edmundmiller/dotfiles/walking-mode
Claude Code and agent skill by edmundmiller/dotfiles
- community
Checking that the SKILL.md file is still in the repository.
Low-interruption coordination for realtime voice sessions. Use when the user says "walking mode," says they are walking, hands-free, or not at the computer, or asks for fewer voice updates while juggling tasks. Do not use for ordinary requests to write concisely.
Install
npx vskill@latest install edmundmiller/dotfiles/walking-modeSKILL.md
Walking mode
Treat attention as scarce. Keep an internal ledger of each task and thread: state, next step, blocker, and evidence. Compress what is spoken, not what is tracked.
Acknowledge activation once in one short sentence. Keep the mode active across tasks until the user explicitly asks for normal or full updates, or the voice session ends. A request for one detail or status does not end the mode.
Interruption gate
Before speaking, place the update in one lane:
- Interrupt now: Safety-critical information; a decision, approval, input,
or physical action only the user can provide; a terminal outcome that changes their next move; or a report required by higher-priority instructions.
- Hold for recap: Ordinary completions, nonurgent blockers, routine
dispatch or tool narration, process details, unchanged waits, and repeated status.
- Put on screen: Place exact IDs, paths, commands, links, code, test counts,
and long evidence in a visual or on-screen artifact when useful. Speak only the decision or outcome they support unless the user asks to hear the detail.
For mandatory safety, dispatch, or progress reporting, use the shortest clear wording and keep supporting detail on screen. Never imply that a required report was disabled.
Spoken coordination
- When the user must respond, ask one question. Lead with the concrete decision
or action and the minimum context needed to answer.
- At a natural pause or when asked, bundle held items into a short recap. Prefer
one sentence; use Done / Waiting on you / Still running when those labels are clearer.
- State changed outcomes and the user's next action. Keep all held detail
available for later recall.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/conditional/codex/walking-mode/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/edmundmiller/dotfiles/walking-mode)