@qvac/skills 0.1.6 → 0.1.8

package/hash.js

@@ -1,2 +1,2 @@
 // Autogenerated by scripts/build.mjs from skills/. Do not edit.
-export const SKILLS_HASH = 'ba65671970b03d38'
+export const SKILLS_HASH = '0eb3f5d497a4b6b8'

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@qvac/skills",
-  "version": "0.1.6",
+  "version": "0.1.8",
   "description": "Skills for the QV.AC app — the SKILL.md tree plus a content-addressed bundle of it.",
   "type": "module",
   "main": "index.js",

package/skills/asana/SKILL.md

@@ -47,6 +47,21 @@ metadata:
               "scopes": [],
               "extraAuthParams": {
                 "resource": "https://mcp.asana.com/v2"
+              },
+              "verify": {
+                "url": "https://mcp.asana.com/v2/mcp",
+                "method": "POST",
+                "body": {
+                  "jsonrpc": "2.0",
+                  "id": 1,
+                  "method": "initialize",
+                  "params": {
+                    "protocolVersion": "2025-03-26",
+                    "capabilities": {},
+                    "clientInfo": { "name": "qvac", "version": "1.0.0" }
+                  }
+                },
+                "reject": [{ "status": [401, 403], "error": "asana_not_mcp_app" }]
               }
             }
           }

package/skills/diagrams/SKILL.md

@@ -3,6 +3,29 @@ name: diagrams
 description: Draw diagrams in the chat - flowcharts, sequence, state and ER diagrams, Gantt charts, pie charts, mindmaps and timelines - written as Mermaid code blocks the app renders. Use when the user asks to draw, diagram, sketch, chart, plan, visualize, or map a process, flow, schedule, architecture, or relationship.
 aliases: [diagram, mermaid, flowchart, mindmap]
 platform: [darwin, linux, win32, ios, android]
+version: 2
+# Tuned on Qwen3.5-2B with an offline eval (33 prompts, mention + prose routes, reasoning on as the app
+# runs it, 12k context, 180 s turn budget), judged by the app's own mermaid parser. QVAC-24436, QVAC-24502.
+# A run passes when the diagram asked for parses and reaches the reply with no tool JSON beside it, or,
+# for the three prompts that want a picture or a plot instead, when no diagram is drawn.
+# v1: router + references/<type>.md, harness 0.2.8. 3 repeats: mention 54/99, prose 20/36, 29 skill calls
+#   per run - the 2B loops on the second load (hallucinated files, repeats) until the turn budget ends,
+#   and the app shows the raw call or "Diagram unavailable". 71-77% of drawn blocks parsed.
+# v2: every recipe inline, nothing to load. Same harness, 3 repeats: mention 72/99, prose 31/36; 91-97%
+#   of drawn blocks parse; context 4156 / 4787 tokens against 5497 / 6317. Skill calls per run 23-35: the
+#   model still asks for a body it has, which @qvac/harness answers (a repeat load is acknowledged, not
+#   re-run; a misspelt file resolves to its nearest match). With those fixes, 3 repeats: 76/99 and 30/36,
+#   ~2 calls per run, context 4002 / 3771.
+#   Tried and dropped: the per-type size budgets from the reference files (12 nodes, 8 states, ...).
+#   They measured the same (79/99, 33/36 on harness main) but on a phone they cut a 40-node mind map to
+#   10 nodes: the eval scores what parses, not what was left out. The state alias for a spaced name and
+#   the gantt `axisFormat` / `excludes weekends` headers from the same files stayed: one clause each.
+#   This text, harness main, 3 repeats: mention 84/99, prose 28/36; 93-96% of drawn blocks parse; context
+#   3305 / 3730; ~2 skill calls per run; the ticket prompt 6 of 6.
+#   Not fixed. The three route-away prompts (a logo, a photo, a revenue plot) get a diagram 6-9 times
+#   in 9 on v2 against 4 in 9 on v1: a page that opens with "draw" draws. Four variants that reworded
+#   the "do not load" rule, or cut the recipes to 300 words, measured 25-55% against v1's 55% and were
+#   dropped.
 ---
 
