npx claudepluginhub askscio/glean-plugins-internal --plugin gleanThis skill is limited to using the following tools:
Discover and use Glean skills to help with enterprise app tasks (Jira, Slack,
Creates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.
Executes implementation plans in current session by dispatching fresh subagents per independent task, with two-stage reviews: spec compliance then code quality.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
Discover and use Glean skills to help with enterprise app tasks (Jira, Slack, Google Workspace, Salesforce, etc.) or actions you don't already have a tool for. Where possible, aim to complete the user's request end-to-end rather than just listing available skills.
Your current session ID is: ${CLAUDE_SESSION_ID}
When discover_skills or run_tool returns a response containing
[AUTHENTICATION_REQUIRED], the user needs to complete sign-in in their browser.
A browser window will open automatically and the response includes a sign-in URL.
When this happens:
Do not treat this as an error or attempt to work around it.
If no arguments were provided and the task can't be inferred from conversation context, ask the user what they'd like to do before proceeding.
Call discover_skills with the task description. Always include session_id.
discover_skills({
query: "<task description>",
session_id: "${CLAUDE_SESSION_ID}"
})
The response is an XML index of discovered skills with file paths.
You can call discover_skills multiple times — e.g. to discover skills for
individual sub-tasks as you work through a broad request.
Browse the returned skills and select the one most relevant to the user's
request. Read its SKILL.md file for detailed instructions. Skills typically
contain guidance on how to use their tools, but the tools can also be called
as independent units.
Read each tool's JSON file (e.g. tools/TOOL_NAME.json) to get the exact
server_id, name, and inputSchema with parameter names and types.
Never guess parameter names - always read the tool JSON file first.
Call run_tool with the server_id, tool_name (from the name field in the
JSON), and arguments matching the inputSchema exactly.
run_tool({
server_id: "composio/jira-pack",
tool_name: "jirasearch",
arguments: { query: "project = PROJ AND status = Open" }
})
session_id: "${CLAUDE_SESSION_ID}" when calling discover_skillsrun_tool - never guess parameters