shinka-setup

Create ShinkaEvolve task scaffolds from a target directory and task description, producing `evaluate.py` and `initial.<ext>` (multi-language). Use when asked to set up new ShinkaEvolve tasks, evaluation harnesses, or baseline programs for ShinkaEvolve.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%Weight 40%Scale 1-3

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

A well-structured, highly actionable skill body with executable templates and a validated workflow, slightly held back by a section restating known concepts and by reference paths that don't match the real bundle layout.

Suggestions

Trim the "Evolution Flow" section to only what is specific to ShinkaEvolve; drop generic evolutionary-algorithm steps Claude already knows.

Fix the optional-template references to point at the actual bundle paths (e.g. "See scripts/run_evo.py") instead of "skills/shinka-setup/scripts/..." so navigation resolves correctly.

Consider moving the "What is ShinkaEvolve?" overview's repo/paper links into a references file to keep SKILL.md focused on the setup procedure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable templates, but the "Evolution Flow" section re-explains evolutionary-algorithm basics ("Select parent(s)", "LLM proposes patch") that Claude already knows, adding padding.	2 / 3
Actionability	Provides complete, copy-paste-ready templates for initial.py and both evaluate.py paths, plus a concrete smoke-test command — fully executable guidance.	3 / 3
Workflow Clarity	A clear 7-step sequence with an explicit validation checkpoint (step 6: run smoke test, confirm metrics dict and correct.json) and feedback handling for failures.	3 / 3
Progressive Disclosure	Optional templates are correctly split into scripts/run_evo.py and scripts/shinka.yaml, but the in-body references use "skills/shinka-setup/scripts/..." paths that do not match the actual bundle location, weakening navigation signaling.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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

A concise, third-person description that clearly states both the capability (produce evaluate.py and initial.<ext> scaffolds) and explicit triggers for when to use it. It occupies a distinct niche with no overlap risk.

Dimension	Reasoning	Score
Specificity	Names concrete artifacts and actions — "Create ShinkaEvolve task scaffolds" that produce "`evaluate.py` and `initial.<ext>` (multi-language)" — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly answers both what (create scaffolds producing evaluate.py and initial.<ext>) and when via an explicit "Use when" trigger clause.	3 / 3
Trigger Term Quality	"Use when asked to set up new ShinkaEvolve tasks, evaluation harnesses, or baseline programs for ShinkaEvolve" covers natural phrasings a user would say, with good variation.	3 / 3
Distinctiveness Conflict Risk	Scoped tightly to ShinkaEvolve task setup with distinctive triggers, making conflict with unrelated skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: SakanaAI/ShinkaEvolve
Path: skills/shinka-setup/SKILL.md
Commit: b67a073

Reviewed: 12 days ago

Table of Contents

Discovery Implementation Validation

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.