bagbag16/long-running-agent-skills
Two Codex skills for stable long-running AI collaboration: agent-drift-guard (adg) and context-continuity-anchor (cca).
Two Codex skills for stable long-running AI collaboration: agent-drift-guard (adg) and context-continuity-anchor (cca).
npx skills add bagbag16/long-running-agent-skillsTwo Codex skills for stable long-running AI collaboration: agent-drift-guard (adg) and context-continuity-anchor (cca).
Provides unit test, integration test, and mock AI patterns for LangChain4j applications. Creates mock LLM responses, tests retrieval chains, validates RAG workflows, and implements Testcontainers-based integration tests for Java AI services. Use when unit testing AI services, integration testing LangChain4j components, mocking AI models, or testing LLM-based Java applications.
A Claude Code skill that logs sessions as structured diary entries in an Obsidian vault
Team-ready Claude Code skill pack: 14 integrations (Rails+RN+Firebase+ADO+Trello+Slack+...) with multi-account profiles, audit logging, and security-first defaults. ~74% token savings on typical multi-step sessions.
An experimental open-source attempt to make GPT-4 fully autonomous, pushing the boundaries of what is possible with AI.
Slack CLI for agents: read URLs/threads/history/unreads/later/canvases/workflows, search messages/files, download attachments, lookup users, list/create/invite channels, open DMs, draft messages, schedule sends, and explicit sends/edits/deletes/reactions/mark-read/uploads.
Author, validate, and troubleshoot AWS CloudFormation templates. Covers template authoring with secure defaults, pre-deployment validation (cfn-lint, cfn-guard, change sets), and root-cause diagnosis of failed stacks using CloudFormation events and CloudTrail correlation.