skills.rest
berlinguyinca
berlinguyincaCOMMUNITY
Explore all skills by this author →
GitHub

autospec-refine

Refine feature requests into repo-grounded prompts for /autospec.

3|1|Updated Apr 29, 2026
Search Tags:#specification#acceptance criteria#autonomous coding#prompt refinement#repo grounding#audit artifacts#sizing constraints
One-click install
npx skills add https://github.com/berlinguyinca/autospec --skill autospec-refine
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: autospec-refine
Source: https://github.com/berlinguyinca/autospec/tree/main/skills/autospec-refine
Command: npx skills add https://github.com/berlinguyinca/autospec --skill autospec-refine

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires curl, git, gh, jq, and includes scripts (resource) components.

What problem does it solve?

It prevents under-specified feature requests from turning into slow, error-prone implementation by iteratively upgrading the operator’s prompt using repo-grounded evidence before any coding happens.

Core Features & Use Cases

  • N-round repo-grounded prompt refinement: Applies ordered lenses (repo grounding, acceptance-criteria clarity, sizing constraints, and adversarial QA) over multiple iterations.
  • Structured artifacts for auditability: Writes per-round JSON and markdown refinement records plus a schema-validated output set.
  • Handoff to the main autospec pipeline: After approval, forwards the final refined prompt to /autospec for autonomous implementation, with options for interactive or dry-run behavior.
  • Continuous refinement loops: Supports a bounded refine → handoff → execute → report-harvest → re-refine loop for iterative progress.

Quick Start

Use autospec-refine to refine a new feature request over three rounds, then automatically hand the improved prompt off to /autospec.

Frequently Asked Questions about autospec-refine

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

FAQPage Schema
How do I refine ambiguous feature requests into implementation-ready prompts?▼

Iterative prompt refinement upgrades ambiguous feature requests using repo-grounded evidence and ordered lenses for acceptance criteria, sizing constraints, and adversarial QA. This process prevents under-specified prompts from causing slow, error-prone implementation during autonomous coding.

What is the best way to reduce back-and-forth corrections during autonomous coding?▼

Reducing back-and-forth corrections requires iteratively upgrading the operator prompt with repo-grounded evidence and adversarial QA checks before execution. This structured refinement ensures the prompt is implementation-ready and grounded in actual project constraints.

Do I need git and curl installed to run repo-grounded prompt refinement?▼

Yes, repo-grounded prompt refinement requires curl, git, gh, and jq installed in your environment. These dependencies are necessary to pull project knowledge, validate structured artifacts, and handle the final pipeline handoff.

How does prompt refinement handle handoff to an autonomous coding pipeline?▼

Prompt refinement handles autonomous pipeline handoff by forwarding the approved, schema-validated output set to the execution pipeline. It supports autonomous, interactive, or dry-run modes and can trigger a bounded refine, execute, and report-harvest loop.

Does prompt refinement generate audit artifacts for the specification workflow?▼

Yes, prompt refinement generates audit artifacts by writing per-round JSON and markdown refinement records plus a schema-validated output set. These structured artifacts ensure the specification workflow remains fully auditable across multiple iterations.

Related Skills

Explore More Software Engineering Skills→
danmestasdanmestas
4

gh-project-shared

Centralize GitHub project utilities for gh CLI validation and config management.

Community
Intermediate
n-marusovn-marusov

aif-loop

Executes a multi-iteration Reflex Loop with phases to refine artifacts.

Community
Advanced
igmo71igmo71

speckit-specify

Convert vague feature ideas into structured specifications with acceptance criteria.

Community
Advanced
EONMUNEONMUN
1

spec_driven_development.specify

Convert feature ideas into technology-agnostic specifications with user stories and acceptance criteria.

Official
Advanced