a2a-gateway
Agent-to-Agent (A2A) protocol gateway reference. JSON-RPC 2.0 peer-to-peer agent communication. (/a2a-gateway, a2a, agent protocol)
838 repo starsObserved in 1 repos
Agent Building
Agent Building skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
finetuning-technique
Selects a fine-tuning technique (SFT, DPO, RLVR, or RLAIF) for the user's use case and validates it against the selected model's available recipes. Use when the user has decided to finetune and needs to choose a technique, or when the technique needs to be validated against a model. Requires a base model to already be selected (via model-selection skill).
834 repo starsObserved in 2 repos
Agent Building
human-auth-delegation
Overview of how Human Phone authorization and delegation artifacts work. For specific capability handling, see the individual human-auth-* skills.
834 repo starsObserved in 1 repos
Agent Building
generate-subsystem-skills
Generate specialized skills for each subsystem in the monorepo. Creates shared language skills and subsystem-specific checklists for high-quality AI code generation.
833 repo starsObserved in 3 repos
Agent Building
rag-skills
RAG-specific best practices for LlamaIndex, ChromaDB, and Celery workers. Covers ingestion, retrieval, embeddings, and performance.
833 repo starsObserved in 3 repos
Agent Building
improve-add-skill
Improve the repo-local add skill from reviewed Neovim plugin categorization corrections. Use when a correction commit, PR review result, diff, or artifact such as a `teach:` commit shows that `$add` placed, excluded, or reasoned about plugins incorrectly and the reusable lesson should be folded back into `.codex/skills/add/**`.
823 repo starsObserved in 1 repos
Agent Building
implement-ag-playbook
Implement a playbook from its PROMPT specification files. Supports both single-framework (PROMPT-REACT.md, etc.) and 3-framework (PROMPT-3-FRAMEWORKS.md) modes.
820 repo starsObserved in 3 repos
Agent Building
creating-a-coral-task
Author a new CORAL task — the three pieces that must line up (`task.yaml`, `seed/`, a packaged `grader/`), the `coral init` → `coral validate` → smoke-test loop, and how to pick a grader pattern (stdout float, test pass-rate, ratio-vs-baseline, multi-metric, or an LLM rubric judge). Use whenever the user wants to create a CORAL task, write or wire a grader, port a benchmark into CORAL, score open-ended outputs (reports/memos) with a judge, or debug a grader that crashes on the seed / ranks the leaderboard backwards / leaks the answer key. Deep references for the TaskGrader API, grader patterns, rubric judges, and the full task.yaml schema live alongside this skill.
817 repo starsObserved in 1 repos
Agent Building