/diff-remove
Remove a previously adopted DexDiff workflow — deletes its generated skills and config, leaves your data untouched. Use when the user says 'remove that workflow', 'undo the adoption'. Not for listing what's installed; use `diff-list`.
$ npx -y skills add davekilleen/Dex --skill diff-remove --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/diff-remove
Context preview
The summary Claude sees to decide when to auto-load this skill.
Remove a previously adopted DexDiff workflow — deletes its generated skills and config, leaves your data untouched. Use when the user says 'remove that workflow', 'undo the adoption'. Not for listing what's installed; use `diff-list`.
SKILL.md
diff-remove.SKILL.mdname: diff-remove
description: "Remove a previously adopted DexDiff workflow — deletes its generated skills and config, leaves your data untouched. Use when the user says 'remove that workflow', 'undo the adoption'. Not for listing what's installed; use `diff-list`."
What This Command Does
**In plain English:** Undo a DexDiff adoption. Removes the skills, CLAUDE.md sections, and templates that were created when you adopted a workflow. Your data (meeting notes, people pages, etc.) is never deleted.
**When to use it:**
- You adopted a workflow and want to remove it
- You want to clean up before re-adopting an updated version
**How to run it:**
/diff-remove meeting-prep
/diff-remove
---
Arguments
`$ARGUMENTS` — The diff ID of the workflow to remove. This is the `id` field from the methodology YAML, logged during adoption.
If no argument is provided, list all installed diffs and let the user pick:
You have these adopted workflows:
meeting-prep — "Meeting Prep Ritual" (adopted 2026-03-28)
deal-review — "Deal Review Ritual" (adopted 2026-03-25)
Which one would you like to remove?
To get the list, read all JSON files in **both** adoption locations:
- `.dex/adoptions/` - single-workflow adoptions from `/diff-adopt`
- `System/.dex/adoptions/profiles/` - whole-profile adoptions from `/diff-adopt-profile` (these are profile-level records; removing one means removing the skills generated for that profile's workflows, then deleting the profile log)
---
Process
Step 1: Find the Adoption Log
Read `.dex/adoptions/$ARGUMENTS.json`. If it is not there and `$ARGUMENTS` looks like a handle, check `System/.dex/adoptions/profiles/$ARGUMENTS.json` instead.
If the file doesn't exist:
No adoption record found for "$ARGUMENTS".
This means either:
- It was never adopted via /diff-adopt
- It was already removed
- The adoption log was deleted
I can't safely remove it without knowing what was created.
If you want to manually clean up, check .claude/skills/ for related skill folders.
Stop here. Do not attempt to guess what to delete.
Step 2: Parse the Log
Extract:
- `files_created` — every file created during adoption
- `folders_created` — every folder created
- `claude_md_sections` — every CLAUDE.md section title added
Step 3: Check What Still Exists
For each file in `files_created`:
- Check if the file still exists
- If it's been modified since adoption, flag it
For each CLAUDE.md section in `claude_md_sections`:
- Check if the section title still appears in CLAUDE.md
Step 4: Preview the Removal
Removing [diff_name] will:
Delete files:
- .claude/skills/meeting-prep/SKILL.md
- .claude/skills/process-meeting/SKILL.md
Remove from CLAUDE.md:
- "Meeting Workflow" section
NOT deleted (your data is safe):
- [folders] and everything inside them
- Any files you created yourself
[If any files were modified:]
Note: These files were modified after adoption:
- .claude/skills/meeting-prep/SKILL.md (you may have customised it)
Continue? [Yes, remove] [Cancel]Step 5: Remove Files
For each file in `files_created`:
- Delete the file
- If the parent directory is now empty AND inside `.claude/skills/`, delete the empty directory
- Do NOT delete directories outside `.claude/skills/`
Step 6: Remove CLAUDE.md Sections
For each section in `claude_md_sections`:
- Search CLAUDE.md for a heading with that title
- Remove the heading and all content until the next heading of equal or higher level
- If the section can't be found, skip and note it
Step 7: Clean Up
Delete `.dex/adoptions/$ARGUMENTS.json`.
Step 8: Confirm
Done. [diff_name] removed.
Files deleted: [count]
CLAUDE.md sections removed: [count]
Your data in [folders] was not touched.
---
Important Rules
- **Never delete folders created during adoption.** The user may have added content. Folders are never removed.
- **Never delete files not in the adoption log.** The log is the single source of truth.
- **Never delete without preview and confirmation.** Always show what will be removed first.
- **If the adoption log is missing, stop.** Do not guess.
- **Flag modified files.** If a skill was customised after adoption, warn before deleting.
Read more
name: diff-remove description: "Remove a previously adopted DexDiff workflow — deletes its generated skills and config, leaves your data untouched. Use when the user says 'remove that workflow', 'undo the adoption'. Not for listing what's installed; use `diff-list`."
