chore(skills): add disable-model-invocation, minor formatting fixes

- add disable-model-invocation: true to add-recipe, add-vinyl,
  auto-commit, daily-recap, dev-story, get-story, meeting-note,
  quick-note, spike, weekly-review skills
- simplify glab mr view command in address-review
- fix blank lines and markdown table alignment across skill docs

Author: dgokcin

ai-stuff/claude/skills/add-recipe/SKILL.md

@@ -2,6 +2,7 @@
 name: add-recipe
 description: Add a cooking recipe to the vault with proper frontmatter. Accepts a recipe name, description, or URL to parse.
 tools: Write, Read, Glob, WebFetch
+disable-model-invocation: true
 argument-hint: <recipe name or URL>
 ---
 

ai-stuff/claude/skills/add-vinyl/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: add-vinyl
 description: Add a vinyl record to the collection with Discogs metadata. Accepts artist and album name, or a Discogs URL.
+disable-model-invocation: true
 tools: Write, Read, Glob, WebFetch, WebSearch
 argument-hint: <"artist - album" or Discogs URL>
 ---
@@ -34,6 +35,7 @@ discogs_link: <full discogs release URL>
 date_of_purchase: <YYYY-MM-DD, default to today>
 purchased_store: <store name, ask user if not provided>
 ---
+
 tags:: [[virtual library]]
 
 ### Album Cover

ai-stuff/claude/skills/address-review/SKILL.md

@@ -53,7 +53,7 @@ Determine VCS:
 
 ### PR/MR Info
 
-!`gh pr view --json number,title,url,state 2>/dev/null || glab mr view --output json 2>/dev/null | python3 -c "import sys,json; d=json.load(sys.stdin); print(json.dumps({k:d[k] for k in ['iid','title','web_url','state'] if k in d}), end='')" 2>/dev/null || echo "no open pr/mr found"`
+!`gh pr view --json number,title,url,state 2>/dev/null || glab mr view 2>/dev/null || echo "no open pr/mr found"`
 
 ## Instructions
 

ai-stuff/claude/skills/auto-commit/SKILL.md

@@ -3,6 +3,7 @@ name: auto-commit
 description: Analyze all staged and unstaged changes, group them into logical commits, and execute them in order
 context: fork
 agent: gitboi
+disable-model-invocation: true
 allowed-tools:
   - Read
   - Grep
@@ -121,9 +122,10 @@ Start by surveying the damage:
 > [Analyzes all changes]
 >
 > OK here's the plan - I'm splitting this into N commits:
+>
 > 1. type(scope): what
 > 2. type(scope): what
-> ...
+>    ...
 >
 > [Executes each commit]
 >

ai-stuff/claude/skills/daily-recap/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: daily-recap
-description: Fetch today's activity from Slack, Gmail, and Google Calendar, then update/create your daily note in the vault with a recap and standup draft.
+description: "Fetch today's activity from Slack, Gmail, and Google Calendar, then update/create your daily note in the vault with a recap and standup draft."
+disable-model-invocation: true
 argument-hint: [YYYY-MM-DD] (defaults to today)
 model: sonnet
 allowed-tools:
@@ -65,6 +66,7 @@ Fetch today's activity from Slack, Gmail, and Google Calendar. Synthesize into a
 ### Step 1: Determine date
 
 Parse from `$ARGUMENTS`:
+
 - If a date like `2026-03-23`: use that
 - If empty: use today's date
 
@@ -73,6 +75,7 @@ Parse from `$ARGUMENTS`:
 #### 2a. Today's calendar events
 
 Fetch today's events using `gcal_list_events`:
+
 - Start: `YYYY-MM-DDT00:00:00`
 - End: `YYYY-MM-DDT23:59:59`
 - Note event titles, times, attendees
@@ -146,34 +149,40 @@ slack_read_thread(
 Use `gmail_search_messages` with multiple targeted searches:
 
 **General email search:**
+
 ```
 query: "after:YYYY/MM/DD before:YYYY/MM/DD+1"
 ```
 
 **GitLab-specific search** (MR reviews, pipeline updates, mentions):
+
 ```
 query: "from:gitlab@twtools.io after:YYYY/MM/DD before:YYYY/MM/DD+1"
 ```
 
 Look for:
+
 - **MR review requests** — your MR needs review or someone assigned you a review
 - **MR approvals/changes** — feedback on your MRs
 - **Pipeline notifications** — CI/CD failures or successes on your branch/MR
 - **Mentions in discussions** — someone @mentioned you in an MR comment or issue
 - **MR merges** — your MR or related MRs that merged
 
 **Jira-specific search** (ticket assignments, workflow changes):
+
 ```
 query: "from:jira@wahanda.atlassian.net after:YYYY/MM/DD before:YYYY/MM/DD+1"
 ```
 
 Look for:
+
 - **New tickets assigned to you** — add to `## recap → needs attention` with tag `#new-ticket`
 - **Status changes on your tickets** — useful context for what changed
 - **Comments on tickets you watch** — decide if actionable, flag with `#review-feedback` if relevant
 - **Blocker notifications** — tickets you're blocked on or blocking others
 
 **Read most relevant emails** with `gmail_read_message`. Focus on:
+
 - Action items (needs your review, response, or decision)
 - Decisions made (merged MRs, closed tickets)
 - Unresolved items (pending reviews, open feedback)
@@ -188,13 +197,15 @@ Dia is a browser that generates its own daily activity summaries as HTML artifac
 **If no output is returned**, skip this step silently.
 
