Continuous Agent Loop
affaan-m/ECC
Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.
Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements.
Install Autoresearch
$ npx skills add pedronauck/skills --skill autoresearch -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install pedronauck/skills autoresearch --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/pedronauck/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/curated/autoresearch .claude/skills/autoresearch && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "autoresearch" agent skill from https://github.com/pedronauck/skills/tree/main/skills/curated/autoresearch into .claude/skills/autoresearch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "autoresearch", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/pedronauck/skills/tree/main/skills/curated/autoresearchType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add pedronauck/skills --skill autoresearch -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install pedronauck/skills autoresearch --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pedronauck/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/curated/autoresearch .agents/skills/autoresearch && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "autoresearch" agent skill from https://github.com/pedronauck/skills/tree/main/skills/curated/autoresearch into .agents/skills/autoresearch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "autoresearch", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add pedronauck/skills --skill autoresearch -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install pedronauck/skills autoresearch --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pedronauck/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/curated/autoresearch .cursor/skills/autoresearch && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "autoresearch" agent skill from https://github.com/pedronauck/skills/tree/main/skills/curated/autoresearch into .cursor/skills/autoresearch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "autoresearch", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/pedronauck/skills.git --path skills/curated/autoresearch--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add pedronauck/skills --skill autoresearch -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install pedronauck/skills autoresearch --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pedronauck/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/curated/autoresearch .gemini/skills/autoresearch && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "autoresearch" agent skill from https://github.com/pedronauck/skills/tree/main/skills/curated/autoresearch into .gemini/skills/autoresearch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "autoresearch", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install pedronauck/skills autoresearchInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add pedronauck/skills --skill autoresearch -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/pedronauck/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/curated/autoresearch .github/skills/autoresearch && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "autoresearch" agent skill from https://github.com/pedronauck/skills/tree/main/skills/curated/autoresearch into .github/skills/autoresearch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "autoresearch", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add pedronauck/skills --skill autoresearch -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install pedronauck/skills autoresearch --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pedronauck/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/curated/autoresearch .opencode/skills/autoresearch && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "autoresearch" agent skill from https://github.com/pedronauck/skills/tree/main/skills/curated/autoresearch into .opencode/skills/autoresearch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "autoresearch", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
autoresearch- GitHub stars
- 634
- Token cost
- ~3.7k tokens
- SKILL.md length
- 1,837 words
- Files
- 2
- Skills in repo
- 65
- Repo updated
- First seen
- Licence
- None found
At a glance
Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements.
- Works in 7 steps: read the skill → build the eval suite → generate the live dashboard → …
- : optimize this skill
- SKILL.md covers the core job, before starting: gather context, step 1: read the skill and step 2: build the eval suite, plus 9 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Autoresearch is an agent skill from pedronauck/skills. Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoresearch on, make this skill better, self-improve skill, benchmark skill, eval my skill, run evals on. Outputs: an improved SKILL.md, a results log, and a changelog of every mutation tried.
Its SKILL.md is about 3.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `eval-guide.md`).
It sits in Agent Workflows, covering Autonomous loops and LLM evaluation. The repository describes itself as: My personal favorite skills.
When your agent uses it
- : optimize this skill
- Improve this skill
- Run autoresearch on
- Make this skill better
Example prompts
- “/autoresearch”
Workflow steps
7 steps, taken from the step headings in SKILL.md.
- read the skill
- build the eval suite
- generate the live dashboard
- establish baseline
- run the experiment loop
- write the changelog
- deliver results
What it can do on your machine
Read from SKILL.md and the folder at commit 0422940. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are json and markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Autoresearch loads about 3.7k tokens when it runs. Until then it costs about 116 tokens; SKILL.md has 1,837 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 1,837 words (~3,695 tokens).
“Most skills work about 70% of the time. The other 30% you get garbage. The fix isn't to rewrite the skill from scratch. It's to let an agent run it dozens of times, score every output, and tighten the prompt…”
- name
- autoresearch
Files
SKILL.md and 1 other file in skills/curated/autoresearch of pedronauck/skills.