What This Command Does
**In plain English:** Undo a DexDiff adoption. Removes the skills, CLAUDE.md sections, and templates that were created when you adopted a workflow. Your data (meeting notes, people pages, etc.) is never deleted.
**When to use it:**
- You adopted a workflow and want to remove it
- You want to clean up before re-adopting an updated version
**How to run it:**
/diff-remove meeting-prep /diff-remove
---
Arguments
`$ARGUMENTS` — The diff ID of the workflow to remove. This is the `id` field from the methodology YAML, logged during adoption.
If no argument is provided, list all installed diffs and let the user pick:
You have these adopted workflows: meeting-prep — "Meeting Prep Ritual" (adopted 2026-03-28) deal-review — "Deal Review Ritual" (adopted 2026-03-25) Which one would you like to remove?
To get the list, read all JSON files in **both** adoption locations:
- `.dex/adoptions/` - single-workflow adoptions from `/diff-adopt`
- `System/.dex/adoptions/profiles/` - whole-profile adoptions from `/diff-adopt-profile` (these are profile-level records; removing one means removing the skills generated for that profile's workflows, then deleting the profile log)
---
Process
Step 1: Find the Adoption Log
Read `.dex/adoptions/$ARGUMENTS.json`. If it is not there and `$ARGUMENTS` looks like a handle, check `System/.dex/adoptions/profiles/$ARGUMENTS.json` instead.
If the file doesn't exist:
No adoption record found for "$ARGUMENTS". This means either: - It was never adopted via /diff-adopt - It was already removed - The adoption log was deleted I can't safely remove it without knowing what was created. If you want to manually clean up, check .claude/skills/ for related skill folders.
Stop here. Do not attempt to guess what to delete.
Step 2: Parse the Log
Extract:
- `files_created` — every file created during adoption
- `folders_created` — every folder created
- `claude_md_sections` — every CLAUDE.md section title added
Step 3: Check What Still Exists
For each file in `files_created`:
- Check if the file still exists
- If it's been modified since adoption, flag it
For each CLAUDE.md section in `claude_md_sections`:
- Check if the section title still appears in CLAUDE.md
Step 4: Preview the Removal
Removing [diff_name] will:
Delete files:
- .claude/skills/meeting-prep/SKILL.md
- .claude/skills/process-meeting/SKILL.md
Remove from CLAUDE.md:
- "Meeting Workflow" section
NOT deleted (your data is safe):
- [folders] and everything inside them
- Any files you created yourself
[If any files were modified:]
Note: These files were modified after adoption:
- .claude/skills/meeting-prep/SKILL.md (you may have customised it)
Continue? [Yes, remove] [Cancel]Step 5: Remove Files
For each file in `files_created`:
- Delete the file
- If the parent directory is now empty AND inside `.claude/skills/`, delete the empty directory
- Do NOT delete directories outside `.claude/skills/`
Step 6: Remove CLAUDE.md Sections
For each section in `claude_md_sections`:
- Search CLAUDE.md for a heading with that title
- Remove the heading and all content until the next heading of equal or higher level
- If the section can't be found, skip and note it
Step 7: Clean Up
Delete `.dex/adoptions/$ARGUMENTS.json`.
Step 8: Confirm
Done. [diff_name] removed. Files deleted: [count] CLAUDE.md sections removed: [count] Your data in [folders] was not touched.
---
Important Rules
- **Never delete folders created during adoption.** The user may have added content. Folders are never removed.
- **Never delete files not in the adoption log.** The log is the single source of truth.
- **Never delete without preview and confirmation.** Always show what will be removed first.
- **If the adoption log is missing, stop.** Do not guess.
- **Flag modified files.** If a skill was customised after adoption, warn before deleting.
A personal operating system powered by Claude. Strategic work management, meeting intelligence, relationship tracking, daily planning — all configured for your specific role. No coding required.
Repo: davekilleen/Dex
Other skills on davekilleen-dex.
- /agent-browser
Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Alternative to Playwright MCP - uses Bash commands with ref-based element selection. Triggers on "browse website", "fill form", "click
Open skill - /agent-native-architecture
Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.
Open skill - /andrew-kane-gem-writer
This skill should be used when writing Ruby gems following Andrew Kane's proven patterns and philosophy. It applies when creating new Ruby gems, refactoring existing gems, designing gem APIs, or when clean, minimal, production-ready Ruby library code is needed. Triggers on
Open skill - /brainstorming
This skill should be used before implementing features, building components, or making changes. It guides exploring user intent, approaches, and design decisions before planning. Triggers on "let's brainstorm", "help me think through", "what should we build", "explore
Open skill - /compound-docs
Capture solved problems as categorized documentation with YAML frontmatter for fast lookup
Open skill - /create-agent-skills
Expert guidance for creating, writing, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.
Open skill