 # Diagrams
@@ -15,53 +38,120 @@ never call an image tool, and never deliver it as a PDF or image file.
 
 Your reply STARTS with the fence. No preamble, no plan, no "I'll create a
 diagram showing..." - never announce or describe a diagram instead of drawing
-it. Decide the type silently, load its recipe, write the code block, close its
-fence, then add one short sentence saying what it shows - after the closing
+it. Decide the type silently, pick its recipe below, write the code block, close
+its fence, then add one short sentence saying what it shows - after the closing
 fence, never inside it. A complete reply looks like this:
 
 ```mermaid
 flowchart TD
-  A["User sends a message"] --> B{"Needs a tool?"}
-  B -->|yes| C["Run the tool"]
-  B -->|no| D["Answer directly"]
+  A["First step"] --> B{"Condition?"}
+  B -->|yes| C["Second step"]
+  B -->|no| D["Other step"]
 ```
 
-Flow of a message through the assistant.
-
-## Pick the Type, Then Load Its Recipe
-
-Each type's syntax lives in its own reference file, named by the Mermaid
-keyword. Pick the type from the ask, then call the `skill` tool with
-`name: "diagrams"` and `file: "references/<type>.md"` in the SAME turn you
-draw, BEFORE writing the fence - even when you drew another diagram earlier in
-this chat. Copy the recipe's syntax exactly; a diagram written from memory is
-the usual cause of a parse error. Each load is a real `skill` tool call -
-printing the call as JSON or text in your reply loads nothing. After the load,
-reply with the fenced block directly: no further tool calls of any kind.
-
-| The ask                                              | Type                | File                        |
-| ---------------------------------------------------- | ------------------- | --------------------------- |
-| steps, decisions, a process, "map / structure this"  | `flowchart TD`      | `references/flowchart.md`   |
-| a pipeline left to right                             | `flowchart LR`      | `references/flowchart.md`   |
-| a family tree, org chart, reporting lines            | `flowchart TD`      | `references/flowchart.md`   |
-| who calls whom over time, requests and replies       | `sequenceDiagram`   | `references/sequence.md`    |
-| modes and transitions                                | `stateDiagram-v2`   | `references/state.md`       |
-| tables and their relations                           | `erDiagram`         | `references/er.md`          |
-| code types, classes, inheritance                     | `classDiagram`      | `references/class.md`       |
-| a schedule or plan with durations                    | `gantt`             | `references/gantt.md`       |
-| dated events in order                                | `timeline`          | `references/timeline.md`    |
-| shares of a whole, percentages                       | `pie`               | `references/pie.md`         |
-| a brainstorm, idea tree, "mindmap"                   | `mindmap`           | `references/mindmap.md`     |
-
-Use `gitGraph` ONLY when the user names it. Never use experimental or beta
-diagram types, and never invent a keyword a recipe does not show.
+One sentence about what it shows. Copy the SHAPE of this block, never its
+words - the labels come from what the user asked about.
+
+## Pick the Type and Draw - Nothing to Load
+
+Every recipe is here. Pick the row that fits the ask, copy its shape, draw.
+Do not call any tool: the recipe you need is already on this page.
+
+**Steps, a process, a pipeline, an org chart** - `flowchart TD` (top-down) or `flowchart LR`:
+```mermaid
+flowchart LR
+  A["Request"] --> B{"Valid?"}
+  B -->|yes| C["Process"]
+  B -->|no| D["Reject with error"]
+```
+Nodes `id["Label"]`, decisions `id{"Question?"}`, arrows always `-->` with `-->|yes|` labels. Ids never reused. Never lowercase `end` - write `"End"`.
+
+**Who calls whom over time** - `sequenceDiagram`:
+```mermaid
+sequenceDiagram
+  participant App
+  participant Server
+  App->>Server: POST /login
+  Server-->>App: 200 with token
+```
+Declare every `participant` first. Call `A->>B: text`, reply `B-->>A: text`. Never `-->` here.
+
+**Modes and transitions** - `stateDiagram-v2`:
+```mermaid
+stateDiagram-v2
+  [*] --> Idle
+  Idle --> Running : start
+  Running --> [*] : shutdown
+```
+`[*]` starts and ends. `From --> To : label`. State names are single words or `snake_case`; for a spaced name write `state "Waiting for input" as Waiting` once, then `Waiting`.
+
+**Tables and relations** - `erDiagram`:
+```mermaid
+erDiagram
+  USER ||--o{ ORDER : "places"
+  ORDER ||--|{ LINE_ITEM : "contains"
+```
+Entities UPPER_CASE. `||--o{` one-to-many, `||--||` one-to-one. Label in plain quotes after the colon.
+
+**Classes and inheritance** - `classDiagram`:
+```mermaid
+classDiagram
+  class Animal {
+    +String name
+    +speak()
+  }
+  Animal <|-- Dog
+```
+Members inside `class Name { }`. Inheritance `Parent <|-- Child`. No quotes on class names.
+
+**A schedule with durations** - `gantt`:
+```mermaid
+gantt
+  title Delivery
+  dateFormat YYYY-MM-DD
+  section Planning
+    Requirements :a1, 2026-09-01, 5d
+    Design       :a2, after a1, 7d
+```
+Headers are only `title`, `dateFormat`, `axisFormat`, `excludes weekends`, `section`. EVERY other line is `Name :id, start, duration`.
+
+**Dated events in order** - `timeline`:
+```mermaid
+timeline
+  title Company history
+  2019 : Founded
+  2021 : First release
+  2024 : Series A
+```
+One `date : event` per line, indented under the title.
+
+**Shares of a whole** - `pie`:
+```mermaid
+pie title Time spent
+  "Coding" : 60
+  "Review" : 25
+  "Meetings" : 15
+```
+Every slice is `"Label" : number` - quoted label, plain number, no `%`.
+
+**A brainstorm or idea tree** - `mindmap`:
+```mermaid
+mindmap
+  root[Launch plan]
+    Marketing
+      Blog post
+    Engineering
+      Release build
+```
+`root[Topic]` once, then plain unquoted text, two more spaces per level. A second line at the root's depth fails.
+
+Use `gitGraph` ONLY when the user names it. Never invent a keyword not shown above.
 
