AI & models skills.
11,362 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
11,362 results · page 210 of 379
- View details
mat-grand-canonical-mcSkillAI & models
Lets your agent run Grand Canonical Monte Carlo simulations to map composition-temperature phase diagrams.
Ready to connect★ 174
- View details
ml-autoresearchSkillAI & models
Lets your agent run ML training loops like an autoresearch Claude skill, analysing results before the next change.
Ready to connect★ 174
- View details
ml-committee-uncertaintySkillAI & models
Lets your agent measure how uncertain an ML potential's predictions are and flag structures needing verification.
Ready to connect★ 174
- View details
ml-foundation-potentialsSkillAI & models
Helps your agent pick the right machine-learning atom model for a materials simulation.
Ready to connect★ 174
- View details
ml-generative-aditSkillAI & models
Lets your agent generate new crystal structures and molecules using an all-atom diffusion model.
Ready to connect★ 174
- View details
ml-generative-mattergenSkillAI & models
Lets your agent generate new inorganic material structures using a diffusion-based generative model.
Ready to connect★ 174
- View details
ml-mlip-nvalchemiSkillAI & models
Lets your agent run fast batched simulations of materials, including relaxations and molecular dynamics, on GPU.
Ready to connect★ 174
- View details
ml-mlip-speedSkillAI & models
Lets your agent look up benchmark results comparing how fast different machine learning interatomic potentials run.
Ready to connect★ 174
- View details
ml-property-predict-scdSkillAI & models
Lets your agent train a model to predict properties of molecules or periodic materials.
Ready to connect★ 174
- View details
plan-loopSkillAI & models
Lets your agent turn a coding request into a detailed, executable plan before any code is written.
Ready to connect★ 174
- View details
power-analysisSkillAI & models
Use when the user is planning a two-arm comparison (an A/B test, a simple RCT, a behavioral study, or a two-model/two-config evaluation) and needs to size it and preregister it before collecting data — finding the per-group sample size that hits target statistical power for the smallest effect worth
Ready to connect★ 174
- View details
prompt-optimizeSkillAI & models
Lets your agent improve a prompt claude skill can score, making one targeted edit per iteration against your evaluation.
Ready to connect★ 174
- View details
purple-teamSkillAI & models
Lets your agent test and improve its own safety guardrails by simulating attacks and fixes in a loop.
Ready to connect★ 174
- View details
research-proposalSkillAI & models
Lets your agent strengthen a research proposal through repeated grading, using the research claude skill.
Ready to connect★ 174
- View details
research-questionSkillAI & models
Turns a vague topic into a few strong research questions using a research Claude skill that scores each idea.
Ready to connect★ 174
- View details
rulphSkillAI & models
Lets your agent score its work against a rubric you build together, then improve it until it hits your target.
Ready to connect★ 174
- View details
scientific-figureSkillAI & models
Lets your agent turn scientific data into a polished figure by drafting it and having a critic refine it.
Ready to connect★ 174
- View details
tournament-autoresearchSkillAI & models
Runs a tournament where research subagents propose ML model changes, a judge critiques them, and picks the best one.
Ready to connect★ 174
- View details
tribunalSkillAI & models
Lets your agent review a plan from three perspectives—risk, value, and feasibility—and combine them into one verdict.
Ready to connect★ 174
- View details
architectureSkillAI & models
Gives your agent access to the architecture skill that documents Lagune's repo layout, boundaries, and design decisions.
Ready to connect★ 173
- View details
novel-to-script-teamSkillAI & models
A complete multi-agent, multi-skill novel adaptation project. The open-source version depends at runtime on agents/skills/references; the original sources are not distributed with the repository.
Ready to connect★ 173
- View details
seedance-prompt-review-skillSkillAI & models
Seedance prompt review skill. Used to review the Seedance 2.0 dynamic prompts produced by the storyboard artist in phase three, ensuring compliance, camera-movement soundness, and narrative coherence through item-by-item comparison, mental rehearsal, and a scoring system.
Ready to connect★ 173
- View details
white-bearSkillAI & models
Lets your agent audit text for unnecessary mentions of competing targets and other negative framing.
Ready to connect★ 173
- View details
zero-shotSkillAI & models
Lets your agent audit text for over-reliance on few-shot examples instead of stated principles.
Ready to connect★ 173
- View details
ios-accessibilitySkillAI & models
Expert guidance on iOS accessibility best practices, patterns, and implementation. Use when developers mention: (1) iOS accessibility, VoiceOver, Dynamic Type, or assistive technologies, (2) accessibility labels, traits, hints, or values, (3) automated accessibility testing, auditing, or manual test
Ready to connect★ 171
- View details
comment-judgeSkillAI & models
LLM-as-a-judge rubric for code comments (forbidden, false, stale, narration, noise, keep). Loaded in-process by code-reviewer, dotnet-cop and angular-cop to judge every added or changed comment in a review; used by the comment-judge agent for per-module comment purges. Use when judging whether comme
Ready to connect★ 171
- View details
config-syncSkillAI & models
Lets your agent keep agent, rule, hook, and prompt settings in sync between a config repo and live tool directories.
Ready to connect★ 171
- View details
harness-paritySkillAI & models
Keeps your .claude and .opencode config files in sync by copying any agent, skill, or rule change to the other folder.
Ready to connect★ 171
- View details
strategic-compactSkillAI & models
Lets your agent save its work state so long autonomous tasks survive memory compaction without asking you.
Ready to connect★ 171
- View details
codebase-intelSkillAI & models
Lets your agent answer questions about your codebase's structure, logic, risk, and dependencies before making changes.
Ready to connect★ 170
Looking for something else?
AI & models is one category of skills on Ahel. Browse all skills, or open another category above.