[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FAJC4EB8M9ZHN56CS86TJM":3,"skill-same:01M6FAJC4EB8M9ZHN56CS86TJM":100},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":29,"linkOnly":30,"markdownContent":31,"markdownBody":32,"frontMatter":33,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":43,"install":44,"resources":57},"01M6FAJC4EB8M9ZHN56CS86TJM","qiskit",null,"Build and transpile Qiskit circuits, test local simulators and prepare authorized hardware workloads with Sampler\u002FEstimator primitives.","boisenoise\u002Fskills-collections","boisenoise","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F193180?v=4","01M6CDBDQK6BDN55ZMA6B6PKBM","01M6CDBDVSJ3JPTBYN26FZ7TZK",12,"MIT","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-qiskit\u002FSKILL.md",[],[5,18,19,20,21,22,23,24,25,26,27,28],"test","prepare","primitives","build","community","hardware","local","critical","with","test local","2026","2026-11-10 10:12:30",false,"---\nname: qiskit\ndescription: \"Build and transpile Qiskit circuits, test local simulators and prepare authorized hardware workloads with Sampler\u002FEstimator primitives.\"\nlicense: MIT\nmetadata:\n    skill-author: K-Dense Inc.\nrisk: critical\nsource: community\ndate_added: \"2026-03-06\"\n---\n## Bundled upstream support\n\nSupporting files are included at skill-relative paths. See [UPSTREAM-NOTICE.md](UPSTREAM-NOTICE.md) for their pinned sources, licenses, hashes, and import changes.\n\n# Qiskit\n\n## When to Use\n- You are building or optimizing quantum circuits with Qiskit for simulators or real hardware.\n- You need IBM Quantum-style tooling for transpilation, execution, visualization, or algorithm libraries.\n- You want guidance on moving from a simple circuit prototype to backend-aware execution.\n\n## Overview\n\nQiskit provides circuit construction, transpilation and quantum-computing tools.\nProvider plugins and hardware access require their own supported versions,\nauthentication and account entitlements. Performance depends on the workload.\n\nHardware jobs, sessions and serverless calls can consume paid quota. Prepare and\ntest locally first; authorize the exact provider, target and budget before any\nremote submission. Examples are sketches requiring version checks and supplied\nvariables, not preauthorized workloads.\n\n## Quick Start\n\n### Installation\n\n```bash\nuv pip install qiskit\nuv pip install \"qiskit[visualization]\" matplotlib\n```\n\n### First Circuit\n\n```python\nfrom qiskit import QuantumCircuit\nfrom qiskit.primitives import StatevectorSampler\n\n# Create Bell state (entangled qubits)\nqc = QuantumCircuit(2)\nqc.h(0)           # Hadamard on qubit 0\nqc.cx(0, 1)       # CNOT from qubit 0 to 1\nqc.measure_all()  # Measure both qubits\n\n# Run locally\nsampler = StatevectorSampler()\nresult = sampler.run([qc], shots=1024).result()\ncounts = result[0].data.meas.get_counts()\nprint(counts)  # {'00': ~512, '11': ~512}\n```\n\n### Visualization\