AutoResearchClaw: Skill for Claude Code

.claude/skills/a-evolve/SKILL.md

a-evolve is a skill for Claude Code from aiming-lab/AutoResearchClaw. It costs 100 tokens per session (1,697 once invoked), scanned A, original, MIT.

A method for improving an AI agent across repeated runs by examining failures, diagnosing their causes, updating prompts or skills, and checking whether the changes help.

In plain words
What is it for?
It is for analyzing agent failures, creating targeted skills or prompt changes, storing lessons learned, and evaluating improved behavior.
Why use it?
It turns error logs and evaluation results into concrete improvements that can persist for future tasks.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is aiming-lab/AutoResearchClaw's own configuration. It tells Claude Code how to work on AutoResearchClaw itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything AutoResearchClaw configures →

About the project

AutoResearchClaw is a system that turns a research idea into a scientific paper through autonomous and collaborative AI research workflows. It is for researchers who want agents to investigate questions, run experiments, and produce papers, with optional human guidance. Catalogue skills and agents provide parts of its research workflow.

aiming-lab/AutoResearchClaw · 14,344 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to aiming-lab/AutoResearchClaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/aiming-lab/AutoResearchClaw/main/.claude/skills/a-evolve/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/aiming-lab/AutoResearchClaw

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for a-evolve

README.md
[![agentmods](https://agentmods.dev/badge/skills/aiming-lab/autoresearchclaw/a-evolve.svg)](https://agentmods.dev/skills/aiming-lab/autoresearchclaw/a-evolve)
Your own site
<a href="https://agentmods.dev/skills/aiming-lab/autoresearchclaw/a-evolve"><img src="https://agentmods.dev/badge/skills/aiming-lab/autoresearchclaw/a-evolve.svg" alt="Measured on agentmods" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,697 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00100 $0.01697
Opus 5 $0.00050 $0.00848
Sonnet 5 $0.00020 $0.00339
Haiku 4.5 $0.00010 $0.00170

Measured 7d ago against content hash 7b8144bdd37d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

a-evolve scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/a-evolve/SKILL.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

A-Evolve: Agentic Evolution Skill

Apply the Solve → Observe → Evolve → Gate → Reload methodology from A-Evolve to iteratively improve agent performance. This skill is prompt-based — no external dependencies, no harness changes. You analyze failures, propose workspace mutations, and generate durable artifacts (skills, prompt patches, knowledge entries) that the agent can load in future runs.

Core Loop

When asked to evolve or improve agent performance, follow this 5-step loop:

1. Solve (Collect Evidence)

Gather the agent's execution artifacts. Ask the user for or locate:

  • Run logs, error traces, or experiment outputs
  • Pass/fail results per task
  • Metric values (accuracy, reward, success rate)
  • Any existing session files from previous runs

If inside AutoResearchClaw, look at:

  • artifacts/rc-*/ — experiment outputs, charts, reviews
  • evolve.log or stage-specific logs
  • reviews.md — peer review feedback
  • Sentinel watchdog reports

2. Observe (Diagnose)

Analyze the collected evidence to produce structured observations:

For each failed or underperforming task, identify:

  • Error category: code bug, timeout, wrong approach, missing knowledge, API misuse, hallucinated reference, prompt ambiguity, etc.
  • Root cause: What specifically went wrong and why
  • Frequency: Is this a one-off or a recurring pattern across tasks?
  • Severity: blocking (pipeline crash) / degrading (wrong result) / cosmetic (formatting issue)

Write observations as a structured list:

## Observations (Batch N)

### OBS-1: [Category] Short description
- Tasks affected: task_001, task_005, task_012
- Root cause: ...
- Frequency: 3/50 tasks (6%)
- Severity: degrading

### OBS-2: ...

3. Evolve (Propose Mutations)

Based on observations, propose one or more of these mutation types:

A. Generate a Skill (for recurring patterns, frequency ≥ 3)

Write a new SKILL.md file that teaches the agent how to handle this pattern. A good evolved skill:

  • Targets a specific failure category, not generic advice
  • Contains concrete steps the agent should follow
  • Includes a "when to apply" trigger condition
  • Is short (under 100 lines) and self-contained

Read the full file on GitHub · 204 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 204 lines · 100 tokens per session scan A 7b8144bdd37d

Subscribe to this mod's changes

a-evolve is a skill published in the GitHub repository aiming-lab/AutoResearchClaw (14,344 stars, last pushed 18d ago), licensed MIT. It adds 100 tokens to every session and 1,697 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.