Skip to content
OpenAgentSkill
Browsing is open · Catalog captured 2026-11-21 · Automatic updates and account services are paused.

All skills

38,472 Skills

Search uses this published catalog; rankings and counts are snapshots.

Search & research

alpha-evolve

gaasher

Use when the user wants to evolve an ML model/program through population-based search rather than a single sequential refine loop — a generational evolution where parallel proposers each apply one small SEARCH/REPLACE diff to a parent, scored by a cascade-evaluated training run,

Price unconfirmed
Data & analytics

anomaly-investigation

gaasher

Use when the user has a known, already-observed anomaly in their data — a metric spike or drop, an outlier, an unexpected number — and wants its root cause diagnosed, not guessed. Forms a slate of candidate causes, tests each against the data, and eliminates the ones the data ref

Price unconfirmed
Data & analytics

claim-verify

gaasher

Use when the user has a results draft or a set of data-backed claims and wants each one adversarially verified against the underlying dataset before publishing — a pre-publication red-team of the findings. Extracts the discrete checkable claims from the draft, reproduces each cla

Price unconfirmed
Data & analytics

data-analysis

gaasher

Use when the user wants an iterative, self-checking exploratory analysis of a dataset — surfacing findings that are each verified by re-running the computation, not asserted. Proposes one specific hypothesis at a time, writes and runs analysis code to test it, and records the fin

Price unconfirmed
Search & research

dueling-autoresearch

gaasher

Use when the user wants two approaches raced head-to-head on a single shared metric — e.g. a classical/algorithmic lane vs an ML/learned lane, or any two strategies for the same task. Each lane runs its own analysis-first research loop confined to its lane, the lanes share a scor

Price unconfirmed
Search & research

exploratory-autoresearch

gaasher

Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early

Price unconfirmed
Search & research

karpathy

gaasher

Use when the user wants the LLM to do its own ML research: a fully-autonomous loop that hacks the training code, runs it, and keeps changes that lower a single scalar metric (e.g. val_bpb). One agent proposes one change at a time, runs training in the user's env, keeps it only if

Price unconfirmed
Search & research

literature-survey

gaasher

Use when the user wants a structured, saturating literature survey on a question — not a one-shot summary, but an evidence/contradiction matrix (sources × claims) built by iterative search until coverage stops growing. Each round expands the search (new sub-topic queries plus cit

Price unconfirmed
Search & research

ml-autoresearch

gaasher

Use when the user wants an autonomous ML research loop that does more than blindly try changes. After every training run the agent analyses what actually happened inside the model — gradients, activations, embeddings, errors, data — and grounds the next change in that evidence. A

Price unconfirmed
AI & knowledge

prompt-optimize

gaasher

Use when the user has a prompt that feeds a system they can already score, and wants that prompt automatically improved to raise the score against their own evaluation command. Makes one targeted quality edit per iteration — clarity, context, specificity, structure, examples, dec

Price unconfirmed
Development

purple-team

gaasher

Use when the user wants to automatically harden a guardrail, classifier, content filter, prompt, or API they own by running attack and defense together as a closed loop, not just one or the other. It orchestrates the red-team and blue-team loops as independent agents: red finds d

Price unconfirmed
Search & research

research-question

gaasher

Use when the user has a vague topic or area of interest and wants it sharpened into a few strong, novel, feasible research questions. Drafts candidate questions, scores each against a fixed rubric (Specific, Answerable, Novel, Feasible, Significant) with a light literature/web no

Price unconfirmed
Development

specsfy-02-backlog

promovaweb

Use quando o usuário quer transformar uma captura de `specs/inbox/`, uma oportunidade, um problema ou um item existente em backlog pronto para especificação, inclusive por transição automática. Pesquisa duplicatas e referências, cria ou atualiza `specs/backlog/`, faz perguntas ad

Price unconfirmed

Catalog captured:2026-11-21