 ## Hard Rules (every type)
 
 - One diagram per code block, and the fence language is exactly `mermaid`. The
-  first line inside the fence is the type keyword from the table. Default to
-  ONE block; use two only when the recipe's budget forces an overview plus one
-  detail. Never more than two.
+  first line inside the fence is a type keyword from the recipes above. Default to
+  ONE block; use two only for an overview plus one detail. Never more than two.
 - Except in mindmaps, node ids are letters, digits, and underscores, starting
   with a letter, never reused. Mindmap nodes have no ids.
 - Except in mindmaps, every label with a space, punctuation, or brackets goes
@@ -93,8 +183,8 @@ diagram types, and never invent a keyword a recipe does not show.
 ## If the diagram fails
 
 When a diagram cannot render, the app sends its parse error back to you once
-on its own, and the user may send it again. Re-load the type's recipe and fix
-by rewriting the ENTIRE code block, never a partial patch.
+on its own, and the user may send it again. Re-read the type's recipe above and
+fix by rewriting the ENTIRE code block, never a partial patch.
 
 | Error contains | Fix |
 | --- | --- |
@@ -103,5 +193,5 @@ by rewriting the ENTIRE code block, never a partial patch.
 | `Expecting ...` at a flowchart or sequence label | Put the whole label in double quotes |
 | `got 'end'` | Rename the node label to `"End"` |
 | `Maximum text size` or edge limit | Shrink the diagram or split it in two |
-| `No diagram type detected` | Start the fence with one type keyword from the table |
+| `No diagram type detected` | Start the fence with one type keyword from the recipes above |
 | `Duplicate id` | Give every node a fresh unique id |

package/skills/excel/SKILL.md

@@ -4,6 +4,10 @@ description: Create, edit, or read Excel spreadsheets (.xlsx) with openpyxl —
 aliases: [xlsx, spreadsheet, workbook]
 tools: [exec(python)]
 platform: [darwin, linux, win32]
+# Routing tuned on Qwen3.5-4B for QVAC-24106 ("@excel embed this image into a spreadsheet" after a
+# generate_image turn). The bullet list sent 13/14 runs to edit.md, and 6/14 ended with no image in
+# a workbook, most by asking the user to attach one. As a request -> file table: 5/5 to create.md and
+# 5/5 embedded the image; "add a fourth row" to a workbook built in the chat still loads edit.md, 3/3.
 metadata:
   {
     "openclaw":
@@ -32,17 +36,20 @@ copy its recipe and change the content:
 Each load is a real `skill` tool call — printing the call as JSON or text in
 your reply loads nothing.
 
