dym-arex-skill-creator-tao-repo-skill
Creator: create / verify / refresh / extend a repo skill. The repo you need isn't in the library of 1,000 skills yet, or the existing skill has drifted from upstream.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-07 00:13
Agents & models
25,836 results
dym-arex-skill-xuat-skill-sang-agent-khac
Export repo skills to Claude Code / Codex / other agents. You don't want to switch to DisCo, you just want to borrow a few repo skills (e.g. vllm, sglang) for the agent you're using.
dym-browser-use
browser-use/browser-harness — drive the browser over CDP instead of one-off Playwright scripts · type /dym-browser-use <slug> · slugs: repl · qa · cloud
dym-harness-sdk
Strands harness (strands-agents/harness-sdk) — preassembled agent create_harness() + how they test/eval — verified workflow. Type /dym-harness-sdk <slug>. slugs:…
dym-harness-sdk-interventions
Attach a guardrail to a Strands harness tool call via the interventions parameter (ask · smart · .cedar file · text policy · custom handler) — call when needed…
dym-harness-sdk-quickstart
Install strands-harness into an isolated venv and build a pre-assembled agent with create_harness() — call when you need to try the Strands harness, see what tools/plugins/memory it assembles before…
dym-impeccable-install-into-your-project
Install Impeccable into your project. Add the /impeccable skill + design hook to your project's AI harness, in exactly the scope you want (project, not machine).
dym-nuwa-skill
nuwa-skill (alchaincyf/nuwa-skill) — verified workflows. Type /dym-nuwa-skill <slug>. slugs: install · distill-a-person · diagnose-then-distill ·…
dym-nuwa-skill-distill-a-person
Distill a person (direct path, chat-only). Why use it: you already know who you want to distill (Munger, Feynman, Paul Graham, Trương Nhất Minh…) and want to produce a…
dym-nuwa-skill-install
Install nüwa (女娲) into your runtime. Why use it: this is the first mandatory step — nüwa is not a CLI, it is an Agent Skill (a SKILL.md file + references/ +…
dym-nuwa-skill-use-and-update-persona
Use and update a persona skill (chat-only). Why use it: a skill that has been fully distilled and then sits idle is useless — this file explains how to call it into action, how to pull it out…
dym-ruflo
ruflo (claude-flow 3.40) — swarm-agent orchestration INSIDE Claude Code through MCP + hooks + Task tool. Type /dym-ruflo <slug> — slugs: install · init · route.
dym-ruflo-route
Decide whether to use ruflo, and choose among 4 layers of agent orchestration: ruflo · herdr · orca-dispatch (ours) · bare Task tool. Call when unsure 'should I install…
dym-scientific-agent-skills
scientific-agent-skills (K-Dense-AI/scientific-agent-skills) — verified workflows. Type /dym-scientific-agent-skills <slug>. slugs: cai-dat-skills ·…
dym-scientific-agent-skills-cai-dat-skills
Install Scientific Agent Skills into your agent. bring a subset of the 163 scientific skills into the agent (Claude Code / Cursor / Codex / Gemini CLI / Antigravity…) to…
dym-scientific-agent-skills-chay-script-bundled-tu-shell
Run bundled scripts straight from the shell (no agent needed). 105/163 skills carry a scripts/ directory, and 90 of those skills have scripts written with argparse. This is a CLI…
dym-scientific-agent-skills-dung-skill-trong-agent
Use a skill in the agent (PROMPT ONLY, not a shell command). An already-installed skill may still not be chosen by the agent, or it may pick the wrong sibling skill. This file is the way…
dym-scientific-agent-skills-pin-va-cap-nhat
Pin version, update, remove. A skill is an instruction that the agent follows. A silent update changes agent behavior between two runs — exactly what you don't want…
agentic-os-setup
Trigger with "use the agentic-os-setup agent", "run the setup agent", "set up an agentic OS", "persist memory", "add the OS harness", or when the user requires…
os-learning-loop
Trigger with "run the learning loop", "perform a retrospective", "how can we improve from this session", "update our skills based on what we learned", "conduct…
os-skill-improvement
Continuously improves an existing agent skill based on eval results using the RED-GREEN-REFACTOR cycle. Apply when a skill's routing accuracy is low, trigger…
sanctuary-orchestrator-integration
Sanctuary-specific integration skill connecting the Guardian to the Agent Loops Orchestrator. Maps the Separation of Concerns between strategic workflow…
pptx
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or…
rivetkit-actors
Build stateful backends with Rivet Actors: high-performance, long-lived, in-memory, persisted processes. Use when you outgrow HTTP, databases, or queues.…