 **Parse the HTML content** — look for these sections (the structure is consistent):
+
 - `.section` with section-label **"Completed"** → `.item h3` (title) + `.item p` (description) + `.tag` spans
 - `.section` with section-label **"Meetings"** → `.meeting` rows with time + title
 - `.section` with section-label **"Tomorrow"** → `.next-item` rows
 
 **If no context was modified today**, skip this step silently (don't fail).
 
 **Merge Dia data into synthesis (Step 4):**
+
 - Dia "Completed" items → merge into Bucket 1 (what you did today). Avoid duplicating items already captured from Slack/Gmail. Dia tends to have richer descriptions of browser-based work (MR reviews, Datadog investigations, etc.)
 - Dia "Tomorrow" items → merge into Bucket 2 (notes for tomorrow)
 - Dia tags (e.g. `DEVX-1111`, `Datadog`) → use as context when writing task descriptions, but don't include them literally as Obsidian tags
@@ -204,6 +215,7 @@ Dia is a browser that generates its own daily activity summaries as HTML artifac
 When synthesizing Slack data, apply these filters:
 
 **Keep** (work signal):
+
 - Thread replies in team channels (#team-devx-public, #team-devx-private, etc.)
 - Code review discussions (MR links, GitLab/GitHub links)
 - Support given (helping others with questions)
@@ -212,6 +224,7 @@ When synthesizing Slack data, apply these filters:
 - PR approval requests
 
 **Skip** (noise):
+
 - Personal DM chatter (physio appointments, office plans, social banter)
 - Short acknowledgments ("hi", "yess", "sure", emoji-only messages)
 - Bot messages that are purely informational (unless they indicate something actionable)
@@ -225,9 +238,11 @@ Check the injected **"Existing daily notes"** list above:
 
 - **If `YYYY-MM-DD.md` appears in the list**: the note exists — read it with `obsidian read path="work/daily notes/YYYY-MM-DD.md"`
 - **If it does NOT appear**: create it from template:
+
   ```bash
   obsidian create name="YYYY-MM-DD" path="work/daily notes" template="daily-template" silent
   ```
+
   Wait (`sleep 3`) for Templater to process, then read it.
 
 ### Step 4: Synthesize and format output
@@ -253,6 +268,7 @@ Read the daily note file directly to find each section, then use `Edit` to inser
 ### Step 6: Summary
 
 After writing, give a brief conversational summary:
+
 - One line on the overall vibe of the day
 - Call out 1-2 things that need attention tomorrow
 - Confirm the file was updated

ai-stuff/claude/skills/dev-story/SKILL.md

@@ -3,6 +3,7 @@ name: dev-story
 description: Fetch a Jira story and prepare development context. Use when starting work on a ticket, need to understand requirements, or want to prepare for implementation
 context: fork
 agent: jiragirl
+disable-model-invocation: true
 allowed-tools: mcp__claude_ai_Atlassian__getJiraIssue, mcp__claude_ai_Atlassian__getJiraIssueRemoteIssueLinks, mcp__claude_ai_Atlassian__searchJiraIssuesUsingJql, Read, Glob, Grep
 argument-hint: <DEVX-XXX or issue key>
 ---
@@ -12,9 +13,11 @@ argument-hint: <DEVX-XXX or issue key>
 You are **Jira Girl** fetching story context, then handing off to development mode.
 
 ## Persona
+
 @~/.claude/personas/jira-girl.md
 
 ## Configuration
+
 @~/.claude/config/jira-config.md
 
 ## Instructions
@@ -24,14 +27,17 @@ Fetch a Jira story and prepare comprehensive development context.
 ### Process
 
 1. Parse issue key from: `$ARGUMENTS`
+
    - If just a number, prepend `DEVX-`
    - If full key provided, use as-is
 
 2. Fetch the issue using `mcp__claude_ai_Atlassian__getJiraIssue`:
+
    - cloudId: `56552dac-b6cf-4e59-aa06-5e075dca9f8e`
    - issueKey: parsed from arguments
 
 3. Extract and present:
+
    - **Summary**: Issue title
    - **Description**: Full description content
    - **Acceptance Criteria**: From `customfield_10020` if present
@@ -41,31 +47,39 @@ Fetch a Jira story and prepare comprehensive development context.
    - **Linked Issues**: Related tickets
 
 4. Check for remote links (PRs, external refs):
+
    ```
    mcp__claude_ai_Atlassian__getJiraIssueRemoteIssueLinks
    ```
 
 5. Format output for development handoff:
+
    ```markdown
    # DEVX-XXX: [Summary]
 
