Agent Refinement
ruvnet/ruflo
Agent skill for refinement - invoke with $agent-refinement. An agent skill from ruvnet/ruflo.
Sharpen todo items in brain/todos.md into precise, actionable prompts via targeted questioning.
MITAuto-check passed
Install Refine
$ npx skills add poteto/noodle --skill refine -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install poteto/noodle refine --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/poteto/noodle.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/refine .claude/skills/refine && 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 "refine" agent skill from https://github.com/poteto/noodle/tree/main/.agents/skills/refine into .claude/skills/refine/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "refine", 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/poteto/noodle/tree/main/.agents/skills/refineType 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 poteto/noodle --skill refine -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install poteto/noodle refine --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/poteto/noodle.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/refine .agents/skills/refine && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "refine" agent skill from https://github.com/poteto/noodle/tree/main/.agents/skills/refine into .agents/skills/refine/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "refine", 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 poteto/noodle --skill refine -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install poteto/noodle refine --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/poteto/noodle.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/refine .cursor/skills/refine && 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 "refine" agent skill from https://github.com/poteto/noodle/tree/main/.agents/skills/refine into .cursor/skills/refine/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "refine", 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/poteto/noodle.git --path .agents/skills/refine--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 poteto/noodle --skill refine -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install poteto/noodle refine --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/poteto/noodle.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/refine .gemini/skills/refine && 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 "refine" agent skill from https://github.com/poteto/noodle/tree/main/.agents/skills/refine into .gemini/skills/refine/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "refine", 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 poteto/noodle refineInstalls 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 poteto/noodle --skill refine -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/poteto/noodle.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/refine .github/skills/refine && 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 "refine" agent skill from https://github.com/poteto/noodle/tree/main/.agents/skills/refine into .github/skills/refine/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "refine", 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 poteto/noodle --skill refine -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install poteto/noodle refine --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/poteto/noodle.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/refine .opencode/skills/refine && 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 "refine" agent skill from https://github.com/poteto/noodle/tree/main/.agents/skills/refine into .opencode/skills/refine/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "refine", 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
refine- GitHub stars
- 420
- Token cost
- ~385 tokens
- SKILL.md length
- 197 words
- Files
- 1
- Skills in repo
- 26
- Repo updated
- First seen
- Licence
- MIT
At a glance
Sharpen todo items in brain/todos.md into precise, actionable prompts via targeted questioning.
- Works in 6 steps: Read brain/todos.md and review items… → Triage each item: is it clear enough to… → Ask clarifying questions about unclear… → …
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Refine is an agent skill from poteto/noodle. Sharpen todo items in brain/todos.md into precise, actionable prompts via targeted questioning. Triggers: "refine", "refine todos", "clarify todos".
Its SKILL.md is about 390 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Orchestrate agents using skills. The licence is MIT.
Example prompts
- “refine”
- “refine todos”
- “clarify todos”
- “/refine”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Read brain/todos.md and review items under ## Open.
- Triage each item: is it clear enough to act on without further context? A clear item specifies what is wrong, where it happens, and what…
- Ask clarifying questions about unclear items using AskUserQuestion. Group related questions — aim for one round of questions, not a…
- Rewrite unclear items in-place using Edit, incorporating the user's answers. Each rewritten item should be a self-contained prompt that…
- Remove any items the user says are already done or no longer relevant.
- Report a summary of what changed.
What it can do on your machine
Read from SKILL.md and the folder at commit 82d2921. 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.
Context cost
Refine loads about 385 tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 197 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 poteto/noodle at commit 82d2921, republished under its MIT licence (© poteto). 197 words, ~385 tokens.
Download SKILL.mdSave it as
.claude/skills/refine/SKILL.md (or your agent's skills folder).- name
- refine
- description
- Sharpen todo items in brain/todos.md into precise, actionable prompts via targeted questioning. Triggers: "refine", "refine todos", "clarify todos".
Refine
Read brain/todos.md and refine unclear items into actionable prompts through targeted questioning.
Workflow
Use Tasks to track progress. Create a task for each step below (TaskCreate), mark each in_progress when starting and completed when done (TaskUpdate). Check TaskList after each step.
- Read
brain/todos.mdand review items under## Open. - Triage each item: is it clear enough to act on without further context? A clear item specifies what is wrong, where it happens, and what the fix should be. Skip items that already meet this bar.
- Ask clarifying questions about unclear items using
AskUserQuestion. Group related questions — aim for one round of questions, not a back-and-forth (to minimize back-and-forth and user fatigue). Good clarifying questions target:- What — what exactly is the problem or desired behavior?
