Darwin Skill Optimizer
alchaincyf/darwin-skill
Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.
Unattended-run kernel for Grok Bot non-git work. An agent skill from aigorahub/elves.
Install Elves Grok Bot
$ npx skills add aigorahub/elves --skill elves-grok-bot -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install aigorahub/elves elves-grok-bot --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/aigorahub/elves.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/elves-grok-bot .claude/skills/elves-grok-bot && 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 "elves-grok-bot" agent skill from https://github.com/aigorahub/elves/tree/main/skills/elves-grok-bot into .claude/skills/elves-grok-bot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "elves-grok-bot", 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/aigorahub/elves/tree/main/skills/elves-grok-botType 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 aigorahub/elves --skill elves-grok-bot -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install aigorahub/elves elves-grok-bot --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aigorahub/elves.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/elves-grok-bot .agents/skills/elves-grok-bot && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "elves-grok-bot" agent skill from https://github.com/aigorahub/elves/tree/main/skills/elves-grok-bot into .agents/skills/elves-grok-bot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "elves-grok-bot", 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 aigorahub/elves --skill elves-grok-bot -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install aigorahub/elves elves-grok-bot --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aigorahub/elves.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/elves-grok-bot .cursor/skills/elves-grok-bot && 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 "elves-grok-bot" agent skill from https://github.com/aigorahub/elves/tree/main/skills/elves-grok-bot into .cursor/skills/elves-grok-bot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "elves-grok-bot", 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/aigorahub/elves.git --path skills/elves-grok-bot--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 aigorahub/elves --skill elves-grok-bot -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install aigorahub/elves elves-grok-bot --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aigorahub/elves.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/elves-grok-bot .gemini/skills/elves-grok-bot && 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 "elves-grok-bot" agent skill from https://github.com/aigorahub/elves/tree/main/skills/elves-grok-bot into .gemini/skills/elves-grok-bot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "elves-grok-bot", 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 aigorahub/elves elves-grok-botInstalls 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 aigorahub/elves --skill elves-grok-bot -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/aigorahub/elves.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/elves-grok-bot .github/skills/elves-grok-bot && 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 "elves-grok-bot" agent skill from https://github.com/aigorahub/elves/tree/main/skills/elves-grok-bot into .github/skills/elves-grok-bot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "elves-grok-bot", 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 aigorahub/elves --skill elves-grok-bot -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install aigorahub/elves elves-grok-bot --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aigorahub/elves.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/elves-grok-bot .opencode/skills/elves-grok-bot && 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 "elves-grok-bot" agent skill from https://github.com/aigorahub/elves/tree/main/skills/elves-grok-bot into .opencode/skills/elves-grok-bot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "elves-grok-bot", 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
elves-grok-bot- GitHub stars
- 221
- Token cost
- ~914 tokens
- SKILL.md length
- 541 words
- Files
- 1
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- MIT
At a glance
Unattended-run kernel for Grok Bot non-git work. An agent skill from aigorahub/elves.
- The user says use elves for a long unattended job with no PR/merge model
- SKILL.md covers Stage, Stop gate, Watchdog and Each wake
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Elves Grok Bot is an agent skill from aigorahub/elves. Unattended-run kernel for Grok Bot non-git work. Use when the user says "use elves" for a long unattended job with no PR/merge model.
Its SKILL.md is about 910 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Grok Bot, Grok-assistant agents. Not for coding runs — use root SKILL.md for those.
It sits in Agent Workflows. It works with Git. The repository describes itself as: Autonomous multi-batch development skill for Claude Code and Codex. They work while you sleep. The licence is MIT.
When your agent uses it
- The user says use elves for a long unattended job with no PR/merge model
Example prompts
- “use elves”
- “/elves-grok-bot”
Requirements
- Compatibility (from SKILL.md): Grok Bot, Grok-assistant agents. Not for coding runs — use root SKILL.md for those.
What it can do on your machine
Read from SKILL.md and the folder at commit 0f1e493. 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.
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.
Compatibility
Grok Bot, Grok-assistant agents. Not for coding runs — use root SKILL.md for those.
From compatibility in the SKILL.md frontmatter.
