nuke
- Repo stars 330
- License MIT
- Author updated Live
- Author repo claude-skill-registry
- Domain
- Data
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 94 / 100 · audit passed
- Author / version / license
- @majiayu000 · MIT
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Not required
- Operating systems
- macOS · Linux · Windows
- Runtime requirements
- Node.js
- Permissions
-
- Read-only
- Write / modify
- Shell exec
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: nuke
description: Kill all shella processes and reset state. Nuclear option when things are broken. Use with cauti…
category: data
runtime: Node.js
---
# nuke output preview
## PART A: Task fit
- Use case: Kill all shella processes and reset state. Nuclear option when things are broken. Use with caution. Kill all shella processes and optionally clear state. This is destructive - only run when explicitly requested. runs entirely locally; runs on Node.js. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Steps / After Nuking” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Kill all shella processes and reset state. Nuclear option when things are broken. Use with caution. Kill all shella processes and optionally clear state. This is destructive - only run when explicitly requested. runs entirely locally; runs on Node.js. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “Steps / After Nuking” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files, run shell commands.
Start with a small task and check whether the result follows “Steps / After Nuking”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: nuke
description: Kill all shella processes and reset state. Nuclear option when things are broken. Use with cauti…
category: data
source: majiayu000/claude-skill-registry
---
# nuke
## When to use
- Kill all shella processes and reset state. Nuclear option when things are broken. Use with caution. Kill all shella pr…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Steps / After Nuking” and keep inference separate from source facts.
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "nuke" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Steps / After Nuking
rules -> SKILL.md triggers / order / output contract
runtime -> Node.js | read files, write/modify files, run shell commands | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Nuke Shella State
Kill all shella processes and optionally clear state. This is destructive - only run when explicitly requested.
Steps
Confirm with user before proceeding. This will:
- Kill all processes on ports 47100-47200
- Optionally delete registry.json (layout and instance state)
Kill processes on shella ports:
lsof -i :47100-47200 -P -n -t 2>/dev/null | xargs -r kill -9Kill any remaining shella-related node processes (if needed):
pkill -f "shella" 2>/dev/null || trueOptionally clear state (ask user first):
rm -f ~/.local/state/shella/registry.json rm -f ~/.local/state/shella/dev.logVerify clean:
lsof -i :47100-47200 -P -n 2>/dev/null | grep LISTENShould return nothing.
After Nuking
Tell the user to restart with:
npm run dt dev daemonOr for full stack:
npm run dt dev all
Decide Fit First
Design Intent
How To Use It
Boundaries And Review