From ac-tools
Imports/exports reusable assets (skills, templates, agents) between projects and v0.2 Claude Code plugin repositories, with sanitization for secrets/paths and safety checks.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ac-tools:agentic-shareThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Core logic for moving reusable assets between projects and this repository.
Core logic for moving reusable assets between projects and this repository.
import | exportskill | template | agent--plugin, --force, --dry-run)Parsed from: $ARGUMENTS
| Type | Project Source | Repository Target |
|---|---|---|
| skill | .claude/skills/<name>/ or explicit skill dir | plugins/<plugin>/skills/<name>/ |
| template | templates/<name>/ | templates/<name>/ |
| agent | explicit agent markdown path | plugins/ac-workflow/agents/<name>.md |
Notes:
--plugin is required unless destination can be inferred.import or export).skill, template, agent)..claude-plugin/marketplace.jsonplugins//Users/..., /home/...) -> {USER_HOME}api_key, token, secret, bearer values) -> {REDACTED}--dry-run).--force or explicit confirmation.After successful import/export, offer a commit for only touched asset paths.
Conventional message pattern:
feat(assets): import <asset_type> '<asset_name>'
(or export accordingly)
| Error | Action |
|---|---|
| Invalid mode/type | Abort with valid choices |
| Repository root not detected | Abort and request running from repo root |
| Source missing | Abort and print source path |
| Sanitization blockers remain | Abort and print blocker lines |
| Target exists without force | Ask for overwrite confirmation |
npx claudepluginhub waterplanai/agentic-config --plugin ac-toolsExports skills, templates, or agents from a project to a repository's v0.2 plugin architecture via /agentic-export. Supports dry-run, plugin targeting, and pre-flight checks.
Shares Claude Code resources (memories, skills, hooks, scripts, commands) between projects via a centralized claude-settings repo. Copies .claude/* files and publishes them, with private info scanning and optional auto mode.
Analyzes, standardizes, validates, and syncs locally maintained skills into agent skill directories (Claude, Cursor, CodeBuddy, Codex).