shinka-inspect

Load top-performing Shinka programs into agent context using `shinka.utils.load_programs_to_df`, and emit a compact Markdown bundle for iteration planning.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

100%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.

The body is tight, executable, and well-structured, with a clear workflow and a single verified script reference. It is a strong, self-contained skill document.

Dimension	Reasoning	Score
Conciseness	Lean bullet structure with executable commands and no padding explaining concepts Claude already knows; every section earns its place.	3 / 3
Actionability	Provides copy-paste-ready bash invocations with real paths and flags, plus a concrete CLI Arguments table — fully executable guidance.	3 / 3
Workflow Clarity	Sequences a confirm-artifacts pre-check (ls -la) into a single unambiguous script invocation; the operation is read-only on run artifacts, so the destructive/batch validation cap does not apply.	3 / 3
Progressive Disclosure	Well-organized sections with a single clearly-signaled, one-level-deep reference to the real bundle file scripts/inspect_best_programs.py; no nested references.	3 / 3
	Total	12 / 12 Passed

Description

67%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.

The description is concrete and distinctive, but omits explicit trigger guidance and leans on technical jargon over natural user terms. Adding a "Use when…" clause would lift completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. "Use when reviewing top Shinka programs before the next evolution batch, or when preparing a compact context bundle for mutation planning."

Soften technical jargon by adding natural user phrasings alongside the API name, e.g. "inspect best Shinka programs" / "top Shinka runs".

Mirror the body's "Do not use" guidance briefly in the description to sharpen distinctiveness from shinka-setup and shinka-run.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Load top-performing Shinka programs into agent context" and "emit a compact Markdown bundle for iteration planning" — rather than vague language.	3 / 3
Completeness	Clearly states what the skill does but provides no "Use when…" trigger guidance, so the "when" is only implied rather than explicit.	2 / 3
Trigger Term Quality	Includes some relevant keywords ("Shinka programs", "iteration planning") but leans technical (load_programs_to_df, "Markdown bundle") and lacks common natural-user phrasings.	2 / 3
Distinctiveness Conflict Risk	The Shinka-specific niche ("top-performing Shinka programs") is distinctive and unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 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-inspect/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.