ship

ship is a skill in evo-hq/evo, last changed 17 Jul 2026. It can run shell commands. Our pattern check flagged nothing at commit c70c04b on 27 Oct 2026.

Pattern check: nothing flagged · commit c70c04b · 27 Oct 2026

Install

From the author

Land the winning experiment from an evo run as a clean, mergeable change -- open a PR when the repo has a remote, otherwise merge into the working branch. Distills the best-scoring experiment down to the minimal diff that reproduces its behaviour, shaped for the qualities a maintainer merges on (scope discipline, test integrity, style adherence), then attaches an advisory mergeability report. Use when the user invokes /evo:ship, asks to land/merge/ship the best result, or wants to turn a finished optimization into a pull request.

Licence: Apache 2.0
Repo stars: 1.5k
Folder last changed: 17 Jul 2026 (opens in a new tab)
Publisher: evo-hq
Files: 1 file
Checked: c70c04b (opens in a new tab) · 27 Oct 2026

Install

Each tab says whether it installs commit c70c04b, the one we checked, or the latest version.

No tab for your agent? Use Any agent for OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity, and Claude Code for Cline. Kiro needs the folder copied by hand.

Pinned to commit c70c04b, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/evo-hq/evo.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin c70c04b4d2da2f2deb95d1d185b07d88d24f2ea7 &&
  git -C "$tmp" sparse-checkout set -- plugins/evo/skills/ship &&
  git -C "$tmp" checkout -q c70c04b4d2da2f2deb95d1d185b07d88d24f2ea7 &&
  mkdir -p .claude/skills &&
  mkdir .claude/skills/ship &&
  cp -R "$tmp"/plugins/evo/skills/ship/. .claude/skills/ship/ &&
  rm -rf "$tmp"

If Claude Code was already running and this created the skills folder, run /reload-skills.

Or install the evo plugin it ships in. Installs the latest version, not the one we checked. Installs everything in the plugin, including any hooks, MCP servers and scripts our check doesn't cover.

claude plugin marketplace add evo-hq/evo --scope project &&
  claude plugin install evo@evo-hq-evo --scope project

Claude Code docs

Pinned to commit c70c04b, the one we checked.

Skills in the Claude apps belong to your account rather than to a project.

Make ship.zip, with the skill folder at the top level:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/evo-hq/evo.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin c70c04b4d2da2f2deb95d1d185b07d88d24f2ea7 &&
  git -C "$tmp" sparse-checkout set -- plugins/evo/skills/ship &&
  git -C "$tmp" checkout -q c70c04b4d2da2f2deb95d1d185b07d88d24f2ea7 &&
  out="$(mktemp -d)" &&
  cp -R "$tmp"/plugins/evo/skills/ship "$out"/ship &&
  (cd "$out" && zip -qr - ship) > ship.zip &&
  rm -rf "$tmp" "$out"

In Claude, open Customize > Skills, select +, then + Create skill > Upload a skill, and choose ship.zip.

On Free, Pro and Max plans, turn on Code execution and file creation (Create and edit files in newer settings) under Settings > Capabilities.

Claude apps docs

Pinned to commit c70c04b, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/evo-hq/evo.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin c70c04b4d2da2f2deb95d1d185b07d88d24f2ea7 &&
  git -C "$tmp" sparse-checkout set -- plugins/evo/skills/ship &&
  git -C "$tmp" checkout -q c70c04b4d2da2f2deb95d1d185b07d88d24f2ea7 &&
  mkdir -p .agents/skills &&
  mkdir .agents/skills/ship &&
  cp -R "$tmp"/plugins/evo/skills/ship/. .agents/skills/ship/ &&
  rm -rf "$tmp"

Codex picks up new skills on its own; restart it if this one does not appear.

