pi-prompting
Provides internal guidance for composing prompts that Pi runs can handle reliably. Covers coding, review, diagnosis, and research tasks, with DeepSeek as the default model.
Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Provides internal guidance for composing prompts that Pi runs can handle reliably. Covers coding, review, diagnosis, and research tasks, with DeepSeek as the default model.
Uses LSP symbols to inspect Rust project structure. Supports listing structs, traits, functions, and other symbols.
Performs a detailed SWOT analysis of a product or business. Examines strengths, weaknesses, opportunities, and threats and provides actionable recommendations for strategic assessment.
Manages evaluator creation, updates, tasks, column mappings, and evaluation runs on spans or experiments. Supports LLM judges, code evaluators, evaluator prompt improvements, and continuous monitoring of qualities such as correctness and faithfulness.
Integrates Packer builds with the HCP Packer registry by pushing build metadata. Supports image lifecycle management, version tracking, and governance.
Uses a merged weekly changelog in elevenlabs-dx to update ElevenLabs agent skills. Opens a pull request in elevenlabs/skills after the changelog merges or when given a changelog date.
Classifies conversation content, rewrites it as declarative knowledge, and files it in the appropriate vault category. A quick mode saves findings to the raw staging area, and named-vault routing supports multiple destinations.
Supports Word document creation, editing, and analysis, including tracked changes, comments, and formatting. Intended for design briefs, copy documents, and deliverables ready for review.
Supports reading an arXiv paper when the user provides its arXiv URL.
Implements lane-based enemy pathing, wave spawning, and towers that automatically target and fire. Covers economy and life systems, including wave and economy balancing.
Requires direct checks such as running the feature, reading the actual value, or inspecting the diff. Treats compilation, proxies, and self-reports as insufficient evidence of completion.
Programmatically publishes and schedules content across social platforms including X, LinkedIn, Instagram, TikTok, and YouTube. Uses the SocialClaw API and requires SOCIALCLAW_API_KEY.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name