Agent skill

Autoresearch

by Apocrathia in Apocrathia/home-assistant-config

Optional, operator-gated metric experiments under .scratch/ for Home Assistant Homelab.

No licenceAuto-check passedAgent Workflows

Install Autoresearch

skills CLI
$ npx skills add Apocrathia/home-assistant-config --skill autoresearch -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Apocrathia/home-assistant-config autoresearch --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Apocrathia/home-assistant-config.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/autoresearch .claude/skills/autoresearch && rm -rf skills-src

Use ~/.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/

Facts

Skill name
autoresearch
GitHub stars
179
Token cost
~1.2k tokens
SKILL.md length
305 words
Files
1
Skills in repo
22
Repo updated
First seen
Licence
None found

At a glance

Optional, operator-gated metric experiments under .scratch/ for Home Assistant Homelab.

  • Works in 3 steps: Operator explicitly wants metric-driven… → There is a real eval command that… → Experiments stay under .scratch/ — never
  • Tasks that involve Autonomous loops
  • SKILL.md covers When NOT to use this skill, When it is appropriate (rare), Slim workflow and Hand off, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Autoresearch is an agent skill from Apocrathia/home-assistant-config. Optional, operator-gated metric experiments under .scratch/ for Home Assistant Homelab. Prefer prototype for design questions. Use only when a measurable eval exists and the operator wants a short experiment log — not a swarm research loop or docs/research PR.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Autonomous loops. It works with Home Assistant and Git. The repository describes itself as: Apocrathia's Home Assistant Configuration Files.

When your agent uses it

  • Tasks that involve Autonomous loops

Example prompts

  • “/autoresearch”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Operator explicitly wants metric-driven experiments (or find-work surfaces
  2. There is a real eval command that produces a numeric metric (script
  3. Experiments stay under .scratch/ — never

What it can do on your machine

Read from SKILL.md and the folder at commit e28308a. 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 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 1.2k tokens when it runs. Until then it costs about 68 tokens; SKILL.md has 305 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~68
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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 305 words (~1,187 tokens).

“Honest fit check first: this is a Home Assistant config repo, not a benchmark-heavy code swarm. Most questions here are better answered by prototype, live HA traces, or architecture-review.”

— opening of SKILL.md by Apocrathia
name
autoresearch
disable-model-invocation
true

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .agents/skills/autoresearch of Apocrathia/home-assistant-config.

Open the folder on GitHubat commit e28308a

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.

Autoresearch compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Autoresearch this skillApocrathia/home-assistant-config179—~1.2kAutomated safety check: PassNone
Darwin SkillHHU3637kr/skills1451 repos~2.2kAutomated safety check: PassNone
Self-Improvement Tournament Loopzereight/gitlab-mcp2k1 repos~1.8kAutomated safety check: WarnMIT
Effective Harnessesliangdabiao/exa-research-mcp-skill110—~1.5kAutomated safety check: PassNone
AutoResearch LoopLearnPrompt/andrej-karpathy-skills110—~1.4kAutomated safety check: PassMIT
Autoresearch Agentalirezarezvani/claude-skills28k1 repos~3kAutomated safety check: PassMIT

Similar skills

  • Darwin Skill

    HHU3637kr/skills

    Darwin Skill (达尔文.skill): autonomous skill optimizer inspired by Karpathy's autoresearch.

    145 GitHub starsUsed in 1 repo~2.2k tokens
    Agent WorkflowsAuto-check passed
  • Runs an autonomous evolutionary loop that improves a codebase against a measurable benchmark, using agent roles, tournament selection and recorded history until a stop condition.

    2k GitHub starsUsed in 1 repo~1.8k tokens
    DevelopmentAuto-check: warnings
  • Effective Harnesses

    liangdabiao/exa-research-mcp-skill

    Long-running agent project harness for Codex, OpenClaw, Claude Code, and other coding agents.

