Explore AI Agent Skills & Claude Prompts
Discover open-source agent skills for Claude Code, Codex, ChatGPT, and any tool that uses SKILL.md.
Enter through keywords, occupations, creators, and GitHub sources to see what kinds of skills are emerging across domains.
Use the same catalog through the API
Connect 381,784 public skills to your own search, analytics, or agent workflow with the REST API.
Querying local SQLite index...
uniqc-test-before-release
by IAI-USTC-QuantumUse before every UnifiedQuantum release to create and execute a complete release-candidate test plan, including CLI, Gateway frontend, cloud/dummy/real-device workflows, best-practices notebooks, and programmatic documentation-to-software alignment. Produces a full test report and a release/no-release recommendation.
uniqc-release
by IAI-USTC-QuantumCreate a new UnifiedQuantum release: generates release notes, updates CHANGELOG.md, creates a release branch, and opens a PR to main. After merge, creates and pushes a git tag, creates a GitHub Release, and deletes the release branch.
uniqc-build-docs
by IAI-USTC-QuantumRun the full UnifiedQuantum documentation build: execute all examples (pre-doc-execution), regenerate API reference via sphinx-apidoc, and build Sphinx HTML. Reports any warnings, errors, or diffs in example-exec-logs/.
uniqc-circuit-interop
by IAI-USTC-QuantumUse when the user wants to convert quantum circuits across UnifiedQuantum's supported in-process types (uniqc ≥ 0.0.15): Circuit ↔ OriginIR / OriginIR-ext string ↔ OpenQASM 2.0 string ↔ qiskit `QuantumCircuit` ↔ pyqpanda3 circuit. Covers `AnyQuantumCircuit` as the universal input type for compile/simulate/submit, `normalize_to_circuit()` / `NormalizedCircuit`, `Circuit.to_qiskit_circuit()` / `Circuit.to_pyqpanda3_circuit()`, `Circuit.from_qasm()` / `OriginIR_BaseParser` / `OpenQASM2_BaseParser`, the OriginIR-ext default emission (v0.0.15) plus `Circuit.to_originir_official()` / `uniqc.compile.convert_originir_ext_to_originir()` for OriginQ submission, the ext-only gate / instruction inventory, round-trip pitfalls, and which platform expects which IR (OriginQ wants official OriginIR; Quafu/IBM want OpenQASM 2.0; uniqc auto-converts at submit).
uniqc-xeb-qem
by IAI-USTC-QuantumUse when the user wants to characterize hardware (XEB benchmarking, incl. the new parallel-CZ module in 0.0.13) or apply quantum error mitigation (QEM) to readout results in UnifiedQuantum. Covers `xeb_workflow.run_1q/2q/parallel/parallel_cz_xeb_workflow`, `readout_em_workflow.run_readout_em_workflow`, and the `ReadoutEM.apply` / `M3Mitigator.apply` pipeline. Includes the CLI (`uniqc calibrate xeb / readout / pattern`) and the calibration cache layout.
uniqc-algorithm-cases
by IAI-USTC-QuantumUse when the user wants to run a *named* canonical quantum algorithm in UnifiedQuantum: VQE (H2 / TFIM), QPE / phase estimation, Grover, QFT, Deutsch-Jozsa, GHZ / W / Dicke state preparation, classical shadow / state tomography, amplitude estimation, VQD, thermal state. Provides ready-to-run templates that you can adapt to the user's problem.
uniqc-version-tracker
by IAI-USTC-QuantumUse when the user asks to check for a new UnifiedQuantum release, track API changes, run smoke tests across all skills, or produce a version-alignment report. This skill teaches a 5-phase workflow: DETECT version gap (installed uniqc vs CLAUDE.md baseline + git tags + PyPI), DIFF changelog/commits between releases, SMOKE-TEST all 13 skills in parallel via sub-agents, AGGREGATE results cross-referenced with breaking changes, and REPORT with a markdown table + recommendations. All smoke tests use dummy backends only — no real cloud submission.
