ask-suggest-priority-batching
Streamlines wkappbot suggest backlog triaging by batching GPT ranking and automating merge workflows.
Install
mkdir -p .claude/skills/ask-suggest-priority-batching && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18706" && unzip -o skill.zip -d .claude/skills/ask-suggest-priority-batching && rm skill.zipInstalls to .claude/skills/ask-suggest-priority-batching
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Reduce ask-gpt calls when triaging wkappbot suggest backlogs. Use when you have a page of suggestions and want one GPT ranking pass, then one ask per suggestion in priority order.Key capabilities
- →Reduce `ask-gpt` calls for suggestion triage
- →Batch rank suggestions by impact, risk, urgency, effort
- →Merge duplicate suggestions
- →Perform codebase analysis in parallel with GPT ranking
- →Delegate fixes to Opus agents
- →Verify fixes and close suggestions
How it works
The skill pulls one page of suggestions, merges duplicates, and fires a batch GPT ranking. It then performs per-item `ask-gpt` calls for ambiguous items and delegates fixes to Opus agents, verifying and closing suggestions.
Inputs & outputs
When to use ask-suggest-priority-batching
- →Batch ranking suggestions by impact
- →Merging duplicate backlog items
- →Triaging large suggest backlogs
- →Streamlining project maintenance
About ask-suggest-priority-batching
Reduces GPT call volume by batch-ranking page-level suggestions. Automates duplicate merging and keeps triaging bounded to manageable pages.
Reduce ask-gpt calls when triaging wkappbot suggest backlogs. Use when you have a page of suggestions and want one GPT ranking pass, then one ask per suggestion in priority order.
When not to use it
- →When triaging a full backlog at once
- →When blocking on GPT response is acceptable
- →When not using `wkappbot` suggestions
Limitations
- →Requires `wkappbot` tools to be functional
- →Merging duplicates requires specific flags (`--root-cause`, `--work`, `--components`, `--affected-cmds`)
- →Sonnet orchestrates, Opus executes; Sonnet never writes code inline
How it compares
This skill optimizes the suggestion triage process by batching GPT ranking and merging duplicates, significantly reducing `ask-gpt` calls and simplify the workflow compared to individual processing of each suggestion.
Compared to similar skills
ask-suggest-priority-batching side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| ask-suggest-priority-batching (this skill) | 0 | 4mo | No flags | Intermediate |
| your-sub-agent-name | 1 | 1y | Review | Intermediate |
| ava | 0 | 6mo | No flags | Advanced |
| workflow-router | 1 | 9mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by kiexpert
View all by kiexpert →You might also like
your-sub-agent-name
CaptainCrouton89
Create and manage specialized Claude Code subagents for task-specific workflows. Use when delegating work to specialized agents, configuring agent permissions, or understanding subagent architecture and best practices.
ava
protoLabsAI
Codex-native operational orchestration for protoLabs Studio. Use when the user wants autonomous triage, backlog supervision, board operations, agent coordination, or multi-step operational decision-making across the portfolio.
workflow-router
parcadei
Goal-based workflow orchestration - routes tasks to specialist agents based on user goals
loki-mode
davila7
Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.
wg
graphwork
Use this skill for task coordination with WG. Triggers include "wg", task graphs, multi-step projects, tracking dependencies, coordinating agents, or when you see a .wg directory.
run-tasks
JeremyKalmus
Orchestrate task execution via beads and sub-agents. Gets ready work from beads, spawns appropriate agents based on labels, monitors completion, and updates status. Use after /approve-spec has created tasks.