Shinka Inspect

Trust Score 87/100

from shinkaevolve1,186

Extracts top-performing programs from a Shinka run and emits a compact Markdown bundle for iteration and analysis.

triggers:inspectshinkatop programscombined_scoreresults dirinspect_best_programs

GitHub SKILL.md

What it does

Shinka Inspect reads Shinka run artifacts (results dir / SQLite DB), ranks programs by combined_score, selects the top-k candidates (with correct-program fallback), and writes a single Markdown context bundle containing metadata, ranking tables, feedback, and code snippets. The artifact is designed to be loaded by coding agents for the next iteration.

When to use it

Use this skill after an evolutionary run when you need a quick way to surface the best programs for manual review or further automated mutation. It is intended for analysis and preparation before launching further runs or tuning. Avoid when you still need to scaffold or execute runs.

What's included

Scripts: includes a command-line script inspect_best_programs.py (see scripts/) to generate the markdown bundle.
References: none bundled.
Instructions: CLI arguments, typical workflow steps, and fallback behavior when no correct rows exist.

Compatible agents

Best used by coding-capable agents with file-system and python execution access (Copilot-like, local Codex, or CLI-capable agents).

Audit Summary

This skill extracts top-performing programs from a Shinka evolutionary optimization run and emits a Markdown context bundle for iteration planning. The script is well-written with clean structure, argparse CLI, and good error handling, but failed to run due to missing pandas dependency. The SKILL.md provides clear triggers, workflow steps, and CLI argument docs. Niche tool only useful for ShinkaEvolve users.

Watch Out

Requires pandas and shinka packages to be installed
Needs an existing Shinka results directory with SQLite DB
Script modifies sys.path as fallback for local development imports

Missing Dependencies

pandasshinka

Notes

Clean, well-structured skill with no security concerns. Main limitation is narrow audience — only relevant for ShinkaEvolve users. Code quality is solid despite the import failure (missing deps, not code bugs).

Information

Repository: shinkaevolve
Stars: 1,186

Trust Score

Overall87

Security95

Code Quality82

Architecture75

Usefulness45

Related Skills

Development Worktree

Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.

Readwise Reader Document Management

Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.

Bounty Hunter — Atlas

Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.

Junshi — Research Advisor

Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.

Full Stack Builder

End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.

ezBookkeeping API Tools

Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi

Feishu Voice Sender

Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.

Claw Bench

Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.

Back to Skills