NeVibeCode · repository · 26 items
agent-loop-skills: a set by gaasher
The gaasher/agent-loop-skills repository on GitHub: 26 cards with a description and an install command. Inside: 25 skills and 1 plugin. They install into Claude Code, Codex and Cursor.
Install the whole set
/plugin marketplace add gaasher/Agent-Loop-SkillsAbout the repository
- GitHub
- gaasher/agent-loop-skills
- Stars
- ★ 185
- License
- MIT
- Source updated
- 2026-06-30
- In the catalog since
- 2026-11-01
literature-search skill literature-search searches academic papers across Semantic Scholar and arXiv, walks citation trees, and extracts snippets using only the Python standard library.
CX Codex +1
★ 185repo stars
data-analysis skill The data-analysis skill explores a dataset by testing hypotheses and writes up findings backed by reproducible numbers. Use it for open-ended discovery, not to diagnose a known failure.
CX Codex +1
★ 185repo stars
red-team skill red-team finds weaknesses in content filters, classifiers and APIs through adversarial stress-testing — generates attack inputs and builds a catalogue of failures.
CX Codex +1
★ 185repo stars
prompt-optimize skill prompt-optimize is a Claude Code skill that iteratively refines an existing prompt against your evaluation command, keeping only edits that improve the score.
CX Codex +1
★ 185repo stars
anomaly-investigation skill anomaly-investigation is a Claude Code skill that investigates a known spike, drop, or outlier by testing possible causes against data.
CX Codex +1
★ 185repo stars
power-analysis skill power-analysis is a Claude Code skill for sizing a two-group study and drafting its preregistration. It runs during planning, before data collection, for A/B tests, simple RCTs, and evaluations of two models or configurations.
CX Codex +1
★ 185repo stars
claim-verify skill claim-verify is a Claude Code skill that checks data-backed claims in draft reports against raw datasets. It recalculates metrics and stress-tests fragile conclusions.
CX Codex +1
★ 185repo stars
literature-survey skill literature-survey is a Claude Code skill that maps research sources against claims. It runs for questions that need a cited survey of agreement, disputes, and gaps.
CX Codex +1
★ 185repo stars
optimize-loop skill optimize-loop is a skill that runs an edit-measure-revert loop for code modules or SQL queries, keeping changes only when correctness holds and a cost metric falls.
CX Codex +1
★ 185repo stars
research-proposal skill Refines an existing research proposal through iterative literature checks, rubric-based scoring, and targeted revisions until it passes.
CX Codex +1
★ 185repo stars
research-question skill Turn a broad topic into a small set of research questions, then score and revise them. Use it when deciding what a study should ask.
CX Codex +1
★ 185repo stars
karpathy skill karpathy — a Claude Code skill that turns the agent into an autonomous ML researcher: it edits training code, runs it, and keeps only the changes that lower a single scalar metric. The loop runs until a human interrupts it.
CX Codex +1
★ 185repo stars
dueling-autoresearch skill dueling-autoresearch pits two distinct technical approaches against each other on a shared metric. It runs autonomous research loops until interrupted.
CX Codex +1
★ 185repo stars
plan-loop skill plan-loop is a Claude Code skill that turns engineering requests into task-by-task plans before coding starts. It is used to hand work to another engineer or a smaller model.
CX Codex +1
★ 185repo stars
purple-team skill purple-team runs attack and defense as one loop: red-team finds failure classes in a filter or prompt you own, blue-team patches it, a fresh pass checks the patch. Repeat until dry.
CX Codex +1
★ 185repo stars
hypothesis-gen skill hypothesis-gen generates testable research hypotheses and grounds them against published scientific literature using an agentic loop.
CX Codex +1
★ 185repo stars
tournament-autoresearch skill The tournament-autoresearch skill pits architecture proposals against each other before an ML experiment runs. It suits projects where you want an agent to choose one idea and learn from its measured result.
CX Codex +1
★ 185repo stars
swe-loop skill swe-loop is a Claude Code skill that breaks coding requests into tasks, has an Engineer implement them, and QA verify tests and quality.
CX Codex +1
★ 185repo stars
scientific-writer skill scientific-writer refines scientific drafts through iterative critique and peer review. Multiple specialist judges evaluate prose, data, and figures until quality clears the bar.
CX Codex +1
★ 185repo stars
alpha-evolve skill The alpha-evolve skill explores many model-code variants in parallel, scores them through training runs, and keeps diverse strong candidates. Use it for evolutionary search instead of sequential edits.
CX Codex +1
★ 185repo stars
blue-team skill blue-team runs a fix loop over a concrete list of failures: one root-cause class per iteration, a revert on any regression, and a pull request at the end.
CX Codex +1
★ 185repo stars
scientific-figure skill Builds publication-ready scientific figures from data or prompts through an adversarial generator-critic loop evaluated against a strict rubric.
CX Codex +1
★ 185repo stars
tabular-cleanup skill The tabular-cleanup skill cleans messy CSV, TSV, Parquet, Excel, or JSON tables against an agreed data contract. Use it for iterative cleanup with explicit checks and a change log.
CX Codex +1
★ 185repo stars
exploratory-autoresearch skill exploratory-autoresearch runs an autonomous ML experiment loop that samples wildly different designs first, then switches to picking one move per round.
CX Codex +1
★ 185repo stars
ml-autoresearch skill ml-autoresearch drives an autonomous machine learning loop where model diagnostics and research papers shape each code iteration.
CX Codex +1
★ 185repo stars
agent-loops plugin Run agent loops that propose a change, score the result, and keep or revert it. Useful when your task has a measurable feedback signal.
★ 185repo stars