15 skills
Superpowers
superpowers
15 workflow-oriented skills for planning, debugging, TDD, code review, and verification.
#workflow#planning#debugging#tdd#code-review
@obraMIT
GitHubSkill Installer
Find the right research skills and generate one install command.
349
installable capabilities
13
Repositories
Not sure where to start?
Start from the home page with tasks such as framing, reading, drafting, or submission.
Know the job?
Filter by workflow, writing, research, and figures to select agent capabilities.
Install after selecting
The side panel generates a terminal command for your OS and agent.
18 options
Workflow & process
Select only the capabilities you want installed into your agent. For one research task, start with PaperSkills Core or a scenario bundle.
1 skill
Karpathy-Inspired Claude Code Guidelines
andrej-karpathy-skills
A practical workflow skill focused on four coding principles: Think Before Coding, Simplicity First, Surgical Changes, and Goal-Driven Execution.
#workflow#process#guidelines#simplicity#verification
@multica-aiSee repository
GitHub11 skills
Qiushi Skill
qiushi-skill
Methodology-first skill collection that drives agents to investigate facts, focus priorities, iterate in practice, and complete work with disciplined process.
#workflow#methodology#agents#investigation#planning
@HughYauMIT
GitHubCS32 skills
Claude Science
claude-science
32 Claude Science skills from Anthropic — protein structure & design, genomics, single-cell, publication figures, literature, and remote compute — installable across agents with no subscription.
#anthropic#claude-science#research#protein#genomics
@anthropicsApache-2.0
GitHubSASource item1 skill
autoskill
sa.autoskill
Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.
Scientific Agent SkillsMIT license
GitHubCSSource item1 skill
compute-env-setup
cs.compute-env-setup
Set up a compute environment on a remote provider so Claude Science jobs can run there. Covers direct SSH/conda hosts, Slurm clusters, container-via-bridge runners, and managed-API providers (Modal, GCP, RunPod). Use when standing up a new provider, porting an env to a different backend, adding a tool that needs its own software stack, or wiring weight caches. Triggers on "new compute provider", "set up env on", "port env to", "build GPU image", "weight cache", "compute_details", "conda env on the box", "apptainer on slurm".
Claude ScienceApache-2.0
GitHubCSSource item1 skill
customize
cs.customize
Create, configure, and maintain custom agent profiles and author new skills via the `repl` tool. Use when the user wants to create an agent profile, build a custom agent, modify agent capabilities, attach or detach skills/connectors on a profile, author a skill, or inspect which connectors and tools are available. Also use whenever you need the `host.agents.*` or `host.skills.*` Python SDK.
Claude ScienceApache-2.0
GitHubCSSource item1 skill
learn
cs.learn
Use this skill when the user wants intellectual understanding — learning how or why something works, not getting a task done or soliciting Claude's judgment. Trigger for: - Explicit learning requests: teach, explain, ELI5, walk me through, quiz me, flashcards, "I'm rusty on"; definitions ("what is X") - Terse concept names implying "help me understand this": "Galois theory," "transformers, from scratch" - Confusion signals: "won't stick," "keep mixing these up," "not getting it" - Learning-path questions: prerequisites, sequencing, what to study before X - Conceptual questions about mechanisms, causes, or dynamics Don't trigger for: - Tasks: coding, writing, calculation, translation, factual lookup, news updates - Personal troubleshooting; resource/textbook recommendations - Claude's evaluative verdict: opinion prompts ("do you think X", "settle this", "honest take", "is X dead / still taken seriously") and interpretive takes ("was X really as harsh as people say")
Claude ScienceComplete terms in LICENSE.txt
GitHubCSSource item1 skill
managed-model-endpoints
cs.managed-model-endpoints
Register a model service in the managed family — a local model server container the daemon starts/stops on demand, or a remote upstream model API (https). Read the runbook, allocate a port (local only), compose idempotent start/stop scripts (local only), register once. Load when the user wants a model service available for inference, or when list_compute shows managed endpoints.
Claude ScienceApache-2.0
GitHubNSSource item1 skill
nature-experiment-log
ns.nature-experiment-log
标准化实验日志记录——接收原始材料（图/语音/文字），产出带 YAML frontmatter 的标准日志到 Obsidian vault。需配合飞书 CLI 或手动输入使用。
Nature SkillsMIT
GitHubSASource item1 skill
pi-agent
sa.pi-agent
Build with and use Pi, the minimal terminal coding harness. Use for installing Pi, configuring providers/models/settings, creating Pi skills/extensions/packages/themes/prompt templates, embedding Pi through the SDK, integrating over RPC or JSON event streams, parsing sessions, developing custom Pi providers and TUI components, or using ecosystem packages such as pi-subagents (delegation/orchestration), pi-mcp-adapter (MCP servers), pi-interview (interactive forms), and pi-web-access (web search, fetching, video understanding).
Scientific Agent SkillsMIT
GitHubCSSource item1 skill
product-self-knowledge
cs.product-self-knowledge
Stop and consult this skill whenever your response would include specific facts about Anthropic's products. Covers: Claude Code (how to install, Node.js requirements, platform/OS support, MCP server integration, configuration), Claude API (function calling/tool use, batch processing, SDK usage, rate limits, pricing, models, streaming), and Claude.ai (Pro vs Team vs Enterprise plans, feature limits). Trigger this even for coding tasks that use the Anthropic SDK, content creation mentioning Claude capabilities or pricing, or LLM provider comparisons. Any time you would otherwise rely on memory for Anthropic product details, verify here instead — your training data may be outdated or wrong.
Claude ScienceApache-2.0
GitHubCSSource item1 skill
remote-compute-modal
cs.remote-compute-modal
Run GPU jobs on the user's own Modal account via host.compute.create('byoc:modal', ...). Covers the create→submit→wait_for_notification flow, the compute_provider kernel for env setup, image/volume resolution, and the two approval cards. Load once you've decided to dispatch to Modal.
Claude ScienceApache-2.0
GitHubCSSource item1 skill
remote-compute-ssh
cs.remote-compute-ssh
Submit→wait_for_notification→harvest workflow for the user's SSH/SLURM hosts. Load once you've decided to dispatch remote.
Claude ScienceApache-2.0
GitHubAIRSource item1 skill
research-manager
air.research-manager
Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during execution — to maintain a faithful, auditable trace of how a research project actually evolved.
#ARA#Research Recording#Provenance
AI Research SkillsMIT
GitHubCSSource item1 skill
self-awareness
cs.self-awareness
Claude Science's own session database schema and SDK surface for introspection via host.query(). Load this when you need to query your own conversation history, token usage, cost accounting, execution log, or artifact metadata beyond what host.frames()/host.artifacts() provide — e.g. "how many tokens has this session used", "what was my last tool call", "list every file I've written", "where are messages stored", "what tables can I query", "inspect frames.context_data", or any time you're about to PRAGMA-probe the Claude Science metadata DB to discover its schema.
Claude ScienceApache-2.0
GitHubCSSource item1 skill
skill-creator
cs.skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Claude ScienceApache-2.0
GitHubCSSource item1 skill
using-model-endpoint
cs.using-model-endpoint
Call a registered model endpoint over its native HTTP API from the endpoint's scoped inference kernel (BASE_URL preloaded). Load once a task needs predictions from a registered model endpoint.
Claude ScienceApache-2.0
GitHub