$ loading_
Safely uninstall, disable, and re-enable community skills with audit logging.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "skill-manager" skill from askskill: 1. Download https://raw.githubusercontent.com/anthropics/claude-for-legal/main/legal-builder-hub/skills/skill-manager/SKILL.md 2. Save it as ~/.claude/skills/skill-manager/SKILL.md 3. Reload skills and tell me it's ready
Please uninstall the community skill named contract-review-helper. First check install-log.yaml, list the files to be deleted and any config that will be kept, then wait for my confirmation.
It verifies the skill was installed through the hub, shows the deletion list and retained config, and only uninstalls and logs the action after an explicit yes.
Please disable the community skill skills-deadline-alert, tell me which files will be renamed, and then wait for confirmation.
It outputs the files to be renamed, such as SKILL.md, hooks config, or agent files, and after confirmation renames them to disabled variants so the skill stops running.
Please uninstall the privacy-legal skill.
It identifies the skill as a built-in plugin or otherwise not eligible as a community install, refuses deletion or renaming, and explains why.
After trying multiple community skills, developers or DevOps users can use it to verify origin against the install log and safely remove files. It shows the deletion scope first and requires explicit confirmation to avoid mistakes.
When a community skill needs to be paused, it can disable the skill by renaming key files. It keeps configuration directories intact for later re-enabling or reinstallation.
If a user mistakenly treats a built-in legal plugin like a community skill, it refuses the action based on install records and directory checks. This helps protect plugins that ship with claude-for-legal.
The README describes Skill Manager as a safe companion to the installer for removing or disabling community skills installed through the legal builder hub. It uses install-log.yaml as the source of truth, refuses to touch built-in plugins, shows users exactly which files will be deleted or renamed, requires explicit confirmation, and then records the action and updates related hub metadata.
Remove or quiet a community skill after install. Symmetric with the installer:
the installer writes files with user approval, the skill-manager removes or
disables them with user approval. The installer's audit trail (install-log.yaml)
is the source of truth for what this skill may act on.
Only community skills installed through this hub. Identification rule:
~/.claude/plugins/config/claude-for-legal/legal-builder-hub/install-log.yaml
with a most-recent action of install or enable (not uninstall).If either check fails, refuse and tell the user why. Never delete or rename files inside a first-party plugin.
The 12 core plugins that ship with claude-for-legal are off-limits from this
command. The canonical list lives in the hub's CLAUDE.md under "Built-in
plugins." Examples include commercial-legal, corporate-legal,
employment-legal, privacy-legal, product-legal, regulatory-legal,
ai-governance-legal, litigation-legal, litigation-legal,
law-student, legal-clinic, and the hub itself (legal-builder-hub). If
the caller names a skill that resolves into any of these, refuse.
Read install-log.yaml. Find the most recent entry for the named skill.
If not found or if the last action is uninstall: say so and stop.
Determine the install path from the log (written at install time).
Enumerate every file and subdirectory. Also identify any config the skill
wrote to the user's ~/.claude/plugins/config/... — surface this to the user
but do not delete it by default (configuration may be worth keeping for a
later re-install).
Display:
Prompt: "Delete these files? (yes / no)". No deletion without explicit yes.
Remove the skill directory.
Append to install-log.yaml:
- skill: <name>
action: uninstall
timestamp: <ISO8601>
path: <deleted path>
Remove the skill's row from the installed starter pack table in the hub's CLAUDE.md.
SKILL.md → SKILL.md.disabledhooks/hooks.json → hooks/hooks.json.disabled (if present)agents/*.md → agents/*.md.disabled) so scheduled
agents stop firing.Show the rename list. Prompt: "Disable this skill? (yes / no)".
Perform the renames.
Append to install-log.yaml with action: disable.
If the user names a skill whose most recent log action is disable, offer
to re-enable: reverse the renames, log action: enable.
yes./plugin for plugin management.~/.claude/plugins/config/claude-for-legal/<plugin>/ are preserved unless
the user asks for them explicitly.…
It only acts on community skills installed through the legal builder hub. The skill must have a most recent install-log.yaml action of install or enable, and its files must be outside built-in plugin directories.
No, not by default. It surfaces related user config directories, but primarily deletes or renames skill files, usually keeping config for future reinstallation.
It uses the installation audit log as the source of truth, only allows eligible community skills, and requires explicit confirmation before deletion. It also logs actions and refuses to touch first-party built-in plugins.
Search watched skill registries, preview matches, and inspect SKILL.md before installing.
Draft DMCA notices, triage incoming claims, and prepare counter-notice drafts.
Standardize new matter intake and generate matter files plus a structured log.
Compare proposed handbook edits and identify cross-reference and state supplement impacts.
Review offer letters and restrictive covenants with jurisdiction-specific hiring checks.
Manage matter workspaces to separate, switch, and archive client contexts.
Safely uninstall hub-installed community skills with confirmation and audit logging.
Temporarily disable or re-enable an installed community skill without deleting files.
Safely review and install community skills with explicit user approval.
Check installed community skills for updates with diffs and explicit approval.
Suggests relevant community skills based on your task and recent plugin activity.
Assess a skill’s trustworthiness, risks, and design quality before installation.