Ralph
opentabs-dev/opentabs
Plan work and generate ralph task files for autonomous execution.
Convert a PRD markdown file to prd.json for execution. An agent skill from snarktank/compound-product.
Install Tasks
The automated check flagged lines worth reading first. See the safety section below.
$ npx skills add snarktank/compound-product --skill tasks -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install snarktank/compound-product tasks --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/snarktank/compound-product.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tasks .claude/skills/tasks && 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 "tasks" agent skill from https://github.com/snarktank/compound-product/tree/main/skills/tasks into .claude/skills/tasks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tasks", 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/snarktank/compound-product/tree/main/skills/tasksType 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 snarktank/compound-product --skill tasks -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install snarktank/compound-product tasks --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/snarktank/compound-product.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/tasks .agents/skills/tasks && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "tasks" agent skill from https://github.com/snarktank/compound-product/tree/main/skills/tasks into .agents/skills/tasks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tasks", 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 snarktank/compound-product --skill tasks -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install snarktank/compound-product tasks --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/snarktank/compound-product.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/tasks .cursor/skills/tasks && 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 "tasks" agent skill from https://github.com/snarktank/compound-product/tree/main/skills/tasks into .cursor/skills/tasks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tasks", 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/snarktank/compound-product.git --path skills/tasks--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 snarktank/compound-product --skill tasks -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install snarktank/compound-product tasks --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/snarktank/compound-product.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/tasks .gemini/skills/tasks && 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 "tasks" agent skill from https://github.com/snarktank/compound-product/tree/main/skills/tasks into .gemini/skills/tasks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tasks", 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 snarktank/compound-product tasksInstalls 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 snarktank/compound-product --skill tasks -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/snarktank/compound-product.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/tasks .github/skills/tasks && 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 "tasks" agent skill from https://github.com/snarktank/compound-product/tree/main/skills/tasks into .github/skills/tasks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tasks", 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 snarktank/compound-product --skill tasks -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install snarktank/compound-product tasks --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/snarktank/compound-product.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/tasks .opencode/skills/tasks && 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 "tasks" agent skill from https://github.com/snarktank/compound-product/tree/main/skills/tasks into .opencode/skills/tasks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tasks", 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
tasks- GitHub stars
- 542
- Token cost
- ~3.4k tokens
- SKILL.md length
- 763 words
- Files
- 1
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- None found
At a glance
Convert a PRD markdown file to prd.json for execution. An agent skill from snarktank/compound-product.
- Works in 6 steps: Read the PRD → Extract High-Level Tasks → Explode Into Granular Tasks → …
- Generate tasks from prd
- SKILL.md covers The Job, Critical: Agent-Testable Tasks, Input and Output Format, plus 6 more sections
- Calls npm
What it does
Tasks is an agent skill from snarktank/compound-product. Convert a PRD markdown file to prd.json for execution. Triggers on: convert prd, create tasks, prd to json, generate tasks from prd.
Its SKILL.md is about 3.4k 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 Product & Project Management, covering PRD writing and Browser automation. The repository describes itself as: A self-improving product system that reads reports, identifies priorities, and autonomously implements fixes.
When your agent uses it
- Generate tasks from prd
- Tasks that involve PRD writing
- Tasks that involve Browser automation
Example prompts
- “/tasks”
Workflow steps
6 steps, taken from the step headings in SKILL.md.
- Read the PRD
- Extract High-Level Tasks
- Explode Into Granular Tasks
- Order by Dependencies
- Generate prd.json
- Save and Summarize
What it can do on your machine
Read from SKILL.md and the folder at commit 98bb91f. 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:
npm
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.com
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
Tasks loads about 3.4k tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 763 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: warnings
The automated check found patterns that need a careful read before installing.
- WarningTells the agent its actions are pre-authorized / not to stop for confirmationSKILL.md:310
**Do NOT wait for user confirmation.** Save the file and proceed.
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 763 words (~3,401 tokens).
“Converts a PRD markdown document into the prd.json format for the execution loop.”
