autospec-continue
CommunityTurn /continue into shipped autospec changes.
Software Engineering#workflow orchestration#continue#safety guardrails#autonomous implementation#autospec#prompt extraction#issue-to-pr
Authorberlinguyinca
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Keeps you from copy-pasting “what to do next” when an AI already suggested an actionable continuation, so you can immediately turn that next step into tracked, reviewable software work.
Core Features & Use Cases
- Recommendation extraction: pulls the most actionable “next steps” content from the most recent assistant message using ordered matchers (headings, fenced blocks, imperative lists, and “you should/I suggest” patterns).
- Refine then handoff: pipes the extracted recommendation through /autospec-refine and then hands off to /autospec --autonomous for end-to-end implementation.
- Loop or single pass: runs as a continuous extract→refine→handoff loop with termination conditions, or runs once via --no-loop / --once.
Quick Start
Use autospec-continue to extract the latest assistant “next steps” and implement them autonomously: run /continue in the current conversation where the assistant just suggested what to do next.
Dependency Matrix
Required Modules
curljqgitgh
Components
scripts
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: autospec-continue Download link: https://github.com/berlinguyinca/autospec/archive/main.zip#autospec-continue Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.