Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From agent-flow
Fetches open issues from an issue tracker via MCP, enriches with historical metrics, and runs an AI priority engine to suggest fix order.
npx claudepluginhub asysta-act/agent-flow --plugin agent-flowHow this skill is triggered — by the user, by Claude, or both
Slash command
/agent-flow:prioritize [--limit <N>] [--output <path>][--limit <N>] [--output <path>]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Input: `$ARGUMENTS` = optional `--limit <N>` (default: 20), `--output <path>` (default: stdout)
Categorizes backlog issues from Linear/GitHub or manual lists into Leverage/Neutral/Overhead, analyzes time allocation, and suggests optimizations or labels.
Browses Arness-labeled issues from GitHub, Jira, or local feature backlog, selects unblocked one via dependency resolution, and routes to implementation pipeline.
Triages project issues through a state machine with category and state roles. Use when creating issues, reviewing bugs/feature requests, preparing issues for AFK agents, or managing issue workflow.
Share bugs, ideas, or general feedback.
Input: $ARGUMENTS = optional --limit <N> (default: 20), --output <path> (default: stdout)
Read Automation Config from CLAUDE.md section ## Automation Config:
Before any pipeline operation, verify MCP tool availability:
mcp__* tool matching the tracker type is accessible/agent-flow:check-setup for diagnostics."Via MCP server (per Issue Tracker → Type), fetch open issues (Bug query + Feature query). Limit = --limit flag.
If a metrics report exists (./reports/metrics.md or Metrics → Output from config), read per-area failure patterns and success rates.
You MUST invoke Task(subagent_type='agent-flow:priority-engine', model='opus'). DO NOT inline-execute.
Context: list of issues + historical data (if available).
If priority-engine fails or returns an error, display: "Prioritization failed: {reason}" and stop.
Display the agent's result. If --output is specified → write to file.