aget-propose-actions

Generate ranked next-best actions with evidence grounding and time-budget constraints.

1|Updated Oct 20, 2025
One-click install
npx skills add https://github.com/aget-framework/template-spec-engineer-aget --skill aget-propose-actions
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: aget-propose-actions
Source: https://github.com/aget-framework/template-spec-engineer-aget/tree/main/.claude/skills/aget-propose-actions
Command: npx skills add https://github.com/aget-framework/template-spec-engineer-aget --skill aget-propose-actions

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The skill prevents inconsistent “next-best actions” planning by turning a fuzzy instruction like step back into a standardized, evidence-grounded, time-bounded batch of ranked actions.

Core Features & Use Cases

  • Standardized NBA parsing and ranking: extracts count, budget, and focus from natural language and produces a ranked set sized to the time window.
  • Mandatory current-state grounding (KB review): checks active PROJECT_PLANs, git status, and session progress so proposals don’t drift or repeat stale work.
  • Structural and cross-session safety pre-flights: enforces guardrails for structural skill routing (D71), HANDOFF deferrals (REQ-PA-012), and audit-after-synthesis pairing (REQ-PA-013), while handling aspirational-flag discipline (REQ-PA-014/015).
  • Execution-ready output with decision authority: returns a batch ready for the Execute-All default, including per-action Principal classification and batch-level /aget-go gating.

Quick Start

Invoke /aget-propose-actions with your desired count, budget, and focus for this session to receive a ranked set of evidence-grounded next-best actions ready for authorization.

Frequently Asked Questions about aget-propose-actions

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I rank next-best actions with time-budget constraints during a session?

Ranking next-best actions with time-budget constraints involves parsing a session mandate for count and focus, then generating an evidence-grounded, ranked batch sized to the specified time window.

What are next-best actions and why do they need evidence grounding?

Next-best actions are ranked execution steps proposed mid-session. Evidence grounding via mandatory KB review ensures proposals align with active project plans and avoid repeating stale work.

How do I standardize fuzzy step back instructions into execution-ready action batches?

Standardize fuzzy step back instructions by applying structural-routing guardrails, HANDOFF deferrals, and audit-after-synthesis pairing to produce an execution-ready action batch with decision authority.

Can I propose next-best actions without reviewing the current project plan and git status?

No. Proposing next-best actions requires mandatory current-state grounding that checks active project plans, git status, and session progress to prevent drifting or repeating stale work.

What limitations exist when generating time-bounded next-best action batches?

Limitations include enforced aspirational-flag authorization-shape requirements and HANDOFF deferrals, meaning batches cannot bypass mandatory audit-after-synthesis pairing or structural-routing pre-flights.