- Where — which part of the app, which component, which flow?
- How — how should it work instead? What does "fixed" look like?
- Rewrite unclear items in-place using
Edit, incorporating the user's answers. Each rewritten item should be a self-contained prompt that another agent could act on without additional context. - Remove any items the user says are already done or no longer relevant.
- Report a summary of what changed.
© poteto, 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 .agents/skills/refine of poteto/noodle.
Open the folder on GitHubat commit 82d2921
Compare with similar skills
Refine 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 |
|---|---|---|---|---|---|---|
| Refine this skillpoteto/noodle | 420 | — | ~385 | Automated safety check: Pass | MIT | |
| Agent Refinementruvnet/ruflo | 74k | 2 repos | ~3.5k | Automated safety check: Pass | MIT | |
| Refinewindmill-labs/windmill | 18k | — | ~420 | Automated safety check: Pass | Custom licence | |
| Refiner AutomationComposioHQ/awesome-claude-skills | 77k | 3 repos | ~730 | Automated safety check: Pass | None | |
| Sparc Refineruvnet/ruflo | 74k | — | ~1.5k | Automated safety check: Notes | MIT | |
| Refine Promptpenpot/penpot | 61k | — | ~1.6k | Automated safety check: Pass | MPL-2.0 |
Similar skills
Refine
windmill-labs/windmill
End-of-session reflection. An agent skill from windmill-labs/windmill.
Refiner Automation
ComposioHQ/awesome-claude-skills
Automate Refiner tasks via Rube MCP (Composio). An agent skill from ComposioHQ/awesome-claude-skills.
Sparc Refine
ruvnet/ruflo
Run the SPARC Refinement and Completion phases — review code, improve test coverage, validate against specification, and generate documentation
Refine Prompt
penpot/penpot
Refine and improve a user-supplied prompt for maximum clarity and effectiveness using prompt-engineering best practices and Penpot project context.
Brain Taxonomist
garrytan/gbrain
Filing gate for ALL brain writes. An agent skill from garrytan/gbrain.
More from poteto/noodle
All 26 skills in this repoMeditate
poteto/noodle
Audit and evolve the brain vault — prune outdated content, discover cross-cutting principles, review skills for structural encoding opportunities.
Ruminate
poteto/noodle
Mine past Claude Code and Codex conversations for uncaptured patterns, corrections, and knowledge.
Ast Grep
poteto/noodle
Structural code search via ast-grep — use when code shape and element relationships matter, not just text.
Execute
poteto/noodle
Implementation methodology for executing tasks. An agent skill from poteto/noodle.
Noodle
poteto/noodle
Operate the Noodle CLI — explain commands, find flags, create/edit .noodle.toml config.
Plan
poteto/noodle
Systematic planning for medium-to-large tasks. An agent skill from poteto/noodle.
Questions about Refine
What does Refine do?
Sharpen todo items in brain/todos.md into precise, actionable prompts via targeted questioning. Refine is an agent skill from poteto/noodle.md into precise, actionable prompts via targeted questioning.
How do I install Refine in Claude Code?
Run `npx skills add poteto/noodle --skill refine -a claude-code`. Or copy the skill folder (.agents/skills/refine in poteto/noodle) into .claude/skills/refine in your project. Claude Code loads it when a task matches its description.
How do I install Refine in Codex?
Run `npx skills add poteto/noodle --skill refine -a codex`. Or copy the skill folder (.agents/skills/refine in poteto/noodle) into .agents/skills/refine in your project. Codex loads it when a task matches its description.
Can I use Refine 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 poteto/noodle --skill refine -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/refine, .gemini/skills/refine, .github/skills/refine and .opencode/skills/refine in your project.
What does Refine need to run?
SKILL.md names no scripts, command-line tools or credentials: Refine is instructions for the agent only.
Does Refine 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 Refine 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 Refine use?
Refine 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 Refine use?
About 385 tokens (SKILL.md is roughly 1.5k 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 Refine?
Skills that share tags, products or a category with Refine: Agent Refinement (ruvnet/ruflo, 74k stars), Refine (windmill-labs/windmill, 18k stars), Refiner Automation (ComposioHQ/awesome-claude-skills, 77k stars) and Sparc Refine (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Refine?
poteto (a GitHub user) maintains it in poteto/noodle, which has 420 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on March 19, 2026.
Source: poteto/noodle on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.