-- **Creating a new workbook** (no existing file involved, including one that embeds
-  an image): call the `skill` tool with `name: "excel"` and
-  `file: "references/create.md"`.
-- **Editing an attached workbook** (change cells, add/insert/delete rows, columns or
-  sheets, or embed an image into one that already exists): call the `skill` tool with
-  `name: "excel"` and `file: "references/edit.md"`.
-- **Answering from an attached workbook** (a summary, a question answered,
-  values pulled into the chat — the deliverable is your reply, not a file): call
-  the `skill` tool with `name: "excel"` and `file: "references/read.md"`.
-- **Read then build** (e.g. "summarize this workbook into a new file"): load
-  `references/read.md` and the create or edit file — the read call runs first.
+Pick the file by whether an `.xlsx` is already in this chat:
+
+| The request                                                                         | Load                                            |
+| ----------------------------------------------------------------------------------- | ----------------------------------------------- |
+| "make a spreadsheet of …", "embed this image into a spreadsheet" — no `.xlsx` yet    | `references/create.md`                          |
+| "add a row", "change B2", "add this image to my budget.xlsx" — an `.xlsx` is here    | `references/edit.md`                            |
+| "what is the total in this sheet?", "summarize this workbook" — the answer is a reply | `references/read.md`                            |
+| "summarize this workbook into a new file"                                           | `references/read.md` first, then create or edit |
+
+Load it with the `skill` tool: `name: "excel"` and that `file`.
+
+**An image this chat generated is already attached.** A `generate_image` result in
+any earlier turn is the image "this image" means, and its `attachmentId` stages it.
+Never ask the user to attach an image the conversation already has.
 
 Never write the Python from memory. The recipes carry required patterns (the
 fill-in template, staging rules, guard asserts) that fail in non-obvious ways

package/skills/excel/references/edit.md

@@ -6,6 +6,10 @@ rows, columns, or sheets. Stage the workbook as an input, modify it, and save
 under a **new** output name such as `revised.xlsx` — never overwrite the staged
 input.
 
+**No `.xlsx` in this chat means this is not an edit.** "Put this image in a
+spreadsheet" with no workbook to open is a CREATE: load `references/create.md` and
+build a new one. Never ask the user to attach a workbook they did not mention.
+
 Macro-enabled files (`.xlsm`) can be staged as inputs and read, but this
 runtime cannot deliver `.xlsm` back — macros never survive. Save the edit as
 `.xlsx` and tell the user the macros were not preserved.

package/skills/gmail/SKILL.md

@@ -2,7 +2,7 @@
 name: gmail
 description: Read, search, send, and manage Gmail messages and labels via the Gmail REST API.
 aliases: [inbox, email+send, email+draft, email+reply, email+forward]
-tools: [http_request, gmail_send, gmail_draft]
+tools: [http_request, gmail_get, gmail_send, gmail_draft]
 platform: [darwin, linux, win32]
 credentials: [gmail_access_token]
 allow_list: [https://gmail.googleapis.com/gmail/v1/users/me/]
@@ -23,7 +23,7 @@ metadata:
             ],
             "configSteps": [
               "[Open Google Cloud Console](https://console.cloud.google.com/flows/enableapi?apiid=gmail.googleapis.com) to enable the Gmail API",
-              "[Open OAuth clients](https://console.cloud.google.com/auth/clients) to create an OAuth client — choose \"Desktop app\" as the type",
+              "[Open OAuth clients](https://console.cloud.google.com/auth/clients) to create an OAuth client — choose \"Web application\" as the type",
               "[Open OAuth audience](https://console.cloud.google.com/auth/audience) and add your Google account as a test user"
             ],
             "fields": [
@@ -43,7 +43,6 @@ metadata:
               "authUrl": "https://accounts.google.com/o/oauth2/v2/auth",
               "tokenUrl": "https://oauth2.googleapis.com/token",
               "tokenAuth": "secret-in-body",
-              "port": 18978,
               "scopes": [
                 "https://www.googleapis.com/auth/gmail.modify"
               ],
@@ -61,7 +60,7 @@ metadata:
 
 # Gmail
 
-Use `gmail_send` to send, `gmail_draft` to draft, and `http_request` for everything else (list, search, get, labels, trash). The Gmail credential is attached automatically to every `gmail.googleapis.com` request — **never include an `auth` block**.
+Read with `gmail_get`, send with `gmail_send`, draft with `gmail_draft`. `http_request` is only for list/search, labels and trash. The Gmail credential is attached automatically to every `gmail.googleapis.com` request — **never include an `auth` block**. Never run code.
 
