autoresearch-with-docs

Run iterative corpus-guided experiments and log results to results.tsv.

Updated Aug 27, 2026

Search Tags:#automation #benchmarking #experimentation #guardrails #local-docs #autoresearch #documentation-corpus

Ready to run

npx skills add https://github.com/Elijah-J/InfoScraper --skill autoresearch-with-docs

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: autoresearch-with-docs
Source: https://github.com/Elijah-J/InfoScraper/tree/main/.agents/skills/autoresearch-with-docs
Command: npx skills add https://github.com/Elijah-J/InfoScraper --skill autoresearch-with-docs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill runs a perf-only AutoResearch loop grounded in local documentation, enabling automated, iterative benchmarking and decision-making against a corpus before each experiment.

Core Features & Use Cases

Local-documents driven corpus for experiments, ensuring reproducible baselines.
Iterative design: dispatches focused changes, evaluates impact, and keeps or reverts changes based on results.
Branch-scoped workflow: creates autoresearch/$ARGUMENTS branches, reads configuration, and logs outcomes for auditability.

Quick Start

Initiate autoresearch by supplying a target argument and allowing the workflow to prepare state, switch to the autoresearch/$ARGUMENTS branch, and run the iterative evaluation loop.

Frequently Asked Questions about autoresearch-with-docs

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

FAQPage Schema

How do I automate iterative benchmarking against a local documentation corpus?▼

Automated iterative benchmarking against a local documentation corpus is achieved by running corpus-guided experiments that evaluate performance impact and log outcomes for continuous improvement. The workflow reads configuration files, dispatches focused changes, and keeps or reverts them based on results.

What is a perf-driven AutoResearch loop and how does it work with local docs?▼

A perf-driven AutoResearch loop is an automated workflow that runs iterative experiments grounded in a local documentation corpus. It dispatches focused changes, evaluates their performance impact, and keeps or reverts modifications based on standardized results logged for auditability.

How do I start an automated experimentation workflow with configurable experiment limits?▼

To start automated experimentation, supply a target argument to initiate the workflow, which prepares state, switches to a dedicated autoresearch branch, and runs the iterative evaluation loop. The workflow enforces contracts by reading configuration files like autoresearch.toml.

Does automated AutoResearch require specific configuration files to enforce experiment contracts?▼

Yes, automated AutoResearch requires specific configuration files to enforce contracts, reading program.md, autoresearch.toml, and related state files. These files define experiment limits, guardrails, and state rescue parameters to ensure reproducible baselines and standardized result logging.

How are benchmarking results logged for auditability during iterative experimentation?▼

Benchmarking results are logged for auditability by emitting standardized outputs to a results.tsv file within a branch-scoped workflow. The automated loop creates dedicated autoresearch branches, evaluates performance impact, and records outcomes to track whether changes are kept or reverted.

Can I rescue experiment state if an automated benchmarking workflow is interrupted?▼

Yes, you can rescue experiment state if an automated benchmarking workflow is interrupted because the loop reads related state files and enforces configurable experiment limits. This state rescue capability ensures continuous improvement workflows can recover and resume without losing prior progress.