Writing Docs
nukeop/nuclear
A skill your agent uses when writing or editing documentation in packages/docs.
Answer questions about how to use octo, or diagnose something that isn't working, by reading the product documentation.
Install Product Help
$ npx skills add open-octo/octo-agent --skill product-help -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install open-octo/octo-agent product-help --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/open-octo/octo-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/internal/skills/defaults/product-help .claude/skills/product-help && 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 "product-help" agent skill from https://github.com/open-octo/octo-agent/tree/main/internal/skills/defaults/product-help into .claude/skills/product-help/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "product-help", 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/open-octo/octo-agent/tree/main/internal/skills/defaults/product-helpType 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 open-octo/octo-agent --skill product-help -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install open-octo/octo-agent product-help --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/open-octo/octo-agent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/internal/skills/defaults/product-help .agents/skills/product-help && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "product-help" agent skill from https://github.com/open-octo/octo-agent/tree/main/internal/skills/defaults/product-help into .agents/skills/product-help/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "product-help", 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 open-octo/octo-agent --skill product-help -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install open-octo/octo-agent product-help --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/open-octo/octo-agent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/internal/skills/defaults/product-help .cursor/skills/product-help && 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 "product-help" agent skill from https://github.com/open-octo/octo-agent/tree/main/internal/skills/defaults/product-help into .cursor/skills/product-help/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "product-help", 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/open-octo/octo-agent.git --path internal/skills/defaults/product-help--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 open-octo/octo-agent --skill product-help -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install open-octo/octo-agent product-help --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/open-octo/octo-agent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/internal/skills/defaults/product-help .gemini/skills/product-help && 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 "product-help" agent skill from https://github.com/open-octo/octo-agent/tree/main/internal/skills/defaults/product-help into .gemini/skills/product-help/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "product-help", 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 open-octo/octo-agent product-helpInstalls 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 open-octo/octo-agent --skill product-help -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/open-octo/octo-agent.git skills-src && mkdir -p .github/skills && cp -r skills-src/internal/skills/defaults/product-help .github/skills/product-help && 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 "product-help" agent skill from https://github.com/open-octo/octo-agent/tree/main/internal/skills/defaults/product-help into .github/skills/product-help/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "product-help", 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 open-octo/octo-agent --skill product-help -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install open-octo/octo-agent product-help --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/open-octo/octo-agent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/internal/skills/defaults/product-help .opencode/skills/product-help && 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 "product-help" agent skill from https://github.com/open-octo/octo-agent/tree/main/internal/skills/defaults/product-help into .opencode/skills/product-help/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "product-help", 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
product-help- GitHub stars
- 125
- Token cost
- ~1.4k tokens
- SKILL.md length
- 647 words
- Files
- 15
- Skills in repo
- 40
- Repo updated
- First seen
- Licence
- MIT
At a glance
Answer questions about how to use octo, or diagnose something that isn't working, by reading the product documentation.
- Works in 2 steps: Bundled docs — check the skill directory… → Online docs (fallback, and the source of…
- The user asks how do I...
- SKILL.md covers Documentation sources, How to answer and Example interactions
- Reaches octo-agent.dev
What it does
Product Help is an agent skill from open-octo/octo-agent. Answer questions about how to use octo, or diagnose something that isn't working, by reading the product documentation. Use when the user asks "how do I...", "what is...", "where is the docs for...", any usage/help question about octo itself, or reports a problem — "not working", "won't start", "error", "connection refused", "daemon won't start" — by reading TROUBLESHOOTING.md.
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 14 other files (for example `CLI.md`, `CONFIG.md` and `HOOKS.md`).
It sits in Writing & Content, covering Technical writing. It works with Model Context Protocol. The repository describes itself as: Open-source, single-binary, self-hosted AI agent — your models and data stay on your machine. A coding agent on par with Claude Code and a personal assistant lighter than… The licence is MIT.
When your agent uses it
- The user asks how do I...
- Where is the docs for...