 ## Prerequisites
 
@@ -76,11 +75,13 @@ set the `gmail_access_token` credential.
 
 The host is `gmail.googleapis.com` — not `www.googleapis.com`. Send is at `/messages/send`, never `/send`.
 
-## Common Operations
+## Read messages
 
-### List or search messages
+1. List with `http_request`. Use `q` for Gmail search (`from:`, `subject:`, `is:unread`, `newer_than:7d`, `has:attachment`, `label:work`). Keep `maxResults` ≤ 10. The result is ids only.
+2. Call `gmail_get` with each `id`. It returns `headers` (From, To, Subject, Date), `snippet` and, with `format: "full"`, `text`.
+3. Answer from those fields. Never run code.
 
-`messages.list` returns `{id, threadId}` pairs only — no subjects, no snippets. To summarize you need a follow-up `messages.get` per id. Use `q` for Gmail search syntax (`from:`, `subject:`, `is:unread`, `newer_than:7d`, `has:attachment`, `label:work`). Keep `maxResults` ≤ 10.
+`http_request` to list:
 
 ```json
 {
@@ -90,32 +91,15 @@ The host is `gmail.googleapis.com` — not `www.googleapis.com`. Send is at `/me
 }
 ```
 
-### Get a message (metadata)
-
-For lists and summaries always use `format=metadata` — it skips the body and is far cheaper than `full`.
+`gmail_get` for each id:
 
 ```json
-{
-  "url": "https://gmail.googleapis.com/gmail/v1/users/me/messages/{id}",
-  "method": "GET",
-  "query": {
-    "format": "metadata",
-    "metadataHeaders": "Subject,From,To,Date,Message-ID,References"
-  }
-}
+{ "id": "1a0c420faf8b68fe" }
 ```
 
-### Get a message (full body)
-
-Only when the user needs the content. The body is base64url-encoded in `payload.parts[].body.data` (or `payload.body.data`); decode it before presenting. Prefer the `text/plain` part over `text/html`.
+Use `format: "full"` only when the user asks what a message says.
 
-```json
-{
-  "url": "https://gmail.googleapis.com/gmail/v1/users/me/messages/{id}",
-  "method": "GET",
-  "query": { "format": "full" }
-}
-```
+## Common Operations
 
 ### Send a message
 
@@ -141,7 +125,7 @@ Use `gmail_draft` with the same envelope as `gmail_send`.
 
 A reply is `gmail_send` with the original's `threadId`, `inReplyTo`, and `references`. Without these Gmail starts a new thread.
 