uniqc-doctor-config
by IAI-USTC-QuantumUse when the user is debugging the UnifiedQuantum environment, install, or configuration: run `uniqc doctor` (added in uniqc 0.0.13), interpret its 6-section report (env / core deps / optional dep groups / config tokens / task DB / backend cache / platform connectivity), triage `MissingDependencyError` / `ConfigValidationError` / `AuthenticationError` / `BackendNotFoundError`, fix proxy or token problems, refresh the local backend cache, and validate end-to-end before any cloud submit. Covers the `uniqc config validate` / `uniqc config list` / `uniqc config set` / `uniqc backend update` / `uniqc backend list` flow and the platform-extras layout (qiskit core, Quafu archived, originq / quark extras).
uniqc-platform-verify
by IAI-USTC-QuantumUse when the user wants to verify that a quantum platform's published / cached metadata is actually accurate: cross-check chip topology, qubit availability, basis gates, calibration freshness, and 1q/2q/parallel-CZ gate fidelities against measured XEB + readout calibration on the live backend. Detect stale chip cache, drift between vendor-published numbers and measured values, qubits that should be excluded, and silent backend regressions. Builds on the uniqc 0.0.13 backend-cache refresh fix (IBM/Quafu/Quark `uniqc backend update --platform` actually refreshes now), the strict pre-flight policy in `uniqc.calibration.xeb`, and the parallel-CZ XEB module.
uniqc-quantum-ml
by IAI-USTC-QuantumUse when the user wants to do quantum machine learning with UnifiedQuantum + PyTorch: native `Circuit.param_map` / `param_dict` / `set_param_last` + `uniqc.expectation()` for backend-agnostic differentiable training (v0.0.15), high-level `QNNClassifier` / `QCNNClassifier` / `HybridQCLModel`, low-level `QuantumLayer` (parameter-shift autograd over a `Circuit`), and end-to-end PyTorch training loops on classical datasets (moons / MNIST / quantum-state classification). Covers torchquantum optional dependency and parameter-shift gradients.
uniqc-noise-simulation
by IAI-USTC-QuantumUse when the user wants to model and simulate quantum noise locally with UnifiedQuantum (uniqc ≥ 0.0.13): build error channels (Depolarizing / TwoQubitDepolarizing / BitFlip / PhaseFlip / AmplitudeDamping / PauliError1Q/2Q / Kraus1Q), wire them into ErrorLoader_GenericError / GateTypeError / GateSpecificError, attach readout error, run NoisySimulator on density-matrix or vector backends, drive chip-backed dummy backends (`dummy:originq:<chip>`, `dummy:quark:<chip>`), and validate the noise model against a calibration cache. Notes the 0.0.13 NoisySimulator MRO fix (noise injection no longer silently skipped on certain paths).
uniqc-quantum-volume
by IAI-USTC-QuantumUse when the user wants to run a Quantum Volume (QV) test on a UnifiedQuantum-supported backend: build the standard square QV circuits (n random SU(4) layers, depth n) via qiskit, load them into uniqc, run on the target backend, compute the heavy-output probability, and apply the conventional 2/3 + lower-confidence-bound pass/fail rule across n = 2, 3, 4, … to find the largest passing n. Report `QV = 2^n_max`.
Browse Agent Skills by Occupation
23 major groups · 867 SOC occupations
Browse by Category
Explore agent skills organized by their primary use case
Explore the agent skills ecosystem by occupation and creator
SkillMD is not just a keyword search box. It is an open map that organizes public skills by occupation, creator, and repository, helping you see which workflows, judgment criteria, and domain habits people are writing for AI agents.
Then follow creators and GitHub repositories back to the source: compare the skills a team maintains, whether the repo is active, and how the README frames the work before you open, install, or reuse anything.
Use it three ways: learn an unfamiliar field by occupation, study how creators organize skills, then use source context to decide what is worth opening or reusing.
01 Map a field
Browse 23 occupation groups and 867 SOC roles to learn what skills exist in adjacent domains and how they break down real work.