Codex docs

Pinned to commit c70c04b, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/evo-hq/evo.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin c70c04b4d2da2f2deb95d1d185b07d88d24f2ea7 &&
  git -C "$tmp" sparse-checkout set -- plugins/evo/skills/ship &&
  git -C "$tmp" checkout -q c70c04b4d2da2f2deb95d1d185b07d88d24f2ea7 &&
  mkdir -p .cursor/skills &&
  mkdir .cursor/skills/ship &&
  cp -R "$tmp"/plugins/evo/skills/ship/. .cursor/skills/ship/ &&
  rm -rf "$tmp"

Cursor docs

Pinned to commit c70c04b, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/evo-hq/evo.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin c70c04b4d2da2f2deb95d1d185b07d88d24f2ea7 &&
  git -C "$tmp" sparse-checkout set -- plugins/evo/skills/ship &&
  git -C "$tmp" checkout -q c70c04b4d2da2f2deb95d1d185b07d88d24f2ea7 &&
  mkdir -p .github/skills &&
  mkdir .github/skills/ship &&
  cp -R "$tmp"/plugins/evo/skills/ship/. .github/skills/ship/ &&
  rm -rf "$tmp"

In a running Copilot CLI session, run /skills reload.

Or install it with gh skill, which also installs the commit we checked. Needs GitHub CLI 2.90 or later.

gh skill install evo-hq/evo plugins/evo/skills/ship/SKILL.md@c70c04b4d2da2f2deb95d1d185b07d88d24f2ea7 --agent github-copilot --scope project

Copilot & VS Code docs

Pinned to commit c70c04b, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/evo-hq/evo.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin c70c04b4d2da2f2deb95d1d185b07d88d24f2ea7 &&
  git -C "$tmp" sparse-checkout set -- plugins/evo/skills/ship &&
  git -C "$tmp" checkout -q c70c04b4d2da2f2deb95d1d185b07d88d24f2ea7 &&
  mkdir -p .gemini/skills &&
  mkdir .gemini/skills/ship &&
  cp -R "$tmp"/plugins/evo/skills/ship/. .gemini/skills/ship/ &&
  rm -rf "$tmp"

In a running session, run /skills reload.

Or use Gemini CLI’s own installer. Installs the latest version, not the one we checked.

gemini skills install https://github.com/evo-hq/evo.git --path plugins/evo/skills/ship --scope workspace

Gemini CLI docs

Pinned to commit c70c04b, the one we checked.

Codex, Cursor, Copilot, VS Code, Gemini CLI, OpenCode, Goose, Amp and Zed all read .agents/skills; Claude Code and Kiro list only their own folders.

From your project's root folder:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/evo-hq/evo.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin c70c04b4d2da2f2deb95d1d185b07d88d24f2ea7 &&
  git -C "$tmp" sparse-checkout set -- plugins/evo/skills/ship &&
  git -C "$tmp" checkout -q c70c04b4d2da2f2deb95d1d185b07d88d24f2ea7 &&
  mkdir -p .agents/skills &&
  mkdir .agents/skills/ship &&
  cp -R "$tmp"/plugins/evo/skills/ship/. .agents/skills/ship/ &&
  rm -rf "$tmp"

Or use the skills CLI from skills.sh. Installs the latest version, not the one we checked. The skills CLI reports installs to skills.sh unless you set DISABLE_TELEMETRY=1.

npx skills@1.7.4 add evo-hq/evo --skill ship

Agent Skills docs

What it can touch

From the files and frontmatter at commit c70c04b. This is how much a skill can do, not whether it is risky.

What it can touch: Scripts or outside hosts

Runs shell commands
Its instructions or files give the agent commands to run on your computer.

Pattern check

Pattern check: nothing flagged · commit c70c04b · 27 Oct 2026

We checked every text file in this skill, at commit c70c04b on 27 Oct 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check works Report an incorrect finding