- Any usage/help question about octo itself
- Reports a problem — not working
Example prompts
- “how do I...”
- “what is...”
- “where is the docs for...”
- “/product-help”
Workflow steps
2 steps, taken from the first numbered list in SKILL.md.
- Bundled docs — check the skill directory for reference files. Each is a concise, offline-readable summary; most end with a link to the…
- Online docs (fallback, and the source of truth for anything the bundled summaries don't cover) — the public docs site at…
What it can do on your machine
Read from SKILL.md and the folder at commit 81448b2. 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
Hosts in commands or code, which the agent is likely to contact:
octo-agent.dev
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
Product Help loads about 1.4k tokens when it runs. Until then it costs about 98 tokens; SKILL.md has 647 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 open-octo/octo-agent at commit 81448b2, republished under its MIT licence (© open-octo). 647 words, ~1,439 tokens.
Download SKILL.mdSave it as
.claude/skills/product-help/SKILL.md (or your agent's skills folder). This skill also uses 14 other files; get the full folder from GitHub.- name
- product-help
- description
- Answer questions about how to use octo, or diagnose something that isn't working, by reading the product documentation. Use when the user asks "how do I...", "what is...", "where is the docs for...", any usage/help question about octo itself, or reports a problem — "not working", "won't start", "error", "connection refused", "daemon won't start" — by reading TROUBLESHOOTING.md.
Product Help — answer octo usage questions from documentation
You have access to octo's product documentation. Use it to answer user questions accurately. Do not guess or hallucinate features.
Documentation sources
Bundled docs — check the skill directory for reference files. Each is a concise, offline-readable summary; most end with a link to the fuller online guide for depth (exact schemas, edge cases, worked examples) — follow that link with
web_fetchwhen the summary doesn't fully answer the question, rather than guessing at the missing detail.README.md— quick start, installation, basic usage, feature overviewCLI.md— command reference (octo,octo config,octo skills,octo workflows,octo browser, etc.)CONFIG.md— configuration file format and top-level fieldsSKILLS.md— the default-skill mechanism (embedding, precedence,octo skills) and how to write your ownWORKFLOW.md— contributor development workflow for octo-agent's own codebase, git conventions, PR process (NOT theocto workflowsproduct feature — see CLI.md for that)MCP.md— MCP server configuration (mcp.json, OAuth, Tool Search)MEMORY.md— cross-session memory (file layout, injection) and the optional external memory-backend featurePERMISSIONS.md— the permission engine (modes, rule format, per-session overrides)HOOKS.md— the hooks engine (hooks.yml, event types, blocking)IM.md— the IM/chat bridge (channels.yml, supported platforms,send_message/send_file)TUI.md— terminal UI reference (slash commands, keyboard shortcuts, status bar)WEB.md— Web UI reference (octo servedashboard: composer shortcuts, mid-turn steer vs. queue)THEMES.md— Web UI themes (~/.octo/themes/<id>/: manifest, the light/dark two-block rule, silent-failure traps)TROUBLESHOOTING.md— common issues and fixes
Read the relevant file(s) with
read_filebefore answering.Online docs (fallback, and the source of truth for anything the bundled summaries don't cover) — the public docs site at
https://octo-agent.dev/docs/, fetched withweb_fetch:guides/<topic>/for narrative how-tos — e.g.guides/goals/,guides/workflows/,guides/loop/,guides/cron-tasks/,guides/browser-automation/,guides/sub-agents/,guides/expert-agents/,guides/light-apps/(reusable HTML mini-apps the agent can author; mounted into the left nav or side panel they are octo's closest thing to plugins),guides/sandbox-the-agent/,guides/self-host/,guides/air-gapped/,guides/channels/,guides/hooks/,guides/use-skills/,guides/connect-mcp-servers/,guides/memory/,guides/memory-backends/,guides/profiles/,guides/genui/,guides/customize/(Web UI customization overview: themes + start screen + mounted Light Apps),guides/themes/,guides/start-screen/(customizing the new-session page: cards, hero, app shortcuts — including the built-in cards' text, which lives in the frontend's i18n and nowhere a user can open)reference/<topic>/for exhaustive lookups —reference/cli/,reference/config-file/,reference/permissions/,reference/slash-commands/,reference/tools/,reference/http-api/,reference/security/,reference/compatibility/- Some topics (
sub-agents,expert-agents,light-apps,sandbox-the-agent,self-host) have a full guide online but no bundled summary file at all — go straight toweb_fetchfor those. - For anything neither the bundled docs nor the docs site cover (e.g. an internal design doc under
dev-docs/), fall back tohttps://github.com/open-octo/octo-agent/blob/main/<path>viaweb_fetch.
