Is the Agent Research Aggregator skill free?

Yes. The skill itself is free from Ar9av/PaperOrchestra. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Agent Research Aggregator SkillProof Score?

8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 4/5.

How do I install Agent Research Aggregator?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Agent Research Aggregator with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Agent Research Aggregator

Scans AI agent cache logs and formats them into PaperOrchestra idea.md + experimental_log.md

by Ar9av · Ar9av/PaperOrchestra

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.0/10
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 06c510e

Cloned the repo and ran the pipeline in a temp HOME against a fabricated RL-experiment project (.claude/memory + results_doorkey.json + NOTES.md). discover_logs.py exited 2 with no --project and 0 after --project (matching SKILL.md); the general-file scan has no ** recursion, so I had to point --search-roots directly at the project dir before it found the 3 files. I authored synthesis.json to the documented Phase-3 schema and format_po_inputs.py deterministically produced idea.md (Sparse schema), experimental_log.md (numbered sections + aligned GFM results table + iteration history), and aggregation_report.md with data-quality warnings and a missing-inputs checklist. Compared against an ad-hoc baseline idea/log I wrote from the same logs: the skill output is schema-conformant and downstream-consumable where the baseline is loose prose with results as bullets. grep across all three scripts found no network/exec/base64/exfil patterns; scripts are read-only on cache dirs and skip .env/credentials/keys. The arXiv id 2604.05018 cited throughout is unverifiable.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 6/10
Docs & honesty 4/5

What Agent Research Aggregator does

A pre-processing skill that discovers experimentation logs in AI coding-agent cache directories (.claude, .cursor, .antigravity, .openclaw) or any given folder, then extracts and synthesizes them into the structured idea.md and experimental_log.md input pair the PaperOrchestra paper-writing pipeline expects. Triggers when the user asks to aggregate agent logs for paper writing, prepare PaperOrchestra inputs from a cache, or turn scattered experiment histories into a paper draft. Runs as a cheap pre-pass before the paper-orchestra skill.

How to install Agent Research Aggregator

git clone --depth 1 https://github.com/Ar9av/PaperOrchestra.git /tmp/agent-research-aggregator-src
mkdir -p ~/.claude/skills
cp -R /tmp/agent-research-aggregator-src/skills/agent-research-aggregator ~/.claude/skills/agent-research-aggregator
# Deps: python3 only (stdlib argparse/json/pathlib — no pip install needed for the deterministic scripts).
# Phases 2 & 3 (extraction + synthesis) are LLM calls the host agent performs; no API key wired into the scripts.
# The skill's scripts reference paths as skills/agent-research-aggregator/scripts/*.py — run them from a repo checkout
#   or adjust to ~/.claude/skills/agent-research-aggregator/scripts/*.py
# Downstream paper-orchestra also needs user-supplied template.tex + conference_guidelines.md.

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Agent Research Aggregator

/agent-research-aggregator Scans AI agent cache logs and formats them into PaperOrchestra idea.md + experimental_log.md

It also activates on plain-language prompts like these:

Aggregate my Claude agent logs for paper writing
Extract experiments from my coding agent history
Prepare PaperOrchestra inputs from my .cursor cache

Frequently asked questions

Is the Agent Research Aggregator skill free?: Yes. The skill itself is free from Ar9av/PaperOrchestra. SkillProof publishes the install command and an independent test verdict at no cost.
Does Agent Research Aggregator work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Cloned the repo and ran the pipeline in a temp HOME against a fabricated RL-experiment project (.claude/memory + results_doorkey.json + NOTES.md). discover_logs.py exited 2 with no --project and 0 after --project (matching SKILL.md); the general-file scan has no ** recursion, so I had to point --search-roots directly at the project dir before it found the 3 files. I authored synthesis.json to the documented Phase-3 schema and format_po_inputs.py deterministically produced idea.md (Sparse schema), experimental_log.md (numbered sections + aligned GFM results table + iteration history), and aggregation_report.md with data-quality warnings and a missing-inputs checklist. Compared against an ad-hoc baseline idea/log I wrote from the same logs: the skill output is schema-conformant and downstream-consumable where the baseline is loose prose with results as bullets. grep across all three scripts found no network/exec/base64/exfil patterns; scripts are read-only on cache dirs and skip .env/credentials/keys. The arXiv id 2604.05018 cited throughout is unverifiable.
What is the Agent Research Aggregator SkillProof Score?: 8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 4/5.
How do I install Agent Research Aggregator?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Agent Research Aggregator with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.