-1. Get the original with `format=metadata` and headers `Message-ID,References,Subject,From,Reply-To`; capture its `threadId`.
+1. `gmail_get` the original; capture its `threadId` and its `Message-ID` and `References` headers.
 2. Send with `to` <- original From (or Reply-To), `subject` <- `Re: ` + original (don't double-prefix), `inReplyTo` <- original Message-ID, `references` <- original References then that Message-ID. Keep angle brackets.
 
 ```json
@@ -178,15 +162,15 @@ System labels: `INBOX`, `UNREAD`, `STARRED`, `IMPORTANT`, `SPAM`, `TRASH`. Mark
 
 ## Output Policy
 
-- Lists: up to 5 entries with subject, sender, and a human-readable date. Fetch full bodies only when asked.
-- Decode base64 message bodies before presenting; never include raw base64 blobs.
+- Lists: up to 5 entries with subject, sender, and a human-readable date. Fetch `text` only when asked.
 - Modify/trash: state the user-facing effect ("marked 3 messages as read"), not the label diff.
 - Confirm destructive or outgoing actions (send, reply, trash) with the user first.
 
 ## Common Mistakes
 
 - Using `www.googleapis.com` for Gmail, or building send/draft/reply through `http_request` instead of `gmail_send`/`gmail_draft`.
-- Treating `messages.list` results as if they had subjects — they need a follow-up `messages.get`.
+- Treating `messages.list` results as if they had subjects — call `gmail_get` for each id.
+- Reading a message through `http_request` or code instead of `gmail_get`.
 - Replying without `threadId` + `inReplyTo`/`references` — Gmail starts a new thread.
 - Sending a placeholder (`<RECIPIENT_EMAIL>`, `recipient@example.com`) — the runtime refuses these.
 - Inventing an address. The runtime refuses any recipient absent from the conversation and from earlier tool results; search Gmail or ask the user.

package/skills/gmail/operations.json

@@ -66,6 +66,29 @@
         "url": "https://gmail.googleapis.com/gmail/v1/users/me/drafts",
         "builder": "gmail-draft"
       }
+    },
+    {
+      "tool": "gmail_get",
+      "description": "Read one Gmail message by id: sender, recipients, subject, date, snippet and, with format \"full\", the message text. Call it for each id that messages.list returned. Never read a message with http_request or code.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "id": { "type": "string", "description": "Message id from messages.list" },
+          "format": {
+            "type": "string",
+            "enum": ["metadata", "full"],
+            "description": "metadata (default) for lists and summaries; full only when the user needs the message text"
+          }
+        },
+        "required": ["id"]
+      },
+      "request": {
+        "method": "GET",
+        "url": "https://gmail.googleapis.com/gmail/v1/users/me/messages/{id}",
+        "query": { "metadataHeaders": "Subject,From,To,Date,Message-ID,References" },
+        "builder": "gmail-get"
+      },
+      "response": { "decode": "gmail-message" }
     }
   ]
 }

package/skills/google-calendar/SKILL.md

@@ -23,7 +23,7 @@ metadata:
             ],
             "configSteps": [
               "[Open Google Cloud Console](https://console.cloud.google.com/flows/enableapi?apiid=calendar-json.googleapis.com) to enable the Google Calendar API",
-              "[Open OAuth clients](https://console.cloud.google.com/auth/clients) to create an OAuth client — choose \"Desktop app\" as the type",
+              "[Open OAuth clients](https://console.cloud.google.com/auth/clients) to create an OAuth client — choose \"Web application\" as the type",
               "[Open OAuth audience](https://console.cloud.google.com/auth/audience) and add your Google account as a test user"
             ],
             "fields": [
@@ -43,7 +43,6 @@ metadata:
               "authUrl": "https://accounts.google.com/o/oauth2/v2/auth",
               "tokenUrl": "https://oauth2.googleapis.com/token",
               "tokenAuth": "secret-in-body",
-              "port": 18978,
               "scopes": [
                 "https://www.googleapis.com/auth/calendar"
               ],

package/skills/google-docs/SKILL.md

@@ -22,7 +22,7 @@ metadata:
             ],
             "configSteps": [
               "[Open Google Cloud Console](https://console.cloud.google.com/flows/enableapi?apiid=docs.googleapis.com,drive.googleapis.com) to enable the Google Docs API",
-              "[Open OAuth clients](https://console.cloud.google.com/auth/clients) to create an OAuth client — choose \"Desktop app\" as the type",
+              "[Open OAuth clients](https://console.cloud.google.com/auth/clients) to create an OAuth client — choose \"Web application\" as the type",
               "[Open OAuth audience](https://console.cloud.google.com/auth/audience) and add your Google account as a test user"
             ],
             "fields": [
@@ -42,7 +42,6 @@ metadata:
               "authUrl": "https://accounts.google.com/o/oauth2/v2/auth",
               "tokenUrl": "https://oauth2.googleapis.com/token",
               "tokenAuth": "secret-in-body",
-              "port": 18978,
               "scopes": [
                 "https://www.googleapis.com/auth/documents",
                 "https://www.googleapis.com/auth/drive"

package/skills/google-drive/SKILL.md

