Install the "stage-resolve" agent skill from https://github.com/ReviewStage/stage-cli/tree/main/skills/stage-resolve into .claude/skills/stage-resolve/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stage-resolve", 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.
Type 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.
skills CLI
$ npx skills add ReviewStage/stage-cli --skill stage-resolve -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "stage-resolve" agent skill from https://github.com/ReviewStage/stage-cli/tree/main/skills/stage-resolve into .agents/skills/stage-resolve/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stage-resolve", 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.
skills CLI
$ npx skills add ReviewStage/stage-cli --skill stage-resolve -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "stage-resolve" agent skill from https://github.com/ReviewStage/stage-cli/tree/main/skills/stage-resolve into .cursor/skills/stage-resolve/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stage-resolve", 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.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add ReviewStage/stage-cli --skill stage-resolve -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "stage-resolve" agent skill from https://github.com/ReviewStage/stage-cli/tree/main/skills/stage-resolve into .gemini/skills/stage-resolve/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stage-resolve", 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.
Installs 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).
skills CLI
$ npx skills add ReviewStage/stage-cli --skill stage-resolve -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "stage-resolve" agent skill from https://github.com/ReviewStage/stage-cli/tree/main/skills/stage-resolve into .github/skills/stage-resolve/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stage-resolve", 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.
skills CLI
$ npx skills add ReviewStage/stage-cli --skill stage-resolve -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "stage-resolve" agent skill from https://github.com/ReviewStage/stage-cli/tree/main/skills/stage-resolve into .opencode/skills/stage-resolve/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stage-resolve", 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
stage-resolve
GitHub stars
274
Token cost
~1.3k tokens
SKILL.md length
711 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
MIT
At a glance
Pick up the review comments the user left in the Stage UI for the current diff, make the requested changes, and resolve each thread.
Works in 3 steps: List open threads → Handle each thread → Report back
Development work in your project
SKILL.md covers Prerequisites, Arguments, Step 1 — List open threads and Step 2 — Handle each thread, plus 2 more sections
Calls npm
What it does
Stage Resolve is an agent skill from ReviewStage/stage-cli. Pick up the review comments the user left in the Stage UI for the current diff, make the requested changes, and resolve each thread.
Its SKILL.md is about 1.3k 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 Development. The repository describes itself as: A viewer for reviewing local code changes in small individual chapters. Works with any AI agent. The licence is MIT.
When your agent uses it
Development work in your project
Example prompts
“/stage-resolve”
Requirements
Node.js
Workflow steps
3 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 59b977b. 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
No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.
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
Stage Resolve loads about 1.3k tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 711 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~37
When it runs· the whole SKILL.md, loaded when a task matches
~1.3k
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.
Download SKILL.mdSave it as .claude/skills/stage-resolve/SKILL.md (or your agent's skills folder).
name
stage-resolve
description
Pick up the review comments the user left in the Stage UI for the current diff, make the requested changes, and resolve each thread.
user-invocable
true
stage-resolve
Reads the local review comments the user left in the Stage browser UI (created by /stage-chapters), acts on each open thread, and resolves it. Uses stagereview comments, which reads and writes the same local database the UI uses — the stagereview show server does not need to be running, and the UI picks up your replies and resolutions automatically.
Every comment you write through the CLI is attributed to the agent and shows an "Agent" badge in the UI, so the user can tell your replies from their own notes.
Prerequisites
Run this check before any other work. If it fails, stop with the error message — do not continue.
stagereview is installed. Run which stagereview. If it exits non-zero, instruct the user:
stagereview is not installed. Run:
npm install -g stagereview
Arguments
Diff selectors. Pass through any git refs or flags the user gave (--pr 123, --base main, --ref staged, main..feature, …) to every list and create call exactly as given. They select the same diff scope /stage-chapters used, so you see the threads the UI shows. With no arguments the CLI uses the same default scope stagereview show uses for the working tree.
A single thread ID (full UUID or a prefix of at least 6 characters). When given, handle only that thread and skip the listing step.
Step 1 — List open threads
Run this before editing any files, and keep the output — you will address threads by the IDs it returns:
bash
stagereview comments list --status open --json [refs...] [--pr <ref>] [--base <ref>] [--compare <ref>] [--ref <mode>]
Each thread has id, filePath, side (additions = new file lines, deletions = old file lines), startLine, endLine, status, and comments ordered oldest first. Each comment carries body, authorType (user or agent), and timestamps.