Show full SKILL.md (236 more words)Show less
How to answer
- Identify the topic. Map the user's question to the most relevant doc file(s).
- Read the source. Use
read_filefor bundled docs orweb_fetchfor online docs. - Quote selectively. Cite specific sections or code blocks from the docs to back up your answer.
- Be concise. Give the direct answer first, then optionally link to the full doc for deeper reading.
- Say when you don't know. If neither bundled nor online docs cover the question, say so honestly — don't make up an answer.
Example interactions
User: "how do I add a custom skill?"
→ Read SKILLS.md from the skill directory
→ Answer with the directory layout, frontmatter format, and how to trigger it
User: "what does permission_mode do?"
→ Read CONFIG.md from the skill directory
→ Explain the three modes with their behavior
User: "how do I switch to OpenAI?"
→ Read CONFIG.md and CLI.md
→ Explain octo config wizard vs. editing ~/.octo/config.yml directly
User: "my IM bot stopped responding" / "daemon won't start"
→ Read TROUBLESHOOTING.md from the skill directory
→ Point at ~/.octo/serve.log / ~/.octo/serve.pid and octo serve --status before guessing at a cause
User: "how does the loop feature work?" / "what's the difference between /loop and cron?"
→ No bundled summary covers this — web_fetch guides/loop/ (and guides/cron-tasks/ for the comparison)
→ Explain the syntax and in-session-vs-persistent distinction; don't confuse this with actually
invoking the loop skill — that happens only when the user wants a task run repeatedly right now
© open-octo, 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 14 other files in internal/skills/defaults/product-help of open-octo/octo-agent.
- SKILL.md
- CLI.md
- CONFIG.md
- HOOKS.md
- IM.md
- MCP.md
- MEMORY.md
- PERMISSIONS.md
- README.md
- SKILLS.md
- THEMES.md
- TROUBLESHOOTING.md
- TUI.md
- WEB.md
- WORKFLOW.md
Open the folder on GitHubat commit 81448b2
Compare with similar skills
Product Help 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 |
|---|---|---|---|---|---|---|
| Product Help this skillopen-octo/octo-agent | 125 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Writing Docsnukeop/nuclear | 19k | — | ~907 | Automated safety check: Pass | AGPL-3.0 | |
| Nemoclaw User GuideNVIDIA/NemoClaw | 23k | — | ~869 | Automated safety check: Pass | Apache-2.0 | |
| Agentdock User Guideuvwt/agentdock | 1.2k | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Nemoclaw User GuideNVIDIA/skills | 3.5k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| JavaScript Concept Fact Checkerleonardomso/33-js-concepts | 67k | 1 repos | ~5k | Automated safety check: Pass | MIT |
Similar skills
- Official
Nemoclaw User Guide
NVIDIA/NemoClaw
Find official NemoClaw documentation for installation, configuration, operation, or troubleshooting.
Agentdock User Guide
uvwt/agentdock
当用户询问 AgentDock 是什么、如何使用、配置在哪里、不同平台或安装方式怎样修改配置并生效、如何重启或验证配置、如何发现并配置 Codex/Claude/Grok 等 Coding Agent 的 ACP，以及常见运行问题时使用；覆盖 macOS Desktop、Windows Desktop、Linux 服务、Docker 和直接运行二进制，不用于源码开发与贡献流程。
- Official
Nemoclaw User Guide
NVIDIA/skills
Guides human users' AI agents to the NemoClaw docs MCP server and canonical Fern documentation in Markdown form.
