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 185 of 379
- View details
agents-generatorSkillAI & models
Lets your agent generate an AGENTS.md rules file by analyzing your codebase, with dry-run and backup options.
Ready to connect★ 295
- View details
spring-ai-integrationSkillAI & models
Helps your agent build and integrate LLM features like chat, embeddings, and RAG into Spring Boot apps.
Ready to connect★ 292
- View details
analyze-training-run-irisSkillAI & models
Lets your agent check the health of a training run, including progress, loss, throughput, and interruptions.
Ready to connect★ 296
- View details
crud-purge-below-gate-evalsSkillAI & models
Lets your agent delete incomplete evaluation job records that failed the quality gate.
Ready to connect★ 296
- View details
eval-agentic-cleanupSkillAI & models
Lets your agent audit a finished agentic eval and recommend fixes, without writing anything.
Ready to connect★ 296
- View details
eval-agentic-launchSkillAI & models
Lets your agent launch and verify agentic model evaluation jobs on a cluster, including model selection and tunnel setup.
Ready to connect★ 296
- View details
eval-standard-cleanupSkillAI & models
Lets your agent collect finished math eval job results and record the scores in a SCORES.md tracker.
Ready to connect★ 296
- View details
eval-standard-launchSkillAI & models
Lets your agent launch a fixed math benchmark eval suite (MATH-500, AIME24, gsm8k) on finished model checkpoints.
Ready to connect★ 296
- View details
rl-agentic-job-cleanupSkillAI & models
Lets your agent preserve and publish the best RL training checkpoint after a training job finishes or is cancelled.
Ready to connect★ 296
- View details
rl-agentic-launch-jupiterSkillAI & models
Lets your agent launch and relaunch agentic reinforcement learning training jobs on the Jupiter supercomputer.
Ready to connect★ 296
- View details
rl-standard-job-cleanupSkillAI & models
Lets your agent clean up and publish a finished standard SkyRL reinforcement learning training job on Leonardo.
Ready to connect★ 296
- View details
sft-launchSkillAI & models
Lets your agent launch supervised fine-tuning jobs on major HPC clusters using LLaMA-Factory or axolotl.
Ready to connect★ 296
- View details
supervisor-initSkillAI & models
Sets up a supervisor role that manages your ML experiments, subagents, and secrets from one place.
Ready to connect★ 296
- View details
utils-cleanup-stale-sandboxesSkillAI & models
Lets your agent delete old Daytona sandboxes across all three orgs in one pass.
Ready to connect★ 296
- View details
write-testsSkillAI & models
Lets your agent write tests in pytest style, using the write claude skill for behavior-focused coverage.
Ready to connect★ 296
- View details
emuloSkillAI & models
Lets your agent build a coding-style profile by mining your real local AI coding-session history.
Ready to connect★ 293
- View details
claudemap-runtimeSkillAI & models
Lets your agent turn a code repository into a live architecture map and use it to guide code walkthroughs.
Ready to connect★ 290
- View details
consultSkillAI & models
Lets your agent get second opinions on code, specs, or plans by querying AI models like Gemini, Codex, or Claude.
Ready to connect★ 288
- View details
forgeSkillAI & models
Lets your agent and you co-develop a project's context documents and code together.
Ready to connect★ 288
- View details
update-arch-docsSkillAI & models
Lets your agent update claude skill docs by auditing and pruning the project's architecture and lessons-learned files.
Ready to connect★ 288
- View details
bashkitSkillAI & models
Lets your agent run Bashkit scripts, use its CLI, and find Bashkit docs, examples, and packages.
Ready to connect★ 287
- View details
qa-find-bugs-mcpSkillAI & models
Lets your agent find bugs in the Beancount.io MCP endpoint by testing it live like a QA engineer.
★ 287
- View details
review-itSkillAI & models
Lets your agent review Claude skill code changes, compare branches against main, and run tests in parallel.
Ready to connect★ 287
- View details
to-issuesSkillAI & models
Lets your agent use the to issues skill to break a PRD into ready-to-work GitHub issues.
Ready to connect★ 287
- View details
agentsmd-optimizeSkillAI & models
Lets your agent audit and tidy AI coding-agent instruction files like AGENTS.md, CLAUDE.md, and skills.
Ready to connect★ 286
- View details
basecamp-connectSkillAI & models
Lets your agent set up and manage the local Basecamp connector that hands Basecamp requests to a coding agent.
Ready to connect★ 286
- View details
claude-code-reverseSkillAI & models
Lets your agent analyze local executables and app binaries you own to reverse engineer how they work.
Ready to connect★ 286
- View details
claudrabandSkillAI & models
Lets your agent run and automate Claude Code sessions, sending prompts and managing live session state.
Ready to connect★ 286
- View details
codex-retrospectiveSkillAI & models
Lets your agent use a codex claude skill that reviews its own recent work and updates AGENTS.md to improve it.
Ready to connect★ 286
- View details
harmonyos-appSkillAI & models
Lets your agent build and debug HarmonyOS apps using ArkTS, ArkUI, and the Stage model.
Ready to connect★ 286
Looking for something else?
AI & models is one category of skills on Ahel. Browse all skills, or open another category above.