New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Roborev Refine

by obra in obra/dotfiles

Iterative review-fix loop for the current branch — reviews via daemon, fixes inline, re-reviews until passing or max iterations reached

No licenceAuto-check passed

Install Roborev Refine

skills CLI
$ npx skills add obra/dotfiles --skill roborev-refine -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install obra/dotfiles roborev-refine --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/obra/dotfiles.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/roborev-refine .claude/skills/roborev-refine && rm -rf skills-src

Use ~/.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/

Facts

Skill name
roborev-refine
GitHub stars
116
Token cost
~2.2k tokens
SKILL.md length
1,249 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
None found

At a glance

Iterative review-fix loop for the current branch — reviews via daemon, fixes inline, re-reviews until passing or max iterations reached

  • Works in 4 steps: Validate inputs and refine context → Run the initial review → Fix-review loop → …
  • SKILL.md covers Usage, When NOT to invoke this skill, IMPORTANT and Instructions, plus 2 more sections
  • Calls go

What it does

Roborev Refine is an agent skill from obra/dotfiles. Iterative review-fix loop for the current branch — reviews via daemon, fixes inline, re-reviews until passing or max iterations reached

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

Example prompts

  • “/roborev-refine”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Validate inputs and refine context
  2. Run the initial review
  3. Fix-review loop
  4. Iteration limit reached

What it can do on your machine

Read from SKILL.md and the folder at commit df3be56. 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:

    • go

    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

Roborev Refine loads about 2.2k tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 1,249 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,249 words (~2,224 tokens).

“Iterative review-fix loop: review the current branch or commit range, fix findings, commit, re-review, and repeat until all reviews pass or the iteration limit is reached.”

— opening of SKILL.md by obra
name
roborev-refine

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .codex/skills/roborev-refine of obra/dotfiles.

Open the folder on GitHubat commit df3be56

Compare with similar skills

Roborev 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.

Roborev Refine compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Roborev Refine this skillobra/dotfiles116—~2.2kAutomated safety check: PassNone
Iterative Retrievalaffaan-m/ECC275k7 repos~1.6kAutomated safety check: PassMIT
Agent Refinementruvnet/ruflo74k2 repos~3.5kAutomated safety check: PassMIT
Branchesredis/RedisInsight8.9k—~409Automated safety check: PassCustom licence
Iterate Refinement Notesproduct-on-purpose/pm-skills715—~855Automated safety check: PassApache-2.0
Conventional Branchgithub/awesome-copilot40k—~1.1kAutomated safety check: PassMIT

Similar skills

  • Iterative Retrieval

    affaan-m/ECC

    Pattern for progressively refining context retrieval to solve the subagent context problem.

    275k GitHub starsUsed in 7 repos~1.6k tokens
    Agent WorkflowsAuto-check passed

  • Agent Refinement

    ruvnet/ruflo

    Agent skill for refinement - invoke with $agent-refinement. An agent skill from ruvnet/ruflo.

    74k GitHub starsUsed in 2 repos~3.5k tokens
    DevelopmentAuto-check passed

  • Branches

    redis/RedisInsight

    Official

    Create and name git branches following project conventions. An agent skill from redis/RedisInsight.

    8.9k GitHub stars~409 tokensUpdated 4 days ago
    DevelopmentAuto-check passed

  • Iterate Refinement Notes

    product-on-purpose/pm-skills

    Documents backlog refinement session outcomes including stories refined, estimates, questions raised, and decisions made.

    715 GitHub stars~855 tokensUpdated 4 days ago
    Product & Project ManagementAuto-check passed

  • Conventional Branch

    github/awesome-copilot

    Official

    Create Git branches following the Conventional Branch specification (feature/, bugfix/, hotfix/, release/, chore/).

    40k GitHub stars~1.1k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Finishing a Development Branch

    obra/superpowers

    Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    296k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed

More from obra/dotfiles

All 12 skills in this repo

  • Maintaining Documentation

    obra/dotfiles

    A skill your agent uses when documentation needs creating, checking, or maintaining — docs may have drifted from code, pre-release doc verification, updating docs after finishing code work, adding…

    116 GitHub stars~3.9k tokensUpdated 1 mo ago
    Auto-check passed

  • Chronicle

    obra/dotfiles

    Allows you to view the user's screen as well as several hours of history.

    116 GitHub stars~1.4k tokensUpdated 1 mo ago
    Auto-check passed

  • E2E Scenario Testing

    obra/dotfiles

    A skill your agent uses when verifying a running application end-to-end through its real interface — a web UI, a CLI, or a TUI — by writing and executing agent-run "scenario cards" against a freshly…

    116 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed

  • Roborev Fix

    obra/dotfiles

    A skill your agent uses when the user asks to fix open failing reviews, invokes $roborev-fix, or provides job IDs; do not use when the user only pastes review findings with no request to discover or…

    116 GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check passed

  • Syncing Obsidian

    obra/dotfiles

    A skill your agent uses when reading or writing files in an Obsidian vault that is synced with obsync.

    116 GitHub stars~1.7k tokensUpdated 1 mo ago
    Auto-check passed

  • MCP CLI

    obra/dotfiles

    Use MCP servers on-demand via the mcp CLI tool - discover tools, resources, and prompts without polluting context with pre-loaded MCP integrations

    116 GitHub starsUsed in 1 repo~2.3k tokens
    Auto-check passed

Questions about Roborev Refine

What does Roborev Refine do?

Iterative review-fix loop for the current branch — reviews via daemon, fixes inline, re-reviews until passing or max iterations reached. Roborev Refine is an agent skill from obra/dotfiles.

How do I install Roborev Refine in Claude Code?

Run `npx skills add obra/dotfiles --skill roborev-refine -a claude-code`. Or copy the skill folder (.codex/skills/roborev-refine in obra/dotfiles) into .claude/skills/roborev-refine in your project. Claude Code loads it when a task matches its description.

How do I install Roborev Refine in Codex?

Run `npx skills add obra/dotfiles --skill roborev-refine -a codex`. Or copy the skill folder (.codex/skills/roborev-refine in obra/dotfiles) into .agents/skills/roborev-refine in your project. Codex loads it when a task matches its description.

Can I use Roborev 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 obra/dotfiles --skill roborev-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/roborev-refine, .gemini/skills/roborev-refine, .github/skills/roborev-refine and .opencode/skills/roborev-refine in your project.

What does Roborev Refine need to run?

Going by SKILL.md and its folder, Roborev Refine needs the command-line tools its instructions call (go).

Does Roborev 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 Roborev 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 Roborev Refine use?

No licence was found for Roborev Refine or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Roborev Refine use?

About 2.2k tokens (SKILL.md is roughly 8.9k 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 Roborev Refine?

Skills that share tags, products or a category with Roborev Refine: Iterative Retrieval (affaan-m/ECC, 275k stars), Agent Refinement (ruvnet/ruflo, 74k stars), Branches (redis/RedisInsight, 8.9k stars) and Iterate Refinement Notes (product-on-purpose/pm-skills, 715 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Roborev Refine?

obra (a GitHub user) maintains it in obra/dotfiles, which has 116 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on August 11, 2026.

Source: obra/dotfiles on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.