CtrlK
BlogDocsLog inGet started
Tessl Logo

ship

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.

77

Quality

98%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

96%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a tightly written, fully actionable multi-stage workflow with strong validation checkpoints and explicit guardrails for its destructive operations. Progressive disclosure is good but the skill is a single self-contained file longer than the simple-skill threshold, leaving minor room for splitting detail out.

Suggestions

Consider extracting the Stage 4 mergeability-report field checklist into a reference file (e.g. report-template.md) to shorten SKILL.md toward the lean overview ideal and improve progressive disclosure.

The winner-selection state rules in Stage 1 are detailed enough to live in a reference; keeping only the headline rule inline would tighten the overview while preserving the firm guardrail.

DimensionReasoningScore

Conciseness

Lean and efficient throughout: it assumes Claude knows what a PR, git remote, and benchmark are, and every section (distillation axes, guardrails, report fields) earns its place without restating known concepts.

5 / 5

Actionability

Fully executable guidance with copy-paste-ready commands -- 'evo status', 'evo diff <root_id> <winner_id>', 'git remote -v', 'gh pr create', 'evo run <winner_id> --check' -- and precise, enumerated node-state selection rules for the common cases.

5 / 5

Workflow Clarity

Four explicitly sequenced stages with validation checkpoints and feedback loops: user go-before-proceeding gates, 'evo run --check' to confirm behaviour survived distillation, an explicit report-the-gap loop on failure, and a firm guardrails section covering the destructive push/merge/rewrite operations.

5 / 5

Progressive Disclosure

Well-organized into clear sections (Invocation, Stage 1-4, Guardrails) with no nested references, but at ~141 lines it exceeds the under-50-line simple-skill exception and is a single monolithic file with no external reference split, a minor organization gap versus the one-level-deep reference ideal.

4 / 5

Total

19

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, complete, and well-triggered, naming concrete actions and explicit natural-language triggers with synonyms and the slash-command invocation. It is distinct and unlikely to fire for the wrong skill.

DimensionReasoningScore

Specificity

Lists multiple concrete actions -- 'distills the best-scoring experiment down to the minimal diff', 'open a PR when the repo has a remote, otherwise merge into the working branch', 'attaches an advisory mergeability report' -- covering the skill's operations comprehensively.

5 / 5

Completeness

Explicitly answers both what (distill to minimal diff, land via PR or merge, attach mergeability report) and when (concrete trigger phrases naming /evo:ship and land/merge/ship intents).

5 / 5

Trigger Term Quality

Comprehensive natural triggers: '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' covers the invocation, natural verbs (land/merge/ship), and a paraphrased intent.

5 / 5

Distinctiveness Conflict Risk

Clear niche -- landing the winning experiment from an evo run -- tied to the /evo:ship trigger, with minimal overlap risk against unrelated skills.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
evo-hq/evo
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.