Agent skill

Orca

A skill your agent uses when the user asks to run an Orca flow (e.g.

Apache-2.0Auto-check passedDevelopment

Install Orca

skills CLI

$ npx skills add VirtusLab/orca --skill orca -a claude-code

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

GitHub CLI

$ gh skill install VirtusLab/orca orca --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/VirtusLab/orca.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/orca .claude/skills/orca && 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/

Paste into Claude Code

Install the "orca" agent skill from https://github.com/VirtusLab/orca/tree/master/skills/orca into .claude/skills/orca/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orca", 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

$skill-installer install https://github.com/VirtusLab/orca/tree/master/skills/orca

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 VirtusLab/orca --skill orca -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install VirtusLab/orca orca --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/VirtusLab/orca.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/orca .agents/skills/orca && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "orca" agent skill from https://github.com/VirtusLab/orca/tree/master/skills/orca into .agents/skills/orca/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orca", 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 VirtusLab/orca --skill orca -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install VirtusLab/orca orca --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/VirtusLab/orca.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/orca .cursor/skills/orca && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "orca" agent skill from https://github.com/VirtusLab/orca/tree/master/skills/orca into .cursor/skills/orca/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orca", 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

$ gemini skills install https://github.com/VirtusLab/orca.git --path skills/orca

--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 VirtusLab/orca --skill orca -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install VirtusLab/orca orca --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/VirtusLab/orca.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/orca .gemini/skills/orca && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "orca" agent skill from https://github.com/VirtusLab/orca/tree/master/skills/orca into .gemini/skills/orca/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orca", 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.

GitHub CLI

$ gh skill install VirtusLab/orca orca

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 VirtusLab/orca --skill orca -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/VirtusLab/orca.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/orca .github/skills/orca && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "orca" agent skill from https://github.com/VirtusLab/orca/tree/master/skills/orca into .github/skills/orca/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orca", 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 VirtusLab/orca --skill orca -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install VirtusLab/orca orca --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/VirtusLab/orca.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/orca .opencode/skills/orca && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "orca" agent skill from https://github.com/VirtusLab/orca/tree/master/skills/orca into .opencode/skills/orca/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orca", 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: orca
GitHub stars: 180
Token cost: ~1.4k tokens
SKILL.md length: 792 words
Files: 3
Skills in repo: 1
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

A skill your agent uses when the user asks to run an Orca flow (e.g.

Works in 3 steps: Choose the flow and where the run goes → Get the prompt → Run
The user asks to run an Orca flow (e.g
SKILL.md covers When to use, 1. Choose the flow and where…, 2. Get the prompt and 3. Run, plus 1 more section
Calls git

What it does

Orca is an agent skill from VirtusLab/orca. Use when the user asks to run an Orca flow (e.g. "use orca to implement …"), or when delegating a well-defined implementation task to Orca's autonomous multi-agent flow — a headless plan-code-review CLI to hand a coding task to instead of implementing it yourself.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `.claude-plugin/plugin.json` and `README.md`).

It sits in Development, covering Code review. The repository describes itself as: Deterministic, AI-driven development flows. The licence is Apache-2.0.

When your agent uses it

The user asks to run an Orca flow (e.g
Tasks that involve Code review

Example prompts

“use orca to implement …”
“/orca”

Workflow steps

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

Choose the flow and where the run goes
Get the prompt
Run

What it can do on your machine

Read from SKILL.md and the folder at commit e5f1c41. 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:
- git
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

Orca loads about 1.4k tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 792 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~67
When it runs · the whole SKILL.md, loaded when a task matches: ~1.4k

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 VirtusLab/orca at commit e5f1c41, republished under its Apache-2.0 licence (© VirtusLab). 792 words, ~1,356 tokens.

Download SKILL.mdSave it as .claude/skills/orca/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.

name: orca
description: Use when the user asks to run an Orca flow (e.g. "use orca to implement …"), or when delegating a well-defined implementation task to Orca's autonomous multi-agent flow — a headless plan-code-review CLI to hand a coding task to instead of implementing it yourself.
argument-hint: [prompt]

Orca

Orca (orca CLI) runs a scripted plan → code → review flow autonomously, using its own coding/review agents. Delegate to it instead of implementing the task yourself when that fits better.

