sakanaai
- 9 skills
- 0 followers
- 2 days ago last updated
- ▌ Review Paper · sakanaaiReview a generated paper draft and emit machine-readable revision feedback without editing the manuscript.
- ▌ Validate Paper · sakanaai bundleValidate grounded paper artifacts and compile LaTeX PDF with strict fail-fast checks.
- ▌ Retrieve References · sakanaai bundleRetrieve grounded BibTeX references from Semantic Scholar Graph API, OpenAlex, or Google Scholar (`scholarly`) and write references.bib plus provenance JSON for paper generation.
- ▌ Scientific Evidence · sakanaai bundleUse when: you start writing a scientific paper. Outputs: a repo-local `scientific-evidence/` bundle generated by the skill script, plus the conventions, schemas, and verification report needed for downstream evidence tracking and auditing.
- ▌ Generate Concept Figure · sakanaaiGenerate one reader-facing conceptual overview figure for paper generation as an editable draw.io diagram via the pinned Autoillustrate npm release, with a deterministic layout and an optional image-model restyle.
- ▌ Shinka Run · sakanaaiRun existing ShinkaEvolve tasks with the `shinka_run` CLI from a task directory (`evaluate.py` + `initial.<ext>`). Use when an agent needs to launch async evolution runs quickly with required `--results_dir`, generation count, and strict namespaced keyword overrides.
- ▌ Shinka Setup · sakanaai bundleCreate 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.
- ▌ Shinka Convert · sakanaai bundleConvert an existing codebase in the current working directory into a ShinkaEvolve task directory by snapshotting the relevant code, adding evolve blocks, and generating `evaluate.py` plus Shinka runner/config files. Use when the user wants to optimize existing code with Shinka instead of creating a brand-new task from a natural-language description.
- ▌ Shinka Inspect · sakanaai bundleLoad top-performing Shinka programs into agent context using `shinka.utils.load_programs_to_df`, and emit a compact Markdown bundle for iteration planning.