ShinkaEvolve is a framework that combines large language models with evolutionary algorithms to improve scientific programs through repeated code variation and evaluation. Researchers and developers use it to explore and optimize code for scientific discovery. Its catalogue skills guide coding agents through setup, conversion, evolution, and result inspection.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add SakanaAI/ShinkaEvolve --skill shinka-convertgit clone --depth 1 https://github.com/SakanaAI/ShinkaEvolveWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sakanaai/shinkaevolve/shinka-convert)<a href="https://agentmods.dev/skills/sakanaai/shinkaevolve/shinka-convert"><img src="https://agentmods.dev/badge/skills/sakanaai/shinkaevolve/shinka-convert/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sakanaai/shinkaevolve/shinka-convert"><img src="https://agentmods.dev/badge/skills/sakanaai/shinkaevolve/shinka-convert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 59 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00072 | $0.01453 |
| Opus 5 | $0.00036 | $0.00727 |
| Sonnet 5 | $0.00014 | $0.00291 |
| Haiku 4.5 | $0.00007 | $0.00145 |
Grade A, and why
shinka-convert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shinka Convert Skill
Use this skill to turn an existing project into a Shinka-ready task.
This is the alternative starting point to shinka-setup:
shinka-setup: new task from natural-language task descriptionshinka-convert: existing codebase to Shinka task conversion
After conversion, the user should still be able to use shinka-run.
When to Use
Invoke this skill when the user:
- Wants to optimize an existing script or repo with Shinka/ShinkaEvolve
- Mentions adapting current code to Shinka output signatures,
metrics.json,correct.json, orEVOLVE-BLOCKmarkers - Wants a sidecar Shinka task generated from the current working directory
Do not use this skill when:
- The user wants a brand-new task scaffold from only a natural-language description
evaluate.pyandinitial.<ext>already exist and the user only wants to launch evolution; useshinka-run
User Inputs
Start from freeform instructions, then ask follow-ups only if high-impact details are missing.
Collect:
- What behavior or file/function to optimize
- Score direction and main metric
- Constraints: correctness, runtime, memory, determinism, style, allowed edits
- Whether original source must remain untouched
- Any required data/assets/dependencies
Default Output
Generate a sidecar task directory at ./shinka_task/ unless the user requests another path.
The task directory should contain:
evaluate.pyrun_evo.pyshinka.yamlinitial.<ext>- A copied snapshot of the minimal runnable source subtree needed for evaluation
Do not edit the original source tree unless the user explicitly requests in-place conversion.
Workflow
- Inspect the current working directory.
- Identify language, entrypoints, package/module layout, dependencies, and current outputs.
- Prefer concrete evidence from the code over guesses.
- Infer the evolvable region from the user's instructions.
- If ambiguous, ask targeted follow-ups.
- Keep the mutable region as small as practical.
- Choose the minimal runnable snapshot scope.
- Copy only the source subtree needed to execute the task in isolation.
- Avoid repo-wide snapshots unless imports/runtime make that necessary.
- Create the sidecar task directory.
- Default:
./shinka_task/ - Avoid overwriting an existing task dir without consent.
- Default:
- Rewrite the snapshot into a stable Shinka contract.
- Preserve original behavior outside the evolvable region.
- Keep CLI behavior intact where practical.
- Ensure the evolvable candidate entry file is named
initial.<ext>soshinka-runcan detect it. - Add tight
EVOLVE-BLOCK-START/EVOLVE-BLOCK-ENDmarkers.
- Generate the evaluator path.
- Python: prefer exposing
run_experiment(...)and userun_shinka_eval. - Non-Python: use
subprocessand writemetrics.jsonpluscorrect.json.
- Python: prefer exposing
- Generate
run_evo.pyandshinka.yaml.- Ensure
init_program_pathandlanguagematch the candidate file. - Keep the output directly compatible with
shinka-run.
- Ensure
- Smoke test before handoff.
- Run
python evaluate.py --program_path <initial file> --results_dir /tmp/shinka_convert_smoke - Confirm evaluator runs without exceptions.
- Confirm required metrics/correctness outputs are written.
- Run
- Ask the user for the next step.
- Either run evolution manually
- Or use the
shinka-runskill
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 171 lines · 72 tokens per session scan A 88daa14d50f5
shinka-convert is a skill published in the GitHub repository SakanaAI/ShinkaEvolve (1,379 stars, last pushed 20d ago), licensed Apache-2.0. It adds 72 tokens to every session and 1,453 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.