Orchestra-Research/AI-Research-SKILLs / 0-autoresearch-skill
autoresearch
VerifiedOrchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 24.4 KB |
| references/agent-continuity.md | markdown | 4.6 KB |
| references/progress-reporting.md | markdown | 6.3 KB |
| references/skill-routing.md | markdown | 8.3 KB |
| templates/findings.md | markdown | 1.5 KB |
| templates/progress-presentation.html | other | 8.5 KB |
| templates/research-log.md | markdown | 4.9 KB |
| templates/research-state.yaml | config | 2.1 KB |
templates/progress-presentation.html
View on GitHub<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Research Progress</title>
<style>
* { margin: 0; padding: 0; box-sizing: border-box; }
body {
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', system-ui, sans-serif;
background: #0d1117;
color: #e6edf3;
line-height: 1.6;
padding: 2rem;
max-width: 1100px;
margin: 0 auto;
}
header {
text-align: center;
padding: 3rem 0 2rem;
border-bottom: 1px solid #21262d;
margin-bottom: 2.5rem;
}
header h1 {
font-size: 2.2rem;
font-weight: 700;
color: #f0f6fc;
margin-bottom: 0.5rem;
}
.subtitle {
font-size: 1.15rem;
color: #8b949e;
font-style: italic;
max-width: 700px;
margin: 0 auto 1rem;
}
.meta {
font-size: 0.85rem;
color: #484f58;
}
.meta span {
display: inline-block;
margin: 0 0.5rem;
padding: 0.15rem 0.6rem;
background: #161b22;
border: 1px solid #21262d;
border-radius: 12px;
}
section {
margin-bottom: 3rem;
}
section h2 {
font-size: 1.4rem;
font-weight: 600;
color: #f0f6fc;
margin-bottom: 1rem;
padding-bottom: 0.5rem;
border-bottom: 1px solid #21262d;
}
p, li { color: #c9d1d9; }
.card {
background: #161b22;
border: 1px solid #21262d;
border-radius: 8px;
padding: 1.5rem;
margin-bottom: 1rem;
}
.card h3 {
font-size: 1.05rem;
color: #58a6ff;
margin-bottom: 0.5rem;
}
.result-grid {
display: grid;
grid-template-columns: repeat(auto-fit, minmax(220px, 1fr));
gap: 1rem;
margin-bottom: 1.5rem;
}
.stat-card {
background: #161b22;
border: 1px solid #21262d;
border-radius: 8px;
padding: 1.2rem;
text-align: center;
}
.stat-card .value {
font-size: 2rem;
font-weight: 700;
color: #58a6ff;
}
.stat-card .label {
font-size: 0.8rem;
color: #8b949e;
text-transform: uppercase;
letter-spacing: 0.05em;
}
.stat-card.positive .value { color: #3fb950; }
.stat-card.negative .value { color: #f85149; }
table {
width: 100%;
border-collapse: collapse;
margin: 1rem 0;
}
th {
text-align: left;
padding: 0.6rem 1rem;
background: #161b22;
color: #8b949e;
font-size: 0.8rem;
text-transform: uppercase;
letter-spacing: 0.05em;
border-bottom: 1px solid #21262d;
}
td {
padding: 0.6rem 1rem;
border-bottom: 1px solid #21262d;
font-size: 0.95rem;
}
.badge {
display: inline-block;
padding: 0.15rem 0.5rem;
border-radius: 10px;
font-size: 0.75rem;
font-weight: 600;
}
.badge-supported { background: #0d2818; color: #3fb950; border: 1px solid #1b4332; }
.badge-refuted { background: #2d1215; color: #f85149; border: 1px solid #4a1c20; }
.badge-active { background: #0c2d6b; color: #58a6ff; border: 1px solid #1158c7; }
.badge-pending { background: #1c1c1c; color: #8b949e; border: 1px solid #333; }
.chart-container {
background: #161b22;
border: 1px solid #21262d;
border-radius: 8px;
padding: 1.5rem;
text-align: center;
margin: 1rem 0;
}
.next-steps {
background: #0c2d6b22;
border: 1px solid #1158c744;
border-radius: 8px;
padding: 1.5rem;
}
.next-steps h3 { color: #58a6ff; margin-bottom: 0.5rem; }
.next-steps ul { padding-left: 1.5rem; }
.next-steps li { margin-bottom: 0.3rem; }
footer {
text-align: center;
padding: 2rem 0;
color: #484f58;
font-size: 0.8rem;
border-top: 1px solid #21262d;
}
</style>
</head>
<body>
<!--
AGENT INSTRUCTIONS:
This is a starting point. Fill in, rearrange, add, or remove sections
based on what's compelling from your current research. The goal is a
research story, not a status dashboard.
