
from agentops416
Graph-based backlog triage using bv/br: rank priorities, find bottlenecks, and produce machine-readable recommendations for agents (robot mode).
Beads BV provides graph-aware triage for software backlogs. Using metrics like PageRank, betweenness, k-core and articulation points, it identifies priority work, bottlenecks, and parallel execution tracks, then emits JSON-safe recommendations for automated agents. The skill maps backlog items as a directed graph and exposes robot-mode commands that return machine-readable recommendations, single-item picks, parallel plans, and deep analytics.
Use this skill when an agent needs to decide what to work on next across repositories or teams, detect blocking labels or cycles, generate a claim-and-claim workflow, or schedule concurrent workstreams. It is intended for automated (robot) contexts — do not run the interactive TUI in agent flows.
Designed to work with code/automation agents that can invoke CLI tools and parse JSON: Claude Code, Cursor, Codex/Codegen-based agents, and other automation runtimes that support shell command execution.
Skill has null SKILL.md body and no scripts. The GitHub source repo (boshu2/agentops) returns 404 — the repo has been deleted or made private. With no actual content to evaluate, the skill is effectively an empty shell with only metadata (name, description, tags) remaining in the database. Cannot assess functionality.
Source repo boshu2/agentops no longer accessible. Skill body is null in DB. This is likely a dead/orphaned skill entry. Consider pruning from directory if source remains unavailable.
Evolve — Goal-Driven Improvement Loop
Autonomous improvement loop that selects high-value work, runs a full research-plan-implement (/rpi) cycle, validates changes, and repeats to compound repo impr
RPI — Full Lifecycle Orchestrator
Orchestrates a three-phase RPI lifecycle (discovery → implementation → validation) for autonomous agent workflows, including complexity classification, routing,
cass Session Search
Mine past agent sessions for working prompts, decisions, rituals and recovery patterns (operational tooling).
PR Preparation & Validation
Systematically prepares pull requests by validating tests, analyzing commit patterns, and generating high-quality, structured PR bodies.
Operationalize
Distill research and learnings into durable automation rules.
Handoff: Durable Session Continuation
Writes compact session handoffs to ensure seamless continuation across agents or context resets.
Meta Skill Search Engine
A powerful search and load engine for AgentSkills across multiple corpora, enabling agents to discover and implement the right skill for a task.
AgentOps Learning & Verdict Analysis
Analyze durable verdict collections to summarize recurring evidence and propose new deterministic checks for agents.