When to use

The user asks for it (/orca, "use an orca flow to …").
The task is well-defined and self-contained, with clear acceptance criteria (a feature or bugfix) — suited to an autonomous plan → code → review flow.
NOT for exploratory/interactive work, or edits small enough to just make yourself.

1. Choose the flow and where the run goes

Run orca list --json and git status --porcelain. If orca is not found, stop and point the user to https://github.com/VirtusLab/orca#getting-set-up.

Skip a question only if the user named the flow, or said where the run goes, explicitly. Otherwise ask both in one AskUserQuestion call:

Flow (header Flow). Put every flow in the question text, one per line as name — description, and say: pick one of the options, or type any other flow name under "Other". Options: implement.sc first, marked "(Recommended)", then up to 3 more, by origin: project, global, built-in.

Where the run goes (header Where). On a clean tree, the options are:

New branch (Recommended) — no flag.
Current branch — the flow commits onto it: --skip-branch.
New worktree — a separate checkout under .orca/worktrees/, this one stays untouched: --worktree.

With local (uncommitted or untracked) changes, list up to 10 changed files in the question text (then "+N more"), and offer:

New branch, keep local changes (Recommended) — for local files the flow should use, e.g. a spec: --keep-changes.
New branch, stash local changes — the run starts from the last commit: no flag.
Current branch, keep local changes: --skip-branch.
New worktree — local changes are NOT included, it starts from the last commit: --worktree.

Without --keep-changes or --skip-branch, a headless run stashes local changes. With either, if the flow fails before its first commit, kept changes to tracked files are lost.

If the user picks the worktree while there are local changes, ask with AskUserQuestion (header Changes): "Commit first" — so the worktree has them — or "Run without them". To commit: git add -A && git commit -m "<short summary>".

Don't pre-create a branch or worktree: the flow creates its own.

2. Get the prompt

Prompt given with the invocation (may be empty):

$ARGUMENTS

If empty, write one from the task discussed in the conversation. If there is none, ask for it in plain text, phrased after the chosen flow's description (e.g. an issue reference, a PR or branch to review, or a description of the change).

Orca's agents don't see this conversation: write the prompt so it stands on its own — goal, acceptance criteria, relevant files, and the path of any spec.

Show full SKILL.md (367 more words)Show less

3. Run

Capture the output in a temporary file, so the user can follow it (tail -f). Runs are long, so use two separate commands:

Create the file, and give the user its path before starting the run:
bash
```
mktemp -t orca-run.XXXXXX.log
```
Start the run with Bash run_in_background: true, using the literal path from step 1 and the flags chosen above. The prompt goes on stdin, so quotes and $ in it need no escaping:
bash
```
orca run <flow> <flags> > <path> 2>&1 <<'ORCA_PROMPT'
<prompt>
ORCA_PROMPT
echo "orca exit code: $?" >> <path>
```

When it finishes, read the file's tail to check the result; repeat its path in your final report.

Add these flags only if the user asks:

--verbose — print a stack trace if the flow aborts.
--honor-pin — run the flow's own pinned orca version instead of forcing this shell's.
--branch <name> — create the run's branch under this name. Refused with --skip-branch, and when the branch already exists.

After it runs

Exit codes: 0 success, 1 action failure, 2 usage error — orca run propagates the flow's own exit code. On success the flow has committed its work on a branch; report that branch (and any PR) to the user, and the worktree path for a --worktree run. The code flows end by opening a PR when the repository is on GitHub. A new-branch run then leaves you on the branch it started from — the work is on the feature branch behind the PR, not the one you are standing on.

Whenever the output has an "Open review findings" block, show it to the user verbatim. Say the review left nothing open only when a code flow exited 0 without one: a failed run may have stopped before printing it.

If a run is interrupted, re-run the same orca run command: flows are resumable and pick up from the last committed stage. A re-run stashes local changes, even with --keep-changes.

orca continue (list sessions with --list, resume one by selector — an id from --list, session name, or branch, e.g. orca continue <branch>) reattaches to a recorded harness session, but requires a real terminal and errors without one — don't invoke it headlessly; tell the user to run it themselves instead.