02 Follow creators
Use creator and repository pages to inspect maintained skill collections, recent updates, and source context before trusting a result.
03 Search with sources
Search 1.7M+ collected skills, then use occupation tags, creators, and GitHub source context to decide what is worth opening.
Start with the occupation map, then follow creators and repositories back to real code. SkillMD helps explain why a skill is worth opening, not only what it is named.
Standardizing Agent Capabilities with SKILL.md and Model Context Protocol (MCP)
In the rapidly evolving landscape of artificial intelligence, LLM agents (Large Language Model agents) have transitioned from simple text predictors to autonomous problem solvers. To orchestrate complex, multi-step agentic workflows, developers require a standardized format to specify agent capabilities, prompt instructions, system rules, and database bindings. This is where SKILL.md and the Model Context Protocol (MCP) have emerged as standard developer paradigms. SkillMD serves as the central directory for indexing, exploring, and sharing these critical agent configurations.
Our open-source registry currently tracks over 1.7 million collected SKILL.md configurations and system prompts. By compiling agent configurations from active developers on GitHub, we bridge the gap between prompt engineering research and production execution. Whether you are building agents with Anthropic's Claude Code, OpenAI's GPT-4, Google's Gemini, or local models using Ollama and LlamaIndex, standardized skill definitions ensure your agents behave predictably across different runtime environments.
What is the Model Context Protocol (MCP)?
The Model Context Protocol (MCP) is an open-source standard designed to connect LLMs to data sources, developer tools, and external environments. MCP establishes a bidirectional communication channel between client applications (like Cursor, Claude Desktop, or custom agent systems) and servers hosting data or capabilities. Standardizing instructions via SKILL.md enables LLMs to query databases, read local files, execute terminal commands, and integrate third-party APIs. SkillMD allows you to find ready-to-run MCP servers and prompt instructions for various occupations and technical tasks.
The Structure of a Professional SKILL.md File
A valid SKILL.md configuration is designed to be easily read by humans and parsed by LLMs. It contains precise system instructions, trigger conditions, required parameters, and execution examples. Below is the typical architectural blueprint of a professional agent skill:
- Metadata & Core Scope: Declares the name of the skill, author details, target models, and a description of the capability.
- Triggers & Intent Detection: Details semantic triggers that help the agent decide when to invoke this skill.
- System Prompts: Explicit system-level instructions that direct the agent's behavior, personality, safety guardrails, and formatting preferences.
- Capabilities & Tools: Lists the files, databases, or APIs the agent must access to complete the tasks.
- Few-Shot Examples: Demonstrates real inputs and outputs, helping the model generalize behavior through in-context learning.
Optimizing Agent Workflows for Modern LLMs
Writing effective agent skills requires deep knowledge of prompt engineering. With the release of advanced reasoning models like Claude 3.5 Sonnet, ChatGPT o1, and DeepSeek-V3, prompt templates must focus on structured thinking. Developers are encouraged to use XML tags (e.g., <thought>, <context>, and <rules>) to isolate execution boundaries. Standardized prompts prevent agents from suffering from context drift, ensuring that long-running tasks remain aligned with the initial system parameters.
Exploring by SOC Occupations and Creator Profiles
What makes SkillMD unique is its taxonomy. Instead of simple text search, we parse and organize files according to the Standard Occupational Classification (SOC) system. This means you can discover skills written for Computer and Mathematical roles, Business and Financial operations, Legal, Design, and and Educational Instruction fields. By tracking creator profiles, developers can study how different teams organize their custom instructions, compare version updates, and fork public configs for specialized enterprise use cases.
SkillMD operates as a high-performance index running on a fast Go backend and a highly responsive Astro SSR frontend. All search queries execute in milliseconds, featuring smart debouncing to prevent multiple API requests while keeping user data secure. Join our community of developers to standardize your AI agent instructions and optimize your LLM prompting workflows today.
Frequently Asked Questions
A practical guide to agent skills: what they are, how to inspect them, and how SkillMD helps you explore the ecosystem.