    ## Status
+
    [Current status]
 
    ## Description
+
    [Full description]
 
    ## Acceptance Criteria
+
    - [ ] Criterion 1
    - [ ] Criterion 2
 
    ## Linked Issues
+
    - DEVX-YYY: Related ticket
 
    ## Remote Links
+
    - PR #123: [title]
 
    ## Ready for Development
+
    [Brief summary of what needs to be done]
    ```
 

ai-stuff/claude/skills/get-story/SKILL.md

@@ -4,6 +4,7 @@ description: Fetch and display a Jira issue with all details using Jira Girl. Us
 context: fork
 agent: jiragirl
 allowed-tools: mcp__claude_ai_Atlassian__getJiraIssue
+disable-model-invocation: true
 argument-hint: <DEVX-XXX or issue number>
 ---
 
@@ -12,9 +13,11 @@ argument-hint: <DEVX-XXX or issue number>
 You are **Jira Girl** - fetch that issue and serve it up with enthusiasm!
 
 ## Persona
+
 @~/.claude/personas/jira-girl.md
 
 ## Configuration
+
 @~/.claude/config/jira-config.md
 
 ## Instructions
@@ -24,18 +27,21 @@ Fetch a Jira issue and display only the body content and comments.
 ### Process
 
 1. Parse issue key from: `$ARGUMENTS`
+
    - If just a number (e.g., `123`), prepend `DEVX-`
    - If full key (e.g., `DEVX-123`), use as-is
    - If different project prefix, use that
 
 2. Fetch the issue:
+
    ```
    mcp__claude_ai_Atlassian__getJiraIssue
    - cloudId: 56552dac-b6cf-4e59-aa06-5e075dca9f8e
    - issueKey: <parsed key>
    ```
 
 3. Display only:
+
    - **Description** (full content)
    - **Comments** (all footer and inline comments)
 
@@ -49,6 +55,7 @@ Fetch a Jira issue and display only the body content and comments.
 [Full description content]
 
 ## Comments
+
 [All comments displayed in order]
 
 View: [DEVX-XXX](https://wahanda.atlassian.net/browse/DEVX-XXX)

ai-stuff/claude/skills/meeting-note/SKILL.md

@@ -2,6 +2,7 @@
 name: meeting-note
 description: "Create a meeting note in the vault with proper frontmatter and structure. Use when the user mentions a meeting, wants to take notes for a call, says 'meeting with X', 'sync with X', 'let me document this call', or is about to join or just finished a meeting."
 tools: Bash, Read
+disable-model-invocation: true
 argument-hint: <meeting title>
 ---
 
@@ -14,29 +15,34 @@ Create a meeting note in the Obsidian vault using the `meeting-template` via the
 1. Parse the meeting title from: `$ARGUMENTS`
    - If no arguments provided, ask for the meeting title
 2. Create the note using the Obsidian CLI:
+
    ```bash
    obsidian create name="<meeting title>" template="meeting-template"
    ```
+
    The template handles everything — frontmatter, date prefix, folder placement (`work/meetings/`), and structure. No need to manually construct paths or content.
 3. Confirm creation and report the file path
 
 ### What the template produces
 
 The meeting-template creates a note at `work/meetings/YYYY-MM-DD <title>.md` with:
+
 - Frontmatter: date, type, client, tags, summary
 - Sections: Attendees, Agenda, Questions, Notes, Action Items
 - Wikilinks to the daily note and meetings MoC
 
 ### After creation
 
 If the user provided attendees, agenda items, or context in their message, use `obsidian append` to fill in the relevant sections:
+
 ```bash
 obsidian append file="YYYY-MM-DD <title>" content="- @person1\n- @person2"
 ```
 
 ### Summary field
 
 The `summary` frontmatter field is important — it powers the meeting views (MoC, date summary, monthly summary). Remind the user to fill it in after the meeting, or offer to set it if they share what the meeting was about:
+
 ```bash
 obsidian property:set file="YYYY-MM-DD <title>" name="summary" value="discussed X and decided Y"
 ```

ai-stuff/claude/skills/quick-note/SKILL.md

@@ -2,6 +2,7 @@
 name: quick-note
 description: "Quick capture a note to work/random or personal/random. Use when the user says 'jot this down', 'save this thought', 'note to self', 'remember this idea', or mentions a random idea, link, or snippet they want to capture. Also trigger when the user wants to quickly save something without specifying a particular note type."
 tools: Bash, Read
+disable-model-invocation: true
 argument-hint: <note title> [--personal]
 ---
 
@@ -17,15 +18,19 @@ Quickly capture a note to the vault's random folders using the Obsidian CLI.
    - The remaining text is the note title
    - If no arguments: ask what to capture
 2. Create the note using the Obsidian CLI:
+
    ```bash
    obsidian create path="<work|personal>/random/<title slug>.md" content="# <Title>"
    ```
+
    - title slug: lowercase with spaces (e.g., `devx support bot idea.md`)
    - No template needed — quick notes are intentionally minimal
 3. If the user provided content in the same message, append it:
+
    ```bash
    obsidian append file="<title slug>" content="<the content>"
    ```
+
 4. Report the created file path when done
 
 ### Rules