Replace {{PLACEHOLDERS}} with actual content.
Embed SVG charts inline (see progress-reporting.md for the trajectory plot function).
Add additional sections as needed.
-->
<header>
<h1>{{PROJECT_TITLE}}</h1>
<p class="subtitle">{{RESEARCH_QUESTION}}</p>
<p class="meta">
<span>{{DATE}}</span>
<span>{{N_EXPERIMENTS}} experiments</span>
<span>Status: {{STATUS}}</span>
</p>
</header>
<!-- Summary stats -->
<section>
<div class="result-grid">
<div class="stat-card positive">
<div class="value">{{BEST_METRIC}}</div>
<div class="label">Best Metric</div>
</div>
<div class="stat-card">
<div class="value">{{BASELINE_METRIC}}</div>
<div class="label">Baseline</div>
</div>
<div class="stat-card positive">
<div class="value">{{IMPROVEMENT}}</div>
<div class="label">Improvement</div>
</div>
<div class="stat-card">
<div class="value">{{N_HYPOTHESES}}</div>
<div class="label">Hypotheses Tested</div>
</div>
</div>
</section>
<!-- Background and motivation -->
<section id="background">
<h2>Background & Motivation</h2>
<div class="card">
<!-- Why does this research matter? What gap are we addressing? -->
<p>{{BACKGROUND_TEXT}}</p>
</div>
</section>
<!-- Optimization trajectory - THE key visual -->
<section id="trajectory">
<h2>Optimization Trajectory</h2>
<div class="chart-container">
<!-- Embed SVG chart here. See references/progress-reporting.md
for the generate_trajectory_svg() function. -->
{{TRAJECTORY_SVG}}
</div>
</section>
<!-- Key findings -->
<section id="findings">
<h2>Key Findings</h2>
<!-- Add cards for each significant finding -->
<div class="card">
<h3>{{FINDING_1_TITLE}}</h3>
<p>{{FINDING_1_DESCRIPTION}}</p>
<!-- Include inline plots, tables, or metrics as needed -->
</div>
</section>
<!-- What was tried -->
<section id="experiments">
<h2>What We Tried</h2>
<table>
<thead>
<tr>
<th>Hypothesis</th>
<th>Change</th>
<th>Result</th>
<th>Status</th>
</tr>
</thead>
<tbody>
<!-- Add rows for notable experiments -->
<tr>
<td>{{H_ID}}</td>
<td>{{CHANGE_SUMMARY}}</td>
<td>{{METRIC_DELTA}}</td>
<td><span class="badge badge-supported">{{STATUS}}</span></td>
</tr>
</tbody>
</table>
</section>
<!-- Current understanding -->
<section id="understanding">
<h2>Current Understanding</h2>
<div class="card">
<!-- The narrative from findings.md, but presented compellingly -->
<p>{{CURRENT_UNDERSTANDING}}</p>
</div>
</section>
<!-- Next steps -->
<section id="next">
<h2>Next Steps</h2>
<div class="next-steps">
<ul>
<li>{{NEXT_STEP_1}}</li>
<li>{{NEXT_STEP_2}}</li>
<li>{{NEXT_STEP_3}}</li>
</ul>
</div>
</section>
<footer>
Generated by Autoresearch | {{DATE}}
</footer>
</body>
</html>
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |