Loading...
Loading...
Found 9,690 Skills
Agentic workflow patterns for autonomous LLM reasoning. Use when building ReAct agents, implementing reasoning loops, or creating LLMs that plan and execute multi-step tasks.
This skill should be used when the user asks to "update GitHub Actions", "check for action updates", "upgrade workflow actions", "update actions to latest version", "replace dependabot for actions", "check for outdated actions", or wants to find outdated GitHub Actions in workflow files and update them to the latest release versions.
Git-centric implementation workflow. Enforces clean checkout, creates a properly named branch, tracks progress in a WIP markdown file, and commits continuously so git logs serve as the primary monitoring channel. Use when starting instructed, offer for any plan-based implementation task.
Build AI-first applications with RAG pipelines, embeddings, vector databases, agentic workflows, and LLM integration. Master prompt engineering, function calling, streaming responses, and cost optimization for 2025+ AI development.
[Tooling & Meta] Restore workflow context from checkpoint after session loss
Log exploration and analysis using Quickwit search engine. Incident investigation, error pattern analysis, and observability workflows. Three index discovery modes for different performance and convenience trade-offs.
Work with the Inpoxia repository's local tools and workflows for CLI usage, GraphMail library changes, and quality checks. Use when tasks involve running or updating `inpoxia` commands, modifying files under `src/inpoxia/**`, validating behavior with `pytest`, or enforcing style/type checks with `ruff` and `pyright`.
Create a plan for review: idea branch, plan file, and draft PR. Part of the Plot workflow. Use on /plot-idea.
Use when "CrewAI", "multi-agent systems", "agent orchestration", "AI crews", or asking about "autonomous agents", "agent collaboration", "role-based agents", "agent workflows", "AI team coordination"
Deploy Sablier EVM contracts (Comptroller, ERC20 Faucet, Flow, Lockup, Airdrops) with full workflow automation. This skill should be used when the user asks to "deploy", "deploy protocol", "deploy to chain", or mentions deployment-related tasks. Handles contract deployment, explorer verification, SDK updates, and sample data creation through Init script.
Maintain durable project context in `tasks/context.md` (state, decisions, milestones, gotchas, optional context links), inline during other workflows or standalone for cleanup/backfill. Triggers: update context.md, decision log, record project context, capture high-value reference links that improve context handoff.
Native Arrow filesystem integration with PyArrow. Optimized for Parquet workflows, zero-copy data transfer, predicate pushdown, and column pruning. Covers S3, GCS, HDFS with PyArrow datasets.