AI & models skills.
11,371 AI & models skills, including triage, domain-modeling and code-review, are listed on Ahel today. Each one has a page of its own that says what it does and whether Ahel can serve it in Claude, Claude Code, ChatGPT, Codex and Cursor.
Category: AI & models
11,371 results · page 27 of 380
- View details
pua-teardown-allSkillAI & models
Lets your agent run the pua teardown-all command in Codex the same way it works in Claude Code.
Ready to connect★ 20k
- View details
pua-yesSkillAI & models
Lets your agent run the Codex yes command using the Claude Code /pua:yes style alias.
Ready to connect★ 20k
- View details
shotSkillAI & models
Lets your agent inject a compact evidence-first prompt style into sub-agents or short sessions.
Ready to connect★ 20k
- View details
skill-inspectorSkillAI & models
Lets your agent review AI skill files for safety and trustworthiness before installing them.
Ready to connect★ 20k
- View details
context-engineering-collectionSkillAI & models
Gives your agent a set of skills for managing context and building reliable multi-agent systems.
Ready to connect★ 18k
- View details
ai-chatSkillAI & models
Guides your agent to improve Windmill's AI chat, covering tools, prompts, and context-window management.
Ready to connect★ 18k
- View details
local-review-codexSkillAI & models
Lets your agent run the same CI pull request code review on your local unpushed work before you push.
Ready to connect★ 18k
- View details
ablation-plannerSkillAI & models
Lets your agent plan ablation studies for a research paper after the main results are confirmed.
Ready to connect★ 17k
- View details
auto-paper-improvement-loopSkillAI & models
Lets your agent review a generated paper, apply fixes, and recompile it over two improvement rounds.
Ready to connect★ 17k
- View details
auto-review-loopSkillAI & models
Runs automatic review-and-fix rounds on your writing or code until an independent AI reviewer scores it good enough.
Ready to connect★ 17k
- View details
auto-review-loop-llmSkillAI & models
Lets your agent run an autonomous research review loop using any OpenAI-compatible LLM API.
Ready to connect★ 17k
- View details
auto-review-loop-minimaxSkillAI & models
Lets your agent run repeated rounds of research review using the MiniMax AI model.
Ready to connect★ 17k
- View details
citation-auditSkillAI & models
Lets your agent check that every citation in a paper is real, correctly attributed, and used in the right context.
Ready to connect★ 17k
- View details
claims-draftingSkillAI & models
Lets your agent draft patent claims for an invention in US, EP, or Chinese formats.
Ready to connect★ 17k
- View details
embodiment-descriptionSkillAI & models
Lets your agent write detailed embodiment sections for patent specifications from your invention disclosure and claims.
Ready to connect★ 17k
- View details
experiment-auditSkillAI & models
Lets your agent have a second AI model independently audit experiment results for faked scores or missing evidence.
Ready to connect★ 17k
- View details
experiment-planSkillAI & models
Turns a research proposal into an experiment plan with claims, ablations, run order, and compute budget.
Ready to connect★ 17k
- View details
experiment-queueSkillAI & models
Lets your agent queue and run large batches of ML experiments on remote GPU servers, retrying failures automatically.
Ready to connect★ 17k
- View details
figure-descriptionSkillAI & models
Lets your agent write formal patent drawing descriptions with reference numerals from your figure files.
Ready to connect★ 17k
- View details
figure-specSkillAI & models
Lets your agent turn structured JSON into editable SVG architecture, workflow, and pipeline diagrams.
Ready to connect★ 17k
- View details
grant-proposalSkillAI & models
Lets your agent draft structured grant proposals for funders like NSF, ERC, and KAKENHI from your research ideas.
Ready to connect★ 17k
- View details
idea-creatorSkillAI & models
Lets your agent generate and rank research ideas for a broad topic you give it.
Ready to connect★ 17k
- View details
idea-discoverySkillAI & models
Lets your agent turn a broad research direction into ranked, checked research ideas with a proposal and experiment plan.
Ready to connect★ 17k
- View details
idea-discovery-robotSkillAI & models
Lets your agent survey robotics research and turn a broad direction into a few grounded, testable research ideas.
Ready to connect★ 17k
- View details
integrity-forensicsSkillAI & models
Lets your agent run a forensic integrity sweep on a research paper and turn the findings into a policy verdict.
Ready to connect★ 17k
- View details
interview-cheatsheetSkillAI & models
Lets your agent create a detailed Chinese ML/LLM interview prep sheet with formulas, PyTorch code, and sample questions.
Ready to connect★ 17k
- View details
invention-structuringSkillAI & models
Lets your agent turn a rough invention idea into a formal patent-ready invention disclosure document.
Ready to connect★ 17k
- View details
kill-argumentSkillAI & models
Lets your agent stress-test a paper by writing the strongest rejection argument, then defending the paper point by point.
Ready to connect★ 17k
- View details
meta-applySkillAI & models
Lets your agent apply approved self-improvement patches to its skill corpus after review and human approval.
Ready to connect★ 17k
- View details
novelty-checkSkillAI & models
Lets your agent check whether a research idea is new by comparing it against recent papers.
Ready to connect★ 17k
Looking for something else?
AI & models is one category of skills on Ahel. Browse all skills, or open another category above.