Skills for Real Engineers. Straight from my .agents directory.
ship
Agent skill fromevo-hq/evo
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.
How to install ship
npx skills add evo-hq/evo# or add only this skill to Claude Code: copy the folder
plugins/evo/skills/ship/
# into
~/.claude/skills/ship/ (all projects)
.claude/skills/ship/ (one project)
1# Ship23Turn a finished evo run into a change a maintainer would merge.45The optimize loop leaves a tree of committed experiments. The winning worktree6diff is not mergeable as-is: it carries debug prints, search-process churn,7over-broad edits, and sometimes a test that was relaxed to clear a gate. Shipping8is the step that re-derives the *minimal clean change* reproducing the winning9behaviour, lands it the way the repo expects (PR or merge), and reports how10mergeable it is.1112Correctness is the floor, not the goal. The score says the behaviour works; this13skill decides whether the *diff* is fit to merge.1415## Invocation1617```bash18/evo:ship # ship the auto-selected winner19/evo:ship exp_0042 # ship a specific experiment instead20```2122## Stage 1 -- Select the winner2324Pick the experiment to ship, then confirm it with the user before touching their25tree.2627```bash28evo status # current best valid score + counts29evo report # top valid experiments table + score chart30```3132- The default winner is the highest-scoring valid result in the graph history,33 not the frontier. `evo frontier` is for choosing where to branch next; it can34 exclude an exhausted branch whose score is still the right thing to ship. An35 explicit `exp_id` argument overrides auto-selection.36- A shippable winner must be valid: `committed`, or `pruned` with37 `prune_kind=exhausted`, with a commit and score, no `gate_result === false`,38…
Excerpt shown under the repository's Apache-2.0 license.
More skills in evo
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
