Tessl • The management layer for AI agent skills

SkillPublic

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

82%

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

93%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 an efficient, highly actionable overview with clean structure and a single well-signaled bundle script. The only gap is an explicit verification checkpoint for the generated output.

Dimension	Reasoning	Score
Conciseness	Lean, well-sectioned body that assumes Claude's competence and never explains what Shinka or a DataFrame is; every section earns its place.	5 / 5
Actionability	Provides copy-paste-ready bash invocations with real script paths, flags, and defaults, plus a CLI Arguments section covering the common cases.	5 / 5
Workflow Clarity	Clear four-step sequence with an artifact-existence checkpoint in step 1, but lacks an explicit verification step confirming the generated markdown bundle before loading it into context.	4 / 5
Progressive Disclosure	A compact single-purpose overview that signals its one bundle reference (the inspect script) inline via executable commands; structure is clean and one level deep.	5 / 5
	Total	19 / 20 Passed

Description

62%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 and clearly distinct within the Shinka niche, but it omits any explicit 'Use when...' trigger guidance and relies on jargon over natural user phrases. Adding a trigger clause would lift completeness and trigger-term quality.

Suggestions

Append a 'Use when...' clause naming the natural trigger (e.g., 'Use when inspecting top Shinka programs before the next evolution batch').

Soften jargon by pairing 'load_programs_to_df' with a plain-language verb a user would say, like 'review' or 'inspect'.

Add a synonym or file cue (e.g., 'results directory', 'programs.sqlite') so users referencing run artifacts match this skill.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ('Load top-performing Shinka programs into agent context', 'emit a compact Markdown bundle') plus the specific function used, with only minor coverage gaps.	4 / 5
Completeness	Has a clear 'what' (load programs, emit markdown bundle) but no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Contains the natural brand keyword 'Shinka programs' and 'top-performing', but leans on technical jargon ('load_programs_to_df', 'iteration planning') and lacks common synonyms a user would naturally say.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear niche tied to the Shinka-specific run inspection task with distinct triggers, making conflict with unrelated skills minimal.	5 / 5
	Total	15 / 20 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
Revision: 8adc053

Reviewed: 2 months ago

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.

shinka-inspect

Table of Contents

Is this your skill?