JavaScript Concept Fact Checker
leonardomso/33-js-concepts
Verifies the technical accuracy of JavaScript concept pages by checking code examples, MDN and ECMAScript claims and external links through a five-phase method.
Beads Documentation Style Guide
gastownhall/beads
Sets the house style for the beads user docs: the canonical concept model, required terminology, prose and diagram conventions, and checks before docs work is done.
More from open-octo/octo-agent
All 40 skills in this repoImage Gen
open-octo/octo-agent
Acquire images as files — generate them with an AI image model (14 providers: OpenAI/gpt-image, Gemini, Qwen, Zhipu, Volcengine, Stability, FLUX, Ideogram, MiniMax, and more), search openly-licensed…
Office XLSX
open-octo/octo-agent
Create, read, and edit Excel (.xlsx) spreadsheets programmatically with openpyxl — cell values, formulas, styling (fonts/fills/borders/alignment/number formats), merged cells, multiple sheets…
Artifact Design
open-octo/octo-agent
Design guidance for any HTML/Markdown file shown in octo's Artifacts panel — reports, dashboards, architecture/system diagrams, generated UIs, slide-style pages, 3D scenes.
Code Review
open-octo/octo-agent
Review local code changes. An agent skill from open-octo/octo-agent.
Ppt Master
open-octo/octo-agent
AI-driven multi-format SVG content generation system. An agent skill from open-octo/octo-agent.
Config Setup
open-octo/octo-agent
Configure octo's global settings through guided conversation — set up AI model endpoints (providers, API keys, models), adjust agent defaults (reasoning effort, permission mode, coauthor, workspace…
Related
Works with
Categories
Questions about Product Help
What does Product Help do?
Answer questions about how to use octo, or diagnose something that isn't working, by reading the product documentation. Product Help is an agent skill from open-octo/octo-agent. Answer questions about how to use octo, or diagnose something that isn't working, by reading the product documentation.
When should I use Product Help?
Product Help fits situations like: the user asks how do I..; where is the docs for..; any usage/help question about octo itself; reports a problem — not working.
How do I install Product Help in Claude Code?
Run `npx skills add open-octo/octo-agent --skill product-help -a claude-code`. Or copy the skill folder (internal/skills/defaults/product-help in open-octo/octo-agent) into .claude/skills/product-help in your project. Claude Code loads it when a task matches its description.
How do I install Product Help in Codex?
Run `npx skills add open-octo/octo-agent --skill product-help -a codex`. Or copy the skill folder (internal/skills/defaults/product-help in open-octo/octo-agent) into .agents/skills/product-help in your project. Codex loads it when a task matches its description.
Can I use Product Help 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 open-octo/octo-agent --skill product-help -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/product-help, .gemini/skills/product-help, .github/skills/product-help and .opencode/skills/product-help in your project.
What does Product Help need to run?
SKILL.md names no scripts, command-line tools or credentials: Product Help is instructions for the agent only.
Does Product Help access the network?
SKILL.md names 1 domain. In commands or code: octo-agent.dev; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Product Help 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 Product Help use?
Product Help 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 Product Help use?
About 1.4k tokens (SKILL.md is roughly 5.8k 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 Product Help?
Skills that share tags, products or a category with Product Help: Writing Docs (nukeop/nuclear, 19k stars), Nemoclaw User Guide (NVIDIA/NemoClaw, 23k stars), Agentdock User Guide (uvwt/agentdock, 1.2k stars) and Nemoclaw User Guide (NVIDIA/skills, 3.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Product Help?
open-octo (a GitHub organization) maintains it in open-octo/octo-agent, which has 125 GitHub stars. The repository holds 40 skills in this directory. The repository was last updated on October 9, 2026.
Source: open-octo/octo-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.