# Vc Autoresearch

Loop: find gaps → fix → repeat until agents find no gaps or a metric goal is hit.

- Repository: https://github.com/withkynam/vibecode-pro-max-kit (1164 stars)
- Category: AI and agents
- License: MIT
- Last updated: 2026-06-21
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add withkynam/vibecode-pro-max-kit --skill vc-autoresearch -g -a claude-code -y`
Codex: `npx skills add withkynam/vibecode-pro-max-kit --skill vc-autoresearch -g -a codex -y`
Cursor: `npx skills add withkynam/vibecode-pro-max-kit --skill vc-autoresearch -g -a cursor -y`
Gemini CLI: `npx skills add withkynam/vibecode-pro-max-kit --skill vc-autoresearch -g -a gemini-cli -y`

## Description

Loop: find gaps → fix → repeat until agents find no gaps or a metric goal is hit. Shared loop primitive for PVL, EVL, and standalone quality runs.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# vc-autoresearch

> **Output style:** Follow `process/development-protocols/communication-standards.md`, answer-first, plain language, no unexplained jargon, TL;DR on long responses.

Reusable loop primitive. Runs: find gaps → write report → fix → check → repeat.

Used directly for spec/doc/UX hardening. Wired into PVL (plan-validate-fix loop, the fix cycle between writing a plan and approving EXECUTE) and EVL (execute-validate-fix loop, the confirmation run after EXECUTE) as the shared bookkeeping layer.

---

## When To Invoke

- **Standalone:** user says "harden this spec", "fix all lint errors", "improve test coverage"
- **PVL:** the ORCHESTRATOR invokes it when vc-validate-agent returns a first-pass CONDITIONAL/BLOCKED verdict (validate-fix loops are needed)
- **EVL:** the ORCHESTRATOR invokes it at the EVL confirmation run, unconditionally after every EXECUTE DONE, before UPDATE PROCESS

Do NOT invoke during RESEARCH or INNOVATE phases.

## Who Runs This (Loop Driver)

The **ORCHESTRATOR is the loop driver**. It executes every bookkeeping step itself:

- **Step 0 setup**, creates the task folder and the `results.tsv` tracking file.
- **Cycle counter + per-cycle iteration report**, writes one report file per loop iteration.
- **TSV row**, appends a row to `results.tsv` after each cycle.
- **Plateau/cap/regression checks**, stops the loop when no progress is made for 3 cycles (HALT_PLATEAU, no improvement after 3 tries), when the hard 10-cycle limit is hit (HALT_CAP), or when a test that was passing now fails (HALT_REGRESSION).

Subagents (vc-validate-agent, vc-tester, vc-plan-agent, vc-execute-agent) are fire-and-forget: they emit a verdict and terminate. They cannot invoke this skill on the orchestrator's behalf, cannot loop themselves, and cannot spawn each other.

If no one runs Step 0, the loop never exists and verdicts silently become "proceed", that failure mode is exactly what this section forbids.

The rest: https://github.com/withkynam/vibecode-pro-max-kit/blob/HEAD/.claude/skills/vc-autoresearch/SKILL.md