- SKILL.md
- eval-guide.md
Open the folder on GitHubat commit 0422940
Compare with similar skills
Autoresearch next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Autoresearch this skillpedronauck/skills | 634 | — | ~3.7k | Automated safety check: Pass | None | |
| Continuous Agent Loopaffaan-m/ECC | 276k | 5 repos | ~298 | Automated safety check: Pass | MIT | |
| Loop Architectfabricioctelles/skills | 106 | — | ~2.1k | Automated safety check: Notes | MIT | |
| Autoresearchbyungjunjang/jangpm-meta-skills | 120 | — | ~6k | Automated safety check: Warn | None | |
| Improving MCP ToolsPostHog/posthog | 40k | — | ~1.5k | Automated safety check: Pass | Custom licence | |
| Inngest AgentsAsymmetric-al/core | 381 | — | ~2.6k | Automated safety check: Pass | AGPL-3.0 |
Similar skills
Loop Architect
fabricioctelles/skills
Design well-structured agent loops with best-practice coaching and cross-model review gates before you run them.
Autoresearch
byungjunjang/jangpm-meta-skills
Autonomously optimize a Claude Code skill or agent system by running it repeatedly, scoring outputs against evals, mutating owned artifacts (prompt, references, scripts, agent definitions), and…
- Official
Improving MCP Tools
PostHog/posthog
Run an improve-my-MCP campaign: an autoresearch-style loop that measures the MCP agent experience with the eval harness, picks the highest-impact tool problem from production data, makes one bounded…
Inngest Agents
Asymmetric-al/core
A skill your agent uses when building durable AI agents or agentic workflows with Inngest and AgentKit, including model calls, tool calls, multi-agent networks, human approval, realtime progress…
Author Skill
ericrisco/rsc-harness
A skill your agent uses when authoring a NEW rsc skill or editing an existing one — scoping it to one job, writing the description that decides whether it ever loads, splitting the body into…
More from pedronauck/skills
All 65 skills in this repoDeep Review
pedronauck/skills
Review branch diffs, working trees, or PRs in depth with defect, polish and cross-contract coverage.
Yc Apply
pedronauck/skills
Prepare, review, and package Y Combinator application answers and founder-video notes using the live form and verified founder facts.
Professional Communication
pedronauck/skills
Guide technical communication for software developers. An agent skill from pedronauck/skills.
Tauri V2
pedronauck/skills
Tauri v2+ cross-platform app development with Rust backend. An agent skill from pedronauck/skills.
Hormozi Ad Factory
pedronauck/skills
Generates 150-750+ ad variations using Alex Hormozi's combinatorial Hook x Meat x CTA framework.
Yt Master
pedronauck/skills
Plans and improves YouTube ideas, titles, thumbnail concepts, scripts, retention, channel strategy, and metric-based diagnosis.
Related
Categories
Questions about Autoresearch
What does Autoresearch do?
Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Autoresearch is an agent skill from pedronauck/skills. Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements.
When should I use Autoresearch?
Autoresearch fits situations like: : optimize this skill; improve this skill; run autoresearch on; make this skill better.
How do I install Autoresearch in Claude Code?
Run `npx skills add pedronauck/skills --skill autoresearch -a claude-code`. Or copy the skill folder (skills/curated/autoresearch in pedronauck/skills) into .claude/skills/autoresearch in your project. Claude Code loads it when a task matches its description.
How do I install Autoresearch in Codex?
Run `npx skills add pedronauck/skills --skill autoresearch -a codex`. Or copy the skill folder (skills/curated/autoresearch in pedronauck/skills) into .agents/skills/autoresearch in your project. Codex loads it when a task matches its description.
Can I use Autoresearch in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add pedronauck/skills --skill autoresearch -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/autoresearch, .gemini/skills/autoresearch, .github/skills/autoresearch and .opencode/skills/autoresearch in your project.
What does Autoresearch need to run?
SKILL.md names no scripts, command-line tools or credentials: Autoresearch is instructions for the agent only.
Does Autoresearch access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Autoresearch safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Autoresearch use?
No licence was found for Autoresearch or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Autoresearch use?
About 3.7k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Autoresearch?
Skills that share tags, products or a category with Autoresearch: Continuous Agent Loop (affaan-m/ECC, 276k stars), Loop Architect (fabricioctelles/skills, 106 stars), Autoresearch (byungjunjang/jangpm-meta-skills, 120 stars) and Improving MCP Tools (PostHog/posthog, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Autoresearch?
pedronauck (a GitHub user) maintains it in pedronauck/skills, which has 634 GitHub stars. The repository holds 65 skills in this directory. The repository was last updated on September 14, 2026.
Source: pedronauck/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.