh",
+      "args": [
+        "-c",
+        "set -a; [ -f .env ] && . ./.env; set +a; exec bunx @delorenj/mcp-server-trello"
+      ]
     }
   }
 }

CLAUDE.md

@@ -24,7 +24,7 @@ If the skill itself can't get the content (Chrome not running, or Oleg is not si
 
 ```
 base/
-  cv-YYYY-MM-base.md           # current master CV in Markdown
+  oleg_proskurin_<role>_cv.md   # master CV(s) in Markdown, one per target role
   reference/
     Oleg_Proskurin_*.pdf        # canonical visual reference (do not edit)
 templates/
@@ -50,20 +50,20 @@ output/
 
 ## Workflow 1 — Generate base CV PDF from Markdown
 
-**Input**: `base/cv-YYYY-MM-base.md`
-**Output**: `output/pdf/cv-YYYY-MM-base.pdf`
+**Input**: `base/oleg_proskurin_<role>_cv.md` (e.g. `oleg_proskurin_ai_engineer_fullstack_cv.md`)
+**Output**: `output/pdf/oleg_proskurin_<role>_cv.pdf`
 
 Steps:
 
 1. Read the Markdown source and the reference PDF (`base/reference/...`) to confirm structure.
-2. Generate `output/html/cv-YYYY-MM-base.html` using `templates/cv-template.html` as a starting point.
+2. Generate `output/html/oleg_proskurin_<role>_cv.html` using `templates/cv-template.html` as a starting point.
    - Link the stylesheet via `<link rel="stylesheet" href="/templates/cv-style.css" />` (absolute path — the PDF script serves the project root).
    - Map MD content to HTML tags **verbatim** — section titles, punctuation, list structure, dates, and contact separators must match MD character-for-character. The structure below is the tag shape; the **text** comes from MD. See "Content vs. style — separation rule" below.
 3. Run the PDF generator:
    ```bash
-   pnpm pdf output/html/cv-YYYY-MM-base.html
+   pnpm pdf output/html/oleg_proskurin_<role>_cv.html
    ```
-4. Open the resulting PDF (`output/pdf/cv-YYYY-MM-base.pdf`) and verify single-page-ish, no orphan bullets, no overflow.
+4. Open the resulting PDF (`output/pdf/oleg_proskurin_<role>_cv.pdf`) and verify single-page-ish, no orphan bullets, no overflow.
 
 ---
 
@@ -205,7 +205,7 @@ The CSS in `templates/cv-style.css` already encodes these — when generating HT
 ## Conventions
 
 - **Language**: every artifact (HTML, MD, PDF, tracking rows, card notes) is in English. Always.
-- **Filenames**: kebab-case. CVs: `cv-YYYY-MM-base.md` for base, `cv.md` inside `tailored/<slug>/` for tailored.
+- **Filenames**: snake_case for base CVs (`oleg_proskurin_<role>_cv.md`), kebab-case for tailored slugs. Tailored CV: `cv.md` inside `tailored/<slug>/`.
 - **Dates**: absolute (`2026-05-24`), never "last Thursday".
 - **Don't edit the reference PDF.** It is the immutable visual anchor.
 - **Don't auto-regenerate PDFs** unless Oleg asks — show diffs first when content changes.

README.md

@@ -33,14 +33,14 @@ pnpm install
 Generate PDF from an HTML file:
 
 ```bash
-pnpm pdf output/html/cv-2026-05-base.html
-# -> output/pdf/cv-2026-05-base.pdf
+pnpm pdf output/html/oleg_proskurin_ai_engineer_fullstack_cv.html
+# -> output/pdf/oleg_proskurin_ai_engineer_fullstack_cv.pdf
 ```
 
 The HTML file should be generated by Claude from the Markdown source — see `CLAUDE.md` for the full flow and styling rules.
 
 ## Workflows
 
-1. **New base CV**: drop a new `cv-YYYY-MM-base.md` into `base/`, ask Claude to generate the HTML, then run `pnpm pdf`.
+1. **New base CV**: drop a new `oleg_proskurin_<role>_cv.md` into `base/`, ask Claude to generate the HTML, then run `pnpm pdf`.
 2. **Tailor for a company**: ask Claude to create `tailored/<company>/cv.md` from the latest base, generate HTML, then PDF.
 3. **Track applications**: append to `tracking/applications.md` and `tracking/outreach.md`.

base/reference/supabase-ai-tooling-essay-q1-eval-loop.md

@@ -6,7 +6,7 @@
 - **Роль:** AI Tooling Engineer
 - **Канал подачи:** ashbyhq, через careers-page Supabase
 - **Дата подачи:** 29 мая 2026
-- **CV использовано:** CV-A (cv-2026-05-base.md), pdf-вариант `oleg_proskurin_ai_engineer_fullstack_cv.pdf`
+- **CV использовано:** CV-A (oleg_proskurin_ai_engineer_fullstack_cv.md), pdf-вариант `oleg_proskurin_ai_engineer_fullstack_cv.pdf`
 - **Статус:** подано, ожидаем ответа
 
 ## Вопрос (дословно)

base/reference/supabase-ai-tooling-essay-q2-knowledge-representation.md

@@ -6,7 +6,7 @@
 - **Роль:** AI Tooling Engineer
 - **Канал подачи:** ashbyhq, через careers-page Supabase
 - **Дата подачи:** 29 мая 2026
-- **CV использовано:** CV-A (cv-2026-05-base.md), pdf-вариант `oleg_proskurin_ai_engineer_fullstack_cv.pdf`
+- **CV использовано:** CV-A (oleg_proskurin_ai_engineer_fullstack_cv.md), pdf-вариант `oleg_proskurin_ai_engineer_fullstack_cv.pdf`
 - **Статус:** подано, ожидаем ответа
 
 ## Вопрос (дословно)

package.json

@@ -5,7 +5,8 @@
   "private": true,
   "type": "module",
   "scripts": {
-    "pdf": "node scripts/generate-pdf.mjs"
+    "pdf": "node scripts/generate-pdf.mjs",
+    "chrome": "bash scripts/launch-chrome.sh &"
   },
   "dependencies": {
     "puppeteer": "^24.37.3"