Context cost
Elves Grok Bot loads about 914 tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 541 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
The full file from aigorahub/elves at commit 0f1e493, republished under its MIT licence (© aigorahub). 541 words, ~914 tokens.
Download SKILL.mdSave it as
.claude/skills/elves-grok-bot/SKILL.md (or your agent's skills folder).- name
- elves-grok-bot
- description
- Unattended-run kernel for Grok Bot non-git work. Use when the user says "use elves" for a long unattended job with no PR/merge model.
- compatibility
- Grok Bot, Grok-assistant agents. Not for coding runs — use root SKILL.md for those.
- license
- MIT
- metadata.author
- John Ennis
- metadata.version
- 1.0.0
- metadata.argument-hint
- Natural language "use elves"
Elves (Grok Bot)
Files are memory. Chat is not. The user owns done. You own the middle.
Do not use /goal — that string is reserved for a possible future feature.
This is not Grok Build and not a coding host. No git, PR, or merge.
Stage
Create one run. Give it a unique run id. Write four files under one folder named for that id. Put the folder path, run id, and reminder id in SURVIVAL and session.json. Every wake uses that exact path. Do not invent a second folder.
- PLAN.md — mission, scope, batches, M-A# acceptance, non-negotiables
- SURVIVAL.md — start with "READ THIS FIRST." Stop gate, next action, file paths
- session.json —
status(running|stopped|blocked|complete),stop_allowed: falseuntil every M-A# has proof,run_id,reminder_id,active_fire - LEDGER.md — last item, last outcome, last record id, next action
Proof is a count, file, or record id. "The important ones are done" is not proof.
Stop gate
Stay closed until acceptance is proven, unless status is already terminal.
Not a stop: a recap, the first slice, silence, "this is a lot," a natural pause, a quiet inbox.
Hard stop only: user said stop, auth is dead, or the next write would break a rule. On a hard stop, set status to stopped or blocked before you return, then delete that exact reminder. Every later fire that sees a terminal status exits without work.
Mid-run ping: answer in a few sentences and continue.
Watchdog
One reminder only, every minute, around the clock (cron: * * * * *). Overnight unattended work is the point — the user may go to bed after kickoff. Persist the reminder id. Each fire: confirm run id and reminder id, then read survival → session → plan → ledger. If status is terminal, delete this reminder if it still exists and exit. If the gate is closed, do the next batch. Do not recap instead of working. When all M-A# are proven, set status: complete, recap once, and delete that exact reminder.
An interrupted fire (status error "Interrupted before it finished") is NOT a stop. Next fire continues from SURVIVAL/LEDGER after reconciling any in-flight item.
Show full SKILL.md (195 more words)Show less
One fire at a time. If session.json active_fire is younger than two minutes, skip this fire. Otherwise set active_fire now, do one batch, then clear it. If LEDGER says a batch is in progress, continue that batch from the last proven record id. Do not start a parallel copy.
Before each send, CRM write, or post: write the item intent and a stable operation key to the ledger. After it lands, write the record id (Gmail message id, CRM id, file) before the next item. After an interrupt, look up that key remotely. Retry only when the remote side has no record. If the outcome is unknown, block and report; do not send again.
When a real batch or person lands, send a short progress note. Do not vanish into tool calls after announcing a step.
Each wake
Read survival. If status is terminal, stop. Count remaining from files. Ship the next batch. Update ledger and session. If work remains, keep going.
Preflight logins before you walk away. Retry a failed worker; do not relaunch into an unchanged workspace. If the session died, report it — do not redo side effects.
No git/PR/merge. Grok Bot skill.
© aigorahub, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/elves-grok-bot of aigorahub/elves.