If the list is empty, tell the user there are no open comment threads for this diff and stop.
The diff scope is keyed on git state. If the working tree was clean when the review was opened and you then edit files, a later list with no arguments resolves to a different (working-tree) scope. Address threads by ID (show, reply, resolve, reopen are not scoped), and do not commit while working through threads unless the user asks.
Show full SKILL.md (378 more words)Show less
Step 2 — Handle each thread
For each open thread, in order:
Read the whole conversation. The first comment is the request; later comments may refine it or answer earlier questions.
Skip threads waiting on the user. If the last comment has authorType: "agent" and asks the user a question they have not answered, leave the thread alone and mention it in your summary.
Decide what the comment asks for.
A request or instruction ("rename this", "add a null check", "extract a helper") → make the change.
A question that implies an action ("should we add a test for this?", "could this be a constant?") → treat it as a request and make the change.
A pure question ("why does this fall back to the primary org?") → answer it and resolve the thread:bash
Before editing, read the surrounding source, not just the anchored lines — the comment is anchored to a diff line range, but the right fix may live nearby. Follow the repository's coding guidelines (for example AGENTS.md or CLAUDE.md) and existing conventions.
Make the change, then run the project's relevant checks (typecheck, lint, tests) for the files you touched.
Resolve with a short summary of what changed:bash
stagereview comments resolve <threadId> --body "Fixed: <what changed and where>"
Keep the body to one or two sentences. Do not paste file contents.
To inspect a single thread in full at any point:
bash
stagereview comments show <threadId>
Step 3 — Report back
Run the listing again with the same selectors you used in Step 1:
bash
stagereview comments list --status open [same selectors as Step 1]
Then tell the user:
which threads you resolved and, in a line each, what you changed;
which threads you replied to with a question and are waiting on them;
that the Stage UI in their browser has already picked up your replies and resolutions.
Leaving your own comments
If you notice something worth flagging while working — a risk, a follow-up, a question about intent — leave a comment on the diff rather than burying it in chat:
Stage Resolve 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.
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.
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.
A skill your agent uses when CI is failing on a branch and you need to diagnose failures from GitHub, fix them locally with iterative verification, and re-push clean commits.
A skill your agent uses when a PR is open and the user wants to autonomously monitor and fix PR review comments, CI failures, and rebase conflicts on a recurring loop, or when asked to…
A skill your agent uses when reviewing code changes against AGENTS.md implementation quality standards, or when asked to do an implementation quality review
Pick up the review comments the user left in the Stage UI for the current diff, make the requested changes, and resolve each thread. Stage Resolve is an agent skill from ReviewStage/stage-cli. Pick up the review comments the user left in the Stage UI for the current diff, make the requested changes, and resolve each thread.
When should I use Stage Resolve?
Stage Resolve fits situations like: development work in your project.
How do I install Stage Resolve in Claude Code?
Run `npx skills add ReviewStage/stage-cli --skill stage-resolve -a claude-code`. Or copy the skill folder (skills/stage-resolve in ReviewStage/stage-cli) into .claude/skills/stage-resolve in your project. Claude Code loads it when a task matches its description.
How do I install Stage Resolve in Codex?
Run `npx skills add ReviewStage/stage-cli --skill stage-resolve -a codex`. Or copy the skill folder (skills/stage-resolve in ReviewStage/stage-cli) into .agents/skills/stage-resolve in your project. Codex loads it when a task matches its description.
Can I use Stage Resolve 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 ReviewStage/stage-cli --skill stage-resolve -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/stage-resolve, .gemini/skills/stage-resolve, .github/skills/stage-resolve and .opencode/skills/stage-resolve in your project.
What does Stage Resolve need to run?
Going by SKILL.md and its folder, Stage Resolve needs the command-line tools its instructions call (npm). Our summary lists: Node.js.
Does Stage Resolve access the network?
SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Stage Resolve 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 Stage Resolve use?
Stage Resolve 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 Stage Resolve use?
About 1.3k tokens (SKILL.md is roughly 5.2k 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 Stage Resolve?
Skills that share tags, products or a category with Stage Resolve: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Stage Resolve?
ReviewStage (a GitHub organization) maintains it in ReviewStage/stage-cli, which has 274 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on September 7, 2026.
Source: ReviewStage/stage-cli on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