    110 GitHub stars~1.5k tokensUpdated 2 mo ago
    DevelopmentAuto-check passed
  • AutoResearch Loop

    LearnPrompt/andrej-karpathy-skills

    Sets up an autonomous research loop where an agent runs experiments on git branches, logs results and proposes the next iteration while you approve each hypothesis change.

    110 GitHub stars~1.4k tokensUpdated 3 mo ago
    Agent WorkflowsAuto-check passed
  • Autoresearch Agent

    alirezarezvani/claude-skills

    Autonomous experiment loop that optimizes any file by a measurable metric.

    28k GitHub starsUsed in 1 repo~3k tokens
    Agent WorkflowsAuto-check passed
  • PR Body

    andrew-blake/melcloudhome

    A skill your agent uses when composing or revising a pull request description in this repo, including PRs that sit in a stack.

    142 GitHub stars~4.5k tokensUpdated today
    DevelopmentAuto-check passed

More from Apocrathia/home-assistant-config

All 22 skills in this repo
  • Reconcile Context

    Apocrathia/home-assistant-config

    Fix drift in Home Assistant Homelab agent context (AGENTS.md, CLAUDE.md, .agents/context/, rules, skills, agents) against the repo.

    179 GitHub stars~931 tokensUpdated 18 days ago
    Auto-check passed
  • Alignment

    Apocrathia/home-assistant-config

    Interview the operator about a topic until shared understanding, walking each branch of the decision tree one at a time.

    179 GitHub stars~1.4k tokensUpdated 18 days ago
    Auto-check passed
  • Architecture Review

    Apocrathia/home-assistant-config

    Explore packages/, layout, and .agents/ for architectural friction (coupling, shallow packages, missing boundaries) and file or recommend agent issues under docs/issues/.

    179 GitHub stars~764 tokensUpdated 18 days ago
    Auto-check passed
  • Automation Debug

    Apocrathia/home-assistant-config

    Systematically diagnose and fix broken Home Assistant automations with a structured reproduce → triggers → conditions → actions workflow.

    179 GitHub stars~1.2k tokensUpdated 18 days ago
    Auto-check passed
  • Config Validate

    Apocrathia/home-assistant-config

    Validate Home Assistant YAML configuration for syntax, structure, entity references, duplicates, and secrets usage before applying changes.

    179 GitHub stars~932 tokensUpdated 18 days ago
    Auto-check passed
  • Create Agent

    Apocrathia/home-assistant-config

    Create a new agent persona under .agents/agents/. An agent skill from Apocrathia/home-assistant-config.

    179 GitHub stars~1.1k tokensUpdated 18 days ago
    Auto-check passed

Questions about Autoresearch

What does Autoresearch do?

Optional, operator-gated metric experiments under .scratch/ for Home Assistant Homelab. Autoresearch is an agent skill from Apocrathia/home-assistant-config.scratch/ for Home Assistant Homelab.

When should I use Autoresearch?

Autoresearch fits situations like: tasks that involve Autonomous loops.

How do I install Autoresearch in Claude Code?

Run `npx skills add Apocrathia/home-assistant-config --skill autoresearch -a claude-code`. Or copy the skill folder (.agents/skills/autoresearch in Apocrathia/home-assistant-config) 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 Apocrathia/home-assistant-config --skill autoresearch -a codex`. Or copy the skill folder (.agents/skills/autoresearch in Apocrathia/home-assistant-config) 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 Apocrathia/home-assistant-config --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 1.2k tokens (SKILL.md is roughly 4.7k 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: Darwin Skill (HHU3637kr/skills, 145 stars), Self-Improvement Tournament Loop (zereight/gitlab-mcp, 2k stars), Effective Harnesses (liangdabiao/exa-research-mcp-skill, 110 stars) and AutoResearch Loop (LearnPrompt/andrej-karpathy-skills, 110 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Autoresearch?

Apocrathia (a GitHub user) maintains it in Apocrathia/home-assistant-config, which has 179 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on September 21, 2026.

Source: Apocrathia/home-assistant-config on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.