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

Agent Skills specPasses with warnings
The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.
- Warning
  Fields outside the spec: evo_version. Uploads to the Claude apps and API, and the spec's validator, reject the file; most agents ignore these fields. O1
  Fix: Delete them for a portable skill, or keep them if you only target the agents that read them.
- Note
  There is no license field, so readers can't tell whether they may reuse the skill. O2
  Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.
Claude CodePasses
Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.
- Note
  Claude Code ignores fields it doesn't know: evo_version. O1
  Fix: Check the spelling against Claude Code's field list, or delete them.
Claude apps & API uploadFails
Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.
- Error
  Upload and packaging fail on fields outside the spec: evo_version. O1
  Fix: Delete them, and keep your own data under metadata as text values.
- Note
  The description is 535 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4
  Fix: If the claude.ai upload refuses it, trim the description to 200 characters.
OpenAI (Codex & API)Passes with warnings
Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.
- Warning
  Fields outside the spec: evo_version. Codex ignores them; OpenAI doesn't say whether its upload accepts them. O1
  Fix: Delete them, or move your own data under metadata as text values.
VS Code & CopilotPasses
VS Code reads skills one folder below .github/skills, .claude/skills or .agents/skills and falls back to the folder name when the name is missing or differs; GitHub's Copilot docs require the exact name SKILL.md.
- Note
  VS Code ignores fields it doesn't support: evo_version. O1
  Fix: Delete them unless another agent you target reads them.

SKILL.md

Files

1 file

Path	Size
SKILL.md (opens in a new tab)	6.6 KB

More from evo-hq/evo

discover
evo-hq/evo
Initialize evo for the current repository by exploring the codebase, proposing unexplored optimization dimensions, constructing the benchmark inside a baseline worktree, and running the first experiment. Use when the user invokes /evo:discover, mentions setting up evo, wants to instrument a codebase for autonomous optimization, or asks to start a new evo run on a project.
- Touches credentials
- Runs shell commands
- +2 more
Pattern check: Nothing flagged
Apache 2.0 · 1.5k repo stars · Updated 17 Jul 2026
finetuning
evo-hq/evo
This skill should be used when picking or diagnosing a training move (SFT, LoRA, DPO/KTO/ORPO, RFT, GRPO/PPO/RLOO, RLHF), or when the user mentions fine-tuning, post-training, training recipe, reward design, or weight updates. Decision tree by reward shape, smoke-run gate, three failure diagnostics, five false-progress patterns. Provider recipes and I/O contract in references/.
- Runs shell commands
- Names web addresses
Pattern check: Nothing flagged
Apache 2.0 · 1.5k repo stars · Updated 17 Jul 2026
infra-setup
evo-hq/evo
Non-user-invocable provider/setup reference for evo backend switching, prerequisite checks, and auth/install guidance.
- Runs shell commands
- Reaches the network
Pattern check: Nothing flagged
Apache 2.0 · 1.5k repo stars · Updated 17 Jul 2026
optimize
evo-hq/evo
Drive structured autoresearch iteration after evo:discover and the baseline commit. Use when the user invokes /evo:optimize or asks to try ideas, try variants, run experiments, use available GPUs, improve the current best/frontier, continue an evo search, or compare candidate changes in an evo workspace. The orchestrator plans and spawns optimization subagents; candidate edits/runs belong to those subagents. Width is set via subagents=N (1 for serial workloads, larger for parallel); the loop's structural value applies at any width.
- Runs shell commands
- Bundles scripts
Pattern check: Nothing flagged
Apache 2.0 · 1.5k repo stars · Updated 17 Jul 2026
report
evo-hq/evo
Read-only evo run reporting. Use when the user invokes /evo:report, asks what happened overnight, asks what improved recently, asks for the best/frontier candidates, asks for a quick score chart without opening the dashboard, or wants the scatter plot in chat output. Never run benchmarks, gates, Slurm commands, evo run, or ad-hoc verification scripts for report requests.
- Runs shell commands
Pattern check: Nothing flagged
Apache 2.0 · 1.5k repo stars · Updated 17 Jul 2026
subagent
evo-hq/evo
Protocol that evo optimization subagents follow when dispatched from /optimize. Auto-loaded by spawned subagents via their host's skill loader. The orchestrator may also invoke this skill to understand the brief shape its dispatched subagents expect + what they're required to emit -- useful when writing briefs or debugging a subagent's behavior.
- Touches credentials
- Runs shell commands
Pattern check: Nothing flagged
Apache 2.0 · 1.5k repo stars · Updated 17 Jul 2026

Install

What it can touch

Pattern check

Format check

SKILL.md

Files

More from evo-hq/evo

discover

finetuning

infra-setup

optimize

report

subagent