Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Rpi Detach

ASecurity

Remove proven-owned RPI installation components while preserving project instructions, custom settings, skills and user work products.

5 stars
0 votes
0 copies
0 views
Added 10/4/2026
ai-agents

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 10/4/2026

$npx -y skills add juan294/cc-rpi --skill rpi-detach --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Rpi Detach?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Rpi Detach
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/juan294-rpi-detach/badge)](https://www.skillsdirectory.com/skills/juan294-rpi-detach)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: "rpi-detach"
description: "Remove proven-owned RPI installation components while preserving project instructions, custom settings, skills and user work products."
argument-hint: "[request]"
disable-model-invocation: true
---
The request is supplied as literal arguments: $ARGUMENTS


# Detach a Project from RPI

Remove only proven-owned unchanged RPI components within the explicit detach
request. Keep project intelligence, custom settings and user work products.

Read [the lifecycle contract](references/lifecycle-contract.md) completely.
Resolve the installed package/source and target project from actual metadata and
the request; do not assume the current directory is the intended target. Use the
ownership-aware engine's explicit source/target plan/apply interface. Skill
invocation or tool visibility does not grant extra authority.

## Inventory and review

1. Read the project's manifest/baselines, legacy evidence and current registrations.
   If no owned installation exists, report nothing to detach; preserve unknown
   candidates. Native plugin removal and shared user lifecycle removal are separate
   scopes; project detach cannot remove them.
2. Generate the engine's explicit `detach` plan for the target. Classify owned
   unchanged files, owned edited files, managed blocks/settings keys, unknown
   content and user work products. Record exactly what is removed and retained.
3. Present the concrete diff and recovery location. Use the detach authorization
   already supplied for safe owned removal; seek input only for a genuinely new
   destructive scope. A detach request does not authorize removal of research,
   plans, decisions, handoffs, custom skills, schedules or unrelated settings.

## Apply and preserve

1. Apply the reviewed engine plan transactionally after baseline/precondition
   verification. Retain edited or unknown files and explain the disposition.
2. Preserve AGENTS.md and CLAUDE.md; remove only their proven-owned unchanged
   blocks while keeping user additions and valid instruction relationships.
3. Remove only individually owned unchanged settings/hook registrations. Keep
   remaining JSON keys, permissions, environment and the user's settings files.
4. Preserve native plugin cache ownership and the independent user-scope lifecycle
   installation. Do not bulk-delete `.claude`, `.agents`, command or skill trees.
5. Keep curated docs and operational reports/logs. Remove only empty owned
   directories when safe. Existing launchd/cron schedules require their own
   explicit scope and concrete reviewed change; do not unload them implicitly.
6. Preserve recovery receipts and required baseline bytes outside the removed
   tree until verification and any recovery obligation finish.

## Completion

Verify remaining user files/settings and native registrations, removed managed
components, instruction integrity and recovery availability. Commit only the
reviewed local detach changes atomically where appropriate. Report removed and
retained files/blocks/keys, conflicts, recovery location and commit identity.
Do not claim complete detachment when conflicts remain. A repeated detach should
make no further changes. Re-adoption uses `rpi-adopt`; do not start it automatically.

Attribution

juan294juan294
View sourceSee grades on GitHubMore from juan294 →
SSkills Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →