Agent Building skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

heurist-skill-marketplace-admin

Admin operations for the Heurist Skill Marketplace. Use this skill when the user asks to add, ingest, approve, reject, remove, update, or list skills in the Heurist marketplace. Also triggers for checking upstream changes, updating external API dependencies, updating metrics (stars/downloads), re-ingesting skills, or any marketplace database management task. Working directory is heurist-agent-framework. Always use uv run python to run scripts.

817 repo starsObserved in 1 repos

Agent Building

GitHub

running-coral-experiments

Run and manage CORAL experiments from the operator side — launch agents with `coral start` (dotlist overrides, model/count, tmux vs local), monitor with `coral status` / `coral log` / `coral show` / the web dashboard, and drive the loop with `coral resume` (inject instructions, fork from an attempt), `coral heartbeat` (tune reflection cadence), and `coral stop`. Use whenever the user wants to start a CORAL run, check on agents, read scores/leaderboard, steer or resume a run, diagnose agents that keep restarting or fail every eval, scale to more agents or islands, or stop a run. Deep references for steering/heartbeat tuning and scaling/troubleshooting live alongside this skill.

817 repo starsObserved in 1 repos

Agent Building

GitHub

agentic-legibility

Score a repository's agentic legibility from repo-visible evidence only. Use when Codex needs to audit how easy a codebase is for coding agents to discover, bootstrap, validate, and navigate, especially for harness-engineering reviews, developer-experience audits, repo cleanup, or before/after comparisons after improving docs, tooling, or architectural constraints.

815 repo starsObserved in 3 repos

Agent Building

GitHub

create-simple-prompt

This skill should be used when the user asks to "create a new prompt sample", "add a new prompt sample", "scaffold a new prompt sample", "create a prompt contribution", "add a prompt", or needs to create a new prompt sample with proper folder structure, README, and sample.json metadata. Do NOT use this skill for agent instructions or system prompts.

808 repo starsObserved in 1 repos

Agent Building

GitHub

create-skill-sample

This skill should be used when the user asks to "create a new skill sample", "add a skill", "scaffold a new skill", "contribute a skill", "create a GitHub Copilot skill", "build a custom skill", or needs to create a new GitHub Copilot custom skill sample with proper folder structure, SKILL.md, README, and sample.json metadata inside the skills folder. Do NOT use this skill for simple prompt samples or agent instructions.

808 repo starsObserved in 1 repos

Agent Building

GitHub

create-system-prompt

This skill should be used when the user asks to "create an agent instruction", "add agent instructions", "scaffold an agent sample", "create a system prompt sample", "add a system prompt", "create a new agent", "build an agent", or needs to create a new agent instruction sample with proper folder structure, README, and sample.json metadata inside the agent-instructions folder. Do NOT use this skill for simple prompt samples that are not agent instructions.

808 repo starsObserved in 1 repos

Agent Building

GitHub

prompt-context-engineer

Transform any rough prompt, request, or idea into a well-structured, context-engineered prompt using Andrej Karpathy's context engineering principles. Use this skill whenever the user asks to improve, rewrite, restructure, optimize, or "engineer" a prompt; mentions prompt engineering or context engineering; pastes a prompt and asks to make it better; wants help writing a system prompt or instructions for an AI; or says things like "turn this into a good prompt", "make this prompt work better", or "Claude isn't giving me what I want with this prompt". Also use it when the user shares a vague request and explicitly wants it converted into a reusable, high-quality prompt. Do NOT use this skill to answer or execute the original prompt itself, to write general (non-prompt) documents, or for code or content generation that isn't about crafting a prompt.

808 repo starsObserved in 1 repos

Agent Building

GitHub

yichen-agent-memory

Install, upgrade, inspect, and maintain the public Agent Memory Vault system from the mcncarl/agent-memory-vault repository, including a shared Claude Code and Codex setup. Use when the user asks to install a Markdown/Obsidian-first memory vault, connect Claude Code and Codex to one fact source, configure SQLite/FTS or optional Zvec semantic retrieval, run search, closeout, audit, or troubleshoot memory scripts and hooks.

807 repo starsObserved in 1 repos

Agent Building

GitHub

aamas-experiments

Use when designing or auditing AAMAS experiments - self-play and population-based training, opponent selection, equilibrium and regret metrics, game-theoretic simulations, ablations, seeds, hyperparameters, compute, and claim-to-evidence fit - with emphasis on experiments that probe the interaction rather than chase a single-agent leaderboard.

805 repo starsObserved in 2 repos

Agent Building

GitHub

wrap-up

Close out (or revisit) a Claude Managed Agent build — refresh the overview page, recap every primitive the founder now owns, show the run log and live status, suggest 1–2 tailored next upgrades, and sweep hygiene (sessions archived, key only in .env, no literal dates in deployment kickoffs). Use when the founder says "/wrap-up", "wrap up", "close it out", "where do things stand with my agent", or at the end of a /launch-your-agent build.

805 repo starsObserved in 1 repos

Agent Building

GitHub