nsf-thrust-refiner

Refine NSF-style proposal thrusts with local literature grounding and evaluation hooks.

13|1|Updated Mar 21, 2026
One-click install
npx skills add https://github.com/yzhao062/agent-config --skill nsf-thrust-refiner
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nsf-thrust-refiner
Source: https://github.com/yzhao062/agent-config/tree/main/reference-skills/nsf-thrust-refiner
Command: npx skills add https://github.com/yzhao062/agent-config --skill nsf-thrust-refiner

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Refine one NSF-style thrust or aim after the initial scaffold exists. Use when Codex needs to deepen a core proposal unit with sharper gaps, local literature grounding, concrete technical measures, evaluation hooks, reviewer-facing running examples or artifact sketches, figure ideas, or visible TODO placeholders while preserving alignment with the current intro, summary, and evaluation plan.

Core Features & Use Cases

  • refine 1-2 concrete thrusts or aims at a time
  • deepen local literature grounding with targeted citations
  • add local evaluation hooks and figure planning while preserving structure
  • leave visible TODOs for unresolved citations or collaborator facts

Quick Start

Patch the target unit to tighten 1-2 thrusts with local grounding, add concrete evaluation hooks, and mark unresolved items with visible TODOs.

Frequently Asked Questions about nsf-thrust-refiner

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

FAQPage Schema
How do I refine an NSF proposal thrust with local literature grounding?▼

You refine an NSF proposal thrust by patching 1-2 concrete aims at a time, injecting targeted local citations, adding local evaluation hooks, and marking unresolved facts with visible TODOs while preserving existing structure.

Can I add evaluation hooks and figure ideas to an NSF aim without breaking the summary?▼

Yes, you can add local evaluation hooks and figure planning while preserving alignment with the current intro, summary, and evaluation plan by applying patch-local edits to the target unit.

What is NSF thrust refinement and when do I need it?▼

NSF thrust refinement is the process of deepening a core proposal unit with sharper gaps, local literature grounding, and concrete technical measures after an initial scaffold exists and requires deepening.

How do I mark unresolved citations in an NSF proposal draft?▼

You mark unresolved citations in an NSF proposal draft by leaving visible TODO placeholders within the thrust unit, ensuring patch-local edits track unresolved collaborator facts and missing references for later completion.

Does NSF thrust refinement work on close variants of NSF-style proposals?▼

Yes, NSF thrust refinement applies to NSF-style proposals and close variants, focusing on sharpening 1-2 concrete thrusts with local grounding, evaluation hooks, figure ideas, and visible TODOs within the unit.

What are the limitations of refining NSF thrusts incrementally?▼

A key limitation is that this refinement requires an initial scaffold to already exist, focusing strictly on patch-local edits to 1-2 thrusts at a time rather than generating the full proposal structure from scratch.