- name
- tasks
Files
Just SKILL.md in skills/tasks of snarktank/compound-product.
Open the folder on GitHubat commit 98bb91f
Compare with similar skills
Tasks 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 |
|---|---|---|---|---|---|---|
| Tasks this skillsnarktank/compound-product | 542 | — | ~3.4k | Automated safety check: Warn | None | |
| Ralphopentabs-dev/opentabs | 967 | — | ~157 | Automated safety check: Pass | MIT | |
| Case Radaryunshu0909/yunshu_skillshub | 767 | — | ~1.9k | Automated safety check: Pass | MIT | |
| CCPM Project Managementautomazeio/ccpm | 8.4k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Ralph Tui Create Beadssubsy/ralph-tui | 2.5k | 1 repos | ~2.6k | Automated safety check: Pass | MIT | |
| Trellis Brainstormanjiemo/SunnyBeach | 178 | 7 repos | ~4k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Case Radar
yunshu0909/yunshu_skillshub
案例雷达。给一个新东西（新工具/新概念/新生态），扫一遍生态找好玩的真实案例，重点是抓"真物"（截图/源码/演示）而不是 GitHub 主页，输出可浏览的 HTML 案例集。当用户说"看看大家用 X 做了什么"、"扫一下 X 生态"、"市面上 X 有什么新玩法"、"给我看 X 的真物案例"、"/case-radar"时触发。不适合：① 已有明确目标的深度调研（使用可用的调研工具直接研究）②…
CCPM Project Management
automazeio/ccpm
Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.
Ralph Tui Create Beads
subsy/ralph-tui
Convert PRDs to beads for ralph-tui execution. An agent skill from subsy/ralph-tui.
Trellis Brainstorm
anjiemo/SunnyBeach
Guides collaborative requirements discovery before implementation.
Adversarial Spec
zscole/adversarial-spec
Iteratively refine a product spec by debating with multiple LLMs (GPT, Gemini, Grok, etc.) until all models agree.
Related
Categories
Questions about Tasks
What does Tasks do?
Convert a PRD markdown file to prd.json for execution. An agent skill from snarktank/compound-product. Tasks is an agent skill from snarktank/compound-product.json for execution.
When should I use Tasks?
Tasks fits situations like: generate tasks from prd; tasks that involve PRD writing; tasks that involve Browser automation.
How do I install Tasks in Claude Code?
Run `npx skills add snarktank/compound-product --skill tasks -a claude-code`. Or copy the skill folder (skills/tasks in snarktank/compound-product) into .claude/skills/tasks in your project. Claude Code loads it when a task matches its description.
How do I install Tasks in Codex?
Run `npx skills add snarktank/compound-product --skill tasks -a codex`. Or copy the skill folder (skills/tasks in snarktank/compound-product) into .agents/skills/tasks in your project. Codex loads it when a task matches its description.
Can I use Tasks 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 snarktank/compound-product --skill tasks -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tasks, .gemini/skills/tasks, .github/skills/tasks and .opencode/skills/tasks in your project.
What does Tasks need to run?
Going by SKILL.md and its folder, Tasks needs the command-line tools its instructions call (npm).
Does Tasks access the network?
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Is Tasks safe to install?
Our automated static check of SKILL.md flagged 1 warning(s): tells the agent its actions are pre-authorized / not to stop for confirmation. Read the flagged lines before installing; the check is not a guarantee either way.
What licence does Tasks use?
No licence was found for Tasks or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Tasks use?
About 3.4k tokens (SKILL.md is roughly 14k 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 Tasks?
Skills that share tags, products or a category with Tasks: Ralph (opentabs-dev/opentabs, 967 stars), Case Radar (yunshu0909/yunshu_skillshub, 767 stars), CCPM Project Management (automazeio/ccpm, 8.4k stars) and Ralph Tui Create Beads (subsy/ralph-tui, 2.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Tasks?
snarktank (a GitHub user) maintains it in snarktank/compound-product, which has 542 GitHub stars. The repository was last updated on January 23, 2026.
Source: snarktank/compound-product on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.