Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Uninstall

ASecurity

Finds everything bootstrap/capture added to this project and offers to detach or remove it, before you actually uninstall the kms plugin. Use when a team is winding down use of kms, e.g. "we're uninstalling kms, clean up what it added", "remove kms's guardrails from this repo".

3 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgorails

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add vivantel/kms --skill uninstall --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Uninstall?

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

Security grade badge for Uninstall
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/vivantel-uninstall/badge)](https://www.skillsdirectory.com/skills/vivantel-uninstall)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: uninstall
description: Finds everything bootstrap/capture added to this project and offers to detach or remove it, before you actually uninstall the kms plugin. Use when a team is winding down use of kms, e.g. "we're uninstalling kms, clean up what it added", "remove kms's guardrails from this repo".
---

Run this *before* uninstalling the `kms` plugin — nothing can act automatically afterward, so this is the only window for cleanup. Finds every trace `bootstrap`/`capture` left in this project and offers to detach (keep the content, stop tracking it as kms's) or remove it.

## What to scan for

1. **`kms-seeded: true` files** — anywhere under `docs/`, matching this skill's sibling `../../templates/` (one subdirectory per artifact type; currently just `guardrails/`).
2. **`kms-generated: true` files** — scan for the marker anywhere under `docs/`, the same way as category 1; don't hardcode which files carry it, since `bootstrap` may stamp more of them over time (currently `docs/skills/product-track-roles.md`, `docs/skills/process-track-roles.md`, and `docs/facts/docs-manifest.md`, all three written by a single `bootstrap` run).
3. **The `<!-- kms:start -->`/`<!-- kms:end -->` block** in the project's agent-instructions file (`AGENTS.md` or whatever host-specific equivalent it uses), if present.
4. **Still-`status: draft` decisions, or facts still `governed-by: TBD`** — a proposal (from `bootstrap` or from `capture`'s own check 1, which drafts stubs the same way) that nobody has acted on yet. Report these separately from categories 1-3 and note plainly that they carry no `kms-seeded`/`kms-generated` marker — they're identified by status, not by marker.

## Report first, then act

List everything found, grouped by category, before asking about any of it — never surface per-file prompts one at a time with no overview. Then, per finding, ask: **detach** (strip `kms-seeded`/`kms-generated`, or the AGENTS.md markers alone leaving the section text, keeping everything else as the team's own) or **remove** (delete the file, or delete just the marked block from AGENTS.md, or delete the still-draft decision/fact). Same confirmation for both — propose, wait for an explicit yes, exactly like every other skill in this plugin.

## Never touch

Any decision/fact past `status: draft`/`governed-by: TBD` — that's the team's own commitment, regardless of topic, marker or no marker. Any guardrail without a `kms-seeded` marker, or any other file without `kms-generated`, outside of category 4 above — that's project-owned. Custom guardrails the team wrote themselves, even ones that resemble something `kms` seeds.

## Out of scope

`plugins/kms/hooks/hooks.json` — it lives in the plugin's own installed directory, not this project's repo, and the host removes it automatically when the plugin is uninstalled. Actually uninstalling the plugin itself — that's a host command, not this skill's job.

Attribution

vivantelvivantel
View sourceMore from vivantel →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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 DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 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', ...

686011 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.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →