Docs Seeker
einverne/dotfiles
Searching internet for technical documentation using llms.txt standard, GitHub repositories via Repomix, and parallel exploration.
Introspect, explain, and improve Ralph Orchestrator using its published llms.txt doc map.
Install Ralph Docs
$ npx skills add mikeyobrien/ralph-orchestrator --skill ralph-docs -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mikeyobrien/ralph-orchestrator ralph-docs --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/mikeyobrien/ralph-orchestrator.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ralph-docs .claude/skills/ralph-docs && 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 "ralph-docs" agent skill from https://github.com/mikeyobrien/ralph-orchestrator/tree/main/skills/ralph-docs into .claude/skills/ralph-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ralph-docs", 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/mikeyobrien/ralph-orchestrator/tree/main/skills/ralph-docsType 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 mikeyobrien/ralph-orchestrator --skill ralph-docs -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mikeyobrien/ralph-orchestrator ralph-docs --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mikeyobrien/ralph-orchestrator.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/ralph-docs .agents/skills/ralph-docs && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ralph-docs" agent skill from https://github.com/mikeyobrien/ralph-orchestrator/tree/main/skills/ralph-docs into .agents/skills/ralph-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ralph-docs", 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 mikeyobrien/ralph-orchestrator --skill ralph-docs -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mikeyobrien/ralph-orchestrator ralph-docs --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mikeyobrien/ralph-orchestrator.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/ralph-docs .cursor/skills/ralph-docs && 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 "ralph-docs" agent skill from https://github.com/mikeyobrien/ralph-orchestrator/tree/main/skills/ralph-docs into .cursor/skills/ralph-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ralph-docs", 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/mikeyobrien/ralph-orchestrator.git --path skills/ralph-docs--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 mikeyobrien/ralph-orchestrator --skill ralph-docs -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mikeyobrien/ralph-orchestrator ralph-docs --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mikeyobrien/ralph-orchestrator.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/ralph-docs .gemini/skills/ralph-docs && 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 "ralph-docs" agent skill from https://github.com/mikeyobrien/ralph-orchestrator/tree/main/skills/ralph-docs into .gemini/skills/ralph-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ralph-docs", 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 mikeyobrien/ralph-orchestrator ralph-docsInstalls 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 mikeyobrien/ralph-orchestrator --skill ralph-docs -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mikeyobrien/ralph-orchestrator.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/ralph-docs .github/skills/ralph-docs && 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 "ralph-docs" agent skill from https://github.com/mikeyobrien/ralph-orchestrator/tree/main/skills/ralph-docs into .github/skills/ralph-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ralph-docs", 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 mikeyobrien/ralph-orchestrator --skill ralph-docs -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mikeyobrien/ralph-orchestrator ralph-docs --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mikeyobrien/ralph-orchestrator.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/ralph-docs .opencode/skills/ralph-docs && 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 "ralph-docs" agent skill from https://github.com/mikeyobrien/ralph-orchestrator/tree/main/skills/ralph-docs into .opencode/skills/ralph-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ralph-docs", 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
ralph-docs- GitHub stars
- 3.2k
- Token cost
- ~1.5k tokens
- SKILL.md length
- 702 words
- Files
- 5 (incl. references)
- Skills in repo
- 16
- Repo updated
- First seen
- Licence
- MIT
At a glance
Introspect, explain, and improve Ralph Orchestrator using its published llms.txt doc map.
- Works in 5 steps: Discover — fetch llms.txt to see the… → Narrow — pick the 1–3 pages that… → Fetch — pull only those pages. Do not… → …
- The user asks questions about Ralphs behavior
- SKILL.md covers Use This Skill For, Core Principle: llms.txt Is…, Workflow and Scope Boundaries, plus 3 more sections
- Calls curl; reaches mikeyobrien.github.io
What it does
Ralph Docs is an agent skill from mikeyobrien/ralph-orchestrator. Introspect, explain, and improve Ralph Orchestrator using its published llms.txt doc map. Use this skill whenever the user asks questions about Ralph's behavior, wants to understand how a Ralph internal works (event loop, hats, memories, tasks, backends, presets), debug an unfamiliar failure mode, or propose a code change to the ralph-orchestrator repo. The skill teaches the agent to discover authoritative answers from the live docs via llms.txt before guessing, and to scope improvements through the published…
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `agents/openai.yaml`, `references/common-questions.md` and `references/contributing.md`).
It sits in Marketing & SEO, covering AI search optimization and Async programming. The repository describes itself as: An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration. The licence is MIT.
When your agent uses it
- The user asks questions about Ralphs behavior
- Wants to understand how a Ralph internal works (event loop
- Debug an unfamiliar failure mode
- Propose a code change to the ralph-orchestrator repo
Example prompts
- “/ralph-docs”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Discover — fetch llms.txt to see the top-level sections
- Narrow — pick the 1–3 pages that actually answer the question. The map
- Fetch — pull only those pages. Do not fetch more than three pages
- Cross-check — for code-level claims, confirm against the repo (crate
- Answer — cite the page you relied on. Include the URL so the user can
What it can do on your machine
Read from SKILL.md and the folder at commit edc2b32. 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
Shell commands in SKILL.md call:
curl
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
mikeyobrien.github.io
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
Ralph Docs loads about 1.5k tokens when it runs, and up to ~4.9k if it reads all its reference files. Until then it costs about 144 tokens; SKILL.md has 702 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 mikeyobrien/ralph-orchestrator at commit edc2b32, republished under its MIT licence (© mikeyobrien). 702 words, ~1,471 tokens.
Download SKILL.mdSave it as
.claude/skills/ralph-docs/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- ralph-docs
- description
- Introspect, explain, and improve Ralph Orchestrator using its published llms.txt doc map. Use this skill whenever the user asks questions about Ralph's behavior, wants to understand how a Ralph internal works (event loop, hats, memories, tasks, backends, presets), debug an unfamiliar failure mode, or propose a code change to the ralph-orchestrator repo. The skill teaches the agent to discover authoritative answers from the live docs via llms.txt before guessing, and to scope improvements through the published architecture rather than the local checkout alone.
Ralph Docs
Introspect Ralph Orchestrator the same way the framework expects a smart agent to — consult the published documentation map at https://mikeyobrien.github.io/ralph-orchestrator/llms.txt, fetch only the sections relevant to the question, and answer from authoritative sources.
Use this skill to behave like an internal Ralph contributor rather than a guess-first assistant.
Use This Skill For
- Answering "how does Ralph do X?" questions about the event loop, hats, memories, tasks, presets, backends, CLI, TUI, diagnostics, waves, or API.
- Explaining an observed behavior ("why did my loop terminate with max_iterations?", "why didn't my hat fire?") from first principles in the docs, not pattern-matching.
- Proposing and scoping an improvement to the
ralph-orchestratorcodebase — locating the right crate, the relevant concept doc, and the existing test surface before writing code. - Triaging a ralph bug report: map symptoms to likely subsystem, pull in the concept + reference docs for that subsystem, identify the probable file path in the repo.
- Onboarding: answer a new user's setup/quick-start questions from the official Getting Started pages instead of the agent's stale training data.
Core Principle: llms.txt Is The Router
Ralph's llms.txt is a curated map, not a full-text dump. The workflow is:
- Discover — fetch
llms.txtto see the top-level sections (Getting Started / Concepts / User Guide / Advanced / API / Examples / Contributing / Reference). - Narrow — pick the 1–3 pages that actually answer the question. The map
links directly to
.mdversions — those are agent-optimized and should be preferred over scraping HTML. - Fetch — pull only those pages. Do not fetch more than three pages speculatively; the budget should be spent on answering, not browsing.
- Cross-check — for code-level claims, confirm against the repo (crate paths are listed in AGENTS.md / CLAUDE.md inside the ralph-orchestrator checkout).
- Answer — cite the page you relied on. Include the URL so the user can verify.
Workflow
Identify the question's subsystem using the taxonomy in
references/llms-txt-map.md(hats, event loop, memories, tasks, backends, presets, CLI, TUI, diagnostics, waves, API).If
~/.cache/ralph-docs/llms.txtexists and is <7 days old, use it. Else refetch it:bash mkdir -p ~/.cache/ralph-docs curl -sSfL https://mikeyobrien.github.io/ralph-orchestrator/llms.txt \ -o ~/.cache/ralph-docs/llms.txtPick the 1–3 linked
.mdpages most relevant to the subsystem. The map entries are documented inreferences/llms-txt-map.md; use it to shortcut the grep.Fetch just those pages via
curl -sSfL <url> -o ~/.cache/ralph-docs/<stem>.mdand read them. Agents withweb_fetchor an equivalent tool should use that instead.Answer the user's question grounded in what you just read. Quote the relevant sentence when the user asks "does Ralph do X?" so they can audit.
If the answer requires a code change, switch to the ralph-orchestrator checkout and follow
references/contributing.mdfor the propose-a-change workflow.
Show full SKILL.md (271 more words)Show less
Scope Boundaries
- This skill answers and explains. For creating/modifying user hats, defer to ralph-hats. For operating a live loop (running, resuming, merging, debugging), defer to ralph-loop. For code changes to ralph-orchestrator itself, this skill scopes the change; the actual editing uses the agent's native code-editing tools.
- Do not invent features not present in the published docs. If llms.txt does not surface an answer, say so and suggest checking the source tree at https://github.com/mikeyobrien/ralph-orchestrator.
- Do not rely on the agent's pretraining for version-sensitive claims (e.g.
CLI flags, preset names). Ralph's CLI evolves; always verify against
guide/cli-reference.mdorreference/changelog.md.
Guardrails
- Prefer
.mdURLs from llms.txt over scraping the rendered HTML. - Cache fetched pages under
~/.cache/ralph-docs/with a 7-day staleness threshold. Refetch llms.txt before any other doc to detect renames/moves. - When cited docs contradict the local checkout (docs newer than the user's
installed ralph version), note the mismatch and suggest
ralph --versionso the user can decide which to trust. - For "how to improve Ralph" requests, always read
concepts/tenets/index.mdfirst. Ralph's six tenets are load-bearing; changes that fight them usually belong somewhere else.
Output Expectations
- Answer first, then link. Don't make the user wait for a verbose tour.
- Include at least one source URL for non-trivial claims.
- When proposing a code change, name the crate + file (see
references/contributing.mdfor the crate map), the concept doc that justifies the change, and the test file that should cover it.
Read These References When Needed
- For the llms.txt section map + which pages answer which question:
references/llms-txt-map.md - For FAQ recipes (common introspection patterns):
references/common-questions.md - For how to propose a code change, including crate layout and PR conventions:
references/contributing.md
© mikeyobrien, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 4 other files (references) in skills/ralph-docs of mikeyobrien/ralph-orchestrator.
- SKILL.md
- agents/openai.yaml
- references/common-questions.md
- references/contributing.md
- references/llms-txt-map.md
Open the folder on GitHubat commit edc2b32
Compare with similar skills
Ralph Docs 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 |
|---|---|---|---|---|---|---|
| Ralph Docs this skillmikeyobrien/ralph-orchestrator | 3.2k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Docs Seekereinverne/dotfiles | 121 | 1 repos | ~1.4k | Automated safety check: Pass | GPL-3.0 | |
| Document Microfeedmicrofeed/microfeed | 4.1k | — | ~1.5k | Automated safety check: Pass | AGPL-3.0 | |
| LLM Docs OptimizerSidiora-Labs/centra-llm-agents | 115 | — | ~5.4k | Automated safety check: Pass | Custom licence | |
| Geo PipelineViryaZheng/recomby-geo | 460 | — | ~1.1k | Automated safety check: Pass | MIT | |
| GitHubkostja94/marketing-skills | 1k | — | ~4.5k | Automated safety check: Pass | MIT |
Similar skills
Document Microfeed
microfeed/microfeed
Create, revise, organize, validate, and publish microfeed documentation.
LLM Docs Optimizer
Sidiora-Labs/centra-llm-agents
Optimize documentation for AI coding assistants and LLMs. An agent skill from Sidiora-Labs/centra-llm-agents.
Geo Pipeline
ViryaZheng/recomby-geo
Entry point + orchestrator for the recomby-geo GEO (Generative Engine Optimization) workflow on OpenAI Codex CLI.
GitHub
kostja94/marketing-skills
When the user wants to use GitHub for SEO, parasite SEO, GEO, open source marketing, README optimization, or curated Awesome lists.
Lognorm
sickn33/agentic-awesome-skills
Work a site's SEO and AI-visibility (GEO) backlog through the hosted LogNorm MCP server: audits, fixes, content, AI-answer tracking.
More from mikeyobrien/ralph-orchestrator
All 16 skills in this repoEvaluate Presets
mikeyobrien/ralph-orchestrator
A skill your agent uses when testing Ralph's hat collection presets, validating preset configurations, or auditing the preset library for bugs and UX issues.
PR Demo
mikeyobrien/ralph-orchestrator
A skill your agent uses when creating animated demos (GIFs) for pull requests or documentation.
Release Bump
mikeyobrien/ralph-orchestrator
A skill your agent uses when bumping ralph-orchestrator version for a new release, after fixes are committed and ready to publish
Review PR
mikeyobrien/ralph-orchestrator
A skill your agent uses when asked to review a PR, run a code review loop, or invoke the ralph reviewer against a pull request number or GitHub URL
Tui Debug In Pane
mikeyobrien/ralph-orchestrator
A skill your agent uses when you need to reproduce or debug TUI rendering issues (garbled output, broken streaming, layout corruption) by running ralph in a tmux split pane and capturing live output.
Ralph Hats
mikeyobrien/ralph-orchestrator
Create, inspect, validate, explain, and improve Ralph hat collections.
Related
Questions about Ralph Docs
What does Ralph Docs do?
Introspect, explain, and improve Ralph Orchestrator using its published llms.txt doc map. Ralph Docs is an agent skill from mikeyobrien/ralph-orchestrator.txt doc map.
When should I use Ralph Docs?
Ralph Docs fits situations like: the user asks questions about Ralphs behavior; wants to understand how a Ralph internal works (event loop; debug an unfamiliar failure mode; propose a code change to the ralph-orchestrator repo.
How do I install Ralph Docs in Claude Code?
Run `npx skills add mikeyobrien/ralph-orchestrator --skill ralph-docs -a claude-code`. Or copy the skill folder (skills/ralph-docs in mikeyobrien/ralph-orchestrator) into .claude/skills/ralph-docs in your project. Claude Code loads it when a task matches its description.
How do I install Ralph Docs in Codex?
Run `npx skills add mikeyobrien/ralph-orchestrator --skill ralph-docs -a codex`. Or copy the skill folder (skills/ralph-docs in mikeyobrien/ralph-orchestrator) into .agents/skills/ralph-docs in your project. Codex loads it when a task matches its description.
Can I use Ralph Docs 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 mikeyobrien/ralph-orchestrator --skill ralph-docs -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ralph-docs, .gemini/skills/ralph-docs, .github/skills/ralph-docs and .opencode/skills/ralph-docs in your project.
What does Ralph Docs need to run?
Going by SKILL.md and its folder, Ralph Docs needs the command-line tools its instructions call (curl).
Does Ralph Docs access the network?
SKILL.md names 1 domain. In commands or code: mikeyobrien.github.io; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Ralph Docs 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 Ralph Docs use?
Ralph Docs is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Ralph Docs use?
About 1.5k tokens (SKILL.md is roughly 5.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.5k tokens, read only when the agent opens those files.
What are the alternatives to Ralph Docs?
Skills that share tags, products or a category with Ralph Docs: Docs Seeker (einverne/dotfiles, 121 stars), Document Microfeed (microfeed/microfeed, 4.1k stars), LLM Docs Optimizer (Sidiora-Labs/centra-llm-agents, 115 stars) and Geo Pipeline (ViryaZheng/recomby-geo, 460 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Ralph Docs?
mikeyobrien (a GitHub user) maintains it in mikeyobrien/ralph-orchestrator, which has 3,167 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 5, 2026.
Source: mikeyobrien/ralph-orchestrator on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.