Files

SKILL.md and 2 other files in skills/orca of VirtusLab/orca.

SKILL.md
.claude-plugin/plugin.json
README.md

Open the folder on GitHubat commit e5f1c41

Compare with similar skills

Orca 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.

Orca compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Orca this skillVirtusLab/orca	180	—	~1.4k	Automated safety check: Pass	Apache-2.0	today
GitHub Review Iterationprisma/orm	48k	—	~2.2k	Automated safety check: Pass	Apache-2.0	today
Cherry Studio PR ReviewCherryHQ/cherry-studio	52k	—	~3.9k	Automated safety check: Pass	AGPL-3.0	today
Review Triage Phaseprisma/orm	48k	—	~995	Automated safety check: Pass	Apache-2.0	today
Deep Reviewdyad-sh/dyad	22k	—	~1.4k	Automated safety check: Pass	Custom licence	yesterday
PR Reviewjaemk/self_update	961	—	~1.5k	Automated safety check: Notes	MIT	1 mo ago

Similar skills

GitHub Review Iteration
prisma/orm
Official
Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.
48k GitHub stars~2.2k tokensUpdated today
DevelopmentAuto-check passed
Cherry Studio PR Review
CherryHQ/cherry-studio
Reviews Cherry Studio branches, pull requests, commits, files and docs against the project's own architecture, naming, API-boundary and UI rules, report-only by default.
52k GitHub stars~3.9k tokensUpdated today
DevelopmentAuto-check passed
Review Triage Phase
prisma/orm
Official
Runs the triage step of the review-framework loop: reads fetched PR review state, builds `review-actions.json`, validates it and renders `review-actions.md`.
48k GitHub stars~995 tokensUpdated today
DevelopmentAuto-check passed
Deep Review
dyad-sh/dyad
Deep multi-agent code review run locally — a fleet of parallel finder agents reviews the diff from independent angles, then adversarial verifier agents reproduce each finding before it is reported.
22k GitHub stars~1.4k tokensUpdated yesterday
DevelopmentAuto-check passed
PR Review
jaemk/self_update
Targeted, read-only review of a PR or checked-out branch. An agent skill from jaemk/self_update.
961 GitHub stars~1.5k tokensUpdated 1 mo ago
DevelopmentAuto-check: notes
Cursor Composer Task Delegate
Chachamaru127/claude-code-harness
Hands one implementation task to Cursor Composer in an isolated git worktree, then reviews its diff and cherry-picks the result into the main branch.
3.2k GitHub stars~4.4k tokensUpdated 3 days ago
DevelopmentAuto-check: notes

Questions about Orca

What does Orca do?

A skill your agent uses when the user asks to run an Orca flow (e.g. Orca is an agent skill from VirtusLab/orca.g.

When should I use Orca?

Orca fits situations like: the user asks to run an Orca flow (e.g; tasks that involve Code review.

How do I install Orca in Claude Code?

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

How do I install Orca in Codex?

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

Can I use Orca 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 VirtusLab/orca --skill orca -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/orca, .gemini/skills/orca, .github/skills/orca and .opencode/skills/orca in your project.

What does Orca need to run?

Going by SKILL.md and its folder, Orca needs the command-line tools its instructions call (git).

Does Orca 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 Orca 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 Orca use?

Orca is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Orca use?

About 1.4k tokens (SKILL.md is roughly 5.4k 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 Orca?

Skills that share tags, products or a category with Orca: GitHub Review Iteration (prisma/orm, 48k stars), Cherry Studio PR Review (CherryHQ/cherry-studio, 52k stars), Review Triage Phase (prisma/orm, 48k stars) and Deep Review (dyad-sh/dyad, 22k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Orca?

VirtusLab (a GitHub organization) maintains it in VirtusLab/orca, which has 180 GitHub stars. The repository was last updated on October 7, 2026.

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

Install Orca

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Orca

When to use

1. Choose the flow and where the run goes

2. Get the prompt

3. Run

After it runs

Files

Compare with similar skills

Similar skills

GitHub Review Iteration

Cherry Studio PR Review

Review Triage Phase

Deep Review

PR Review

Cursor Composer Task Delegate

Related

Questions about Orca