@@ -22,7 +22,7 @@ metadata:
             ],
             "configSteps": [
               "[Open Google Cloud Console](https://console.cloud.google.com/flows/enableapi?apiid=drive.googleapis.com) to enable the Google Drive API",
-              "[Open OAuth clients](https://console.cloud.google.com/auth/clients) to create an OAuth client — choose \"Desktop app\" as the type",
+              "[Open OAuth clients](https://console.cloud.google.com/auth/clients) to create an OAuth client — choose \"Web application\" as the type",
               "[Open OAuth audience](https://console.cloud.google.com/auth/audience) and add your Google account as a test user"
             ],
             "fields": [
@@ -42,7 +42,6 @@ metadata:
               "authUrl": "https://accounts.google.com/o/oauth2/v2/auth",
               "tokenUrl": "https://oauth2.googleapis.com/token",
               "tokenAuth": "secret-in-body",
-              "port": 18978,
               "scopes": [
                 "https://www.googleapis.com/auth/drive"
               ],

package/skills/google-sheets/SKILL.md

@@ -23,7 +23,7 @@ metadata:
             ],
             "configSteps": [
               "[Open Google Cloud Console](https://console.cloud.google.com/flows/enableapi?apiid=sheets.googleapis.com,drive.googleapis.com) to enable the Google Sheets API",
-              "[Open OAuth clients](https://console.cloud.google.com/auth/clients) to create an OAuth client — choose \"Desktop app\" as the type",
+              "[Open OAuth clients](https://console.cloud.google.com/auth/clients) to create an OAuth client — choose \"Web application\" as the type",
               "[Open OAuth audience](https://console.cloud.google.com/auth/audience) and add your Google account as a test user"
             ],
             "fields": [
@@ -43,7 +43,6 @@ metadata:
               "authUrl": "https://accounts.google.com/o/oauth2/v2/auth",
               "tokenUrl": "https://oauth2.googleapis.com/token",
               "tokenAuth": "secret-in-body",
-              "port": 18978,
               "scopes": [
                 "https://www.googleapis.com/auth/spreadsheets",
                 "https://www.googleapis.com/auth/drive"

package/skills/diagrams/references/class.md

@@ -1,29 +0,0 @@
-# Class Diagram
-
-For code types: classes, their members, inheritance.
-
-Budget: 7 classes.
-
-```mermaid
-classDiagram
-  class Animal {
-    +String name
-    +speak()
-  }
-  Animal <|-- Dog
-```
-
-Rules:
-
-- Members go inside `class Name { }`, one per line, `+` public and `-`
-  private, methods end with `()`.
-- Inheritance is `Parent <|-- Child`; composition `Whole *-- Part`;
-  association `A --> B`.
-- Class names are single tokens; no quotes, no `classDef` lines.
-
-## Now draw
-
-This recipe is all you need. Your next output is the reply itself: one fenced
-Mermaid code block (fence language `mermaid`), then one sentence. Do not call
-any tool - not `exec`, not `skill` again, not an image tool. A tool call here
-means the diagram was never drawn.

package/skills/diagrams/references/er.md

@@ -1,27 +0,0 @@
-# ER Diagram
-
-For tables and their relations.
-
-Budget: 8 entities.
-
-```mermaid
-erDiagram
-  USER ||--o{ ORDER : "places"
-  ORDER ||--|{ LINE_ITEM : "contains"
-```
-
-Rules:
-
-- Entities are UPPER_CASE single tokens.
-- `||--o{` reads "one to zero-or-many"; `||--|{` "one to one-or-many";
-  `||--||` "one to one".
-- The relationship label follows the colon in plain double quotes typed directly (no backslash in front).
-- Attributes are optional; if used, list them inside `ENTITY { string name }`
-  blocks with one `type name` per line.
-
-## Now draw
-
-This recipe is all you need. Your next output is the reply itself: one fenced
-Mermaid code block (fence language `mermaid`), then one sentence. Do not call
-any tool - not `exec`, not `skill` again, not an image tool. A tool call here
-means the diagram was never drawn.

package/skills/diagrams/references/flowchart.md

@@ -1,33 +0,0 @@
-# Flowchart
-
-For steps, decisions, processes, pipelines, and any "map this / structure
-this" ask - also family trees, org charts, and reporting lines. `flowchart TD`
-reads top-down; `flowchart LR` left-to-right for a pipeline.
-
-Budget: 12 nodes and 16 edges. Over budget, simplify; if the detail is
-essential, one overview block plus one detail block, never more.
-
-```mermaid
-flowchart LR
-  A["Request"] --> B{"Valid?"}
-  B -->|yes| C["Process"]
-  B -->|no| D["Reject with error"]
-  C --> E["Respond"]
-```
-
-Rules:
-
-- Nodes are `id["Label"]`; decisions are `id{"Question?"}` diamonds.
-- Arrows are always `-->`; the label form is `-->|yes|`. Never `->>` here.
-- Ids: letters, digits, underscores, starting with a letter, never reused.
-- Every label goes in plain double quotes `"`, 40 characters or
-  fewer, `<br/>` for a line break. Never write lowercase `end` - use `"End"`.
-- One node per person or concept, details inside its label; no separate nodes
-  for dates, roles, counts, or statuses.
-
-## Now draw
-
-This recipe is all you need. Your next output is the reply itself: one fenced
-Mermaid code block (fence language `mermaid`), then one sentence. Do not call
-any tool - not `exec`, not `skill` again, not an image tool. A tool call here
-means the diagram was never drawn.