Open the folder on GitHubat commit 0f1e493
Compare with similar skills
Elves Grok Bot 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 |
|---|---|---|---|---|---|---|
| Elves Grok Bot this skillaigorahub/elves | 221 | — | ~914 | Automated safety check: Pass | MIT | |
| Darwin Skill Optimizeralchaincyf/darwin-skill | 6.2k | 1 repos | ~4.7k | Automated safety check: Pass | MIT | |
| CodeGraph Agent Evalcolbymchenry/codegraph | 74k | — | ~950 | Automated safety check: Pass | MIT | |
| Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills | 21k | — | ~1.9k | Automated safety check: Pass | MIT | |
| O2 Review Loopopenobserve/openobserve | 22k | — | ~3.7k | Automated safety check: Pass | AGPL-3.0 | |
| Beads Task Memorygastownhall/beads | 28k | — | ~1.2k | Automated safety check: Pass | MIT |
Similar skills
CodeGraph Agent Eval
colbymchenry/codegraph
Benchmarks how much CodeGraph helps a coding agent on a real repository, comparing runs with and without it for a chosen local or published version.
Neat-Freak Knowledge Closeout
KKKKhazix/khazix-skills
Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.
O2 Review Loop
openobserve/openobserve
Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.
Beads Task Memory
gastownhall/beads
Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction.
Session History Search
slopus/happy
Searches past Claude Code, Codex and Cursor sessions and summarizes what was worked on, tried or decided, using extraction scripts instead of reading raw logs.
More from aigorahub/elves
All 14 skills in this repoElves
aigorahub/elves
Autonomous multi-batch development agent for long unattended runs, reviewed-PR landing, Cobbler-first orchestration, and optional Fugu, Manus, Grok, Devin, or Oh My Pi (omp) provider shortcuts.
Omp
aigorahub/elves
Bounded Oh My Pi (omp) provider shortcut via Elves. An agent skill from aigorahub/elves.
Setup Cobbler
aigorahub/elves
Configure Cobbler model routes and external-agent preferences for this checkout.
Cobbler Mode
aigorahub/elves
Turn on Elves Cobbler Mode for the current Claude Code thread.
Fugu
aigorahub/elves
Run a bounded Sakana Fugu repository task or explicit review through codex-fugu.
Grok
aigorahub/elves
Run a bounded-permission headless Grok Build task. An agent skill from aigorahub/elves.
Related
Works with
Categories
Questions about Elves Grok Bot
What does Elves Grok Bot do?
Unattended-run kernel for Grok Bot non-git work. An agent skill from aigorahub/elves. Elves Grok Bot is an agent skill from aigorahub/elves. Unattended-run kernel for Grok Bot non-git work.
When should I use Elves Grok Bot?
Elves Grok Bot fits situations like: the user says use elves for a long unattended job with no PR/merge model.
How do I install Elves Grok Bot in Claude Code?
Run `npx skills add aigorahub/elves --skill elves-grok-bot -a claude-code`. Or copy the skill folder (skills/elves-grok-bot in aigorahub/elves) into .claude/skills/elves-grok-bot in your project. Claude Code loads it when a task matches its description.
How do I install Elves Grok Bot in Codex?
Run `npx skills add aigorahub/elves --skill elves-grok-bot -a codex`. Or copy the skill folder (skills/elves-grok-bot in aigorahub/elves) into .agents/skills/elves-grok-bot in your project. Codex loads it when a task matches its description.
Can I use Elves Grok Bot 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 aigorahub/elves --skill elves-grok-bot -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/elves-grok-bot, .gemini/skills/elves-grok-bot, .github/skills/elves-grok-bot and .opencode/skills/elves-grok-bot in your project.
What does Elves Grok Bot need to run?
SKILL.md names no scripts, command-line tools or credentials: Elves Grok Bot is instructions for the agent only. Compatibility (from SKILL.md): Grok Bot, Grok-assistant agents. Not for coding runs — use root SKILL.md for those..
Does Elves Grok Bot 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 Elves Grok Bot 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 Elves Grok Bot use?
Elves Grok Bot is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Elves Grok Bot use?
About 914 tokens (SKILL.md is roughly 3.7k 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 Elves Grok Bot?
Skills that share tags, products or a category with Elves Grok Bot: Darwin Skill Optimizer (alchaincyf/darwin-skill, 6.2k stars), CodeGraph Agent Eval (colbymchenry/codegraph, 74k stars), Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars) and O2 Review Loop (openobserve/openobserve, 22k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Elves Grok Bot?
aigorahub (a GitHub organization) maintains it in aigorahub/elves, which has 221 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 11, 2026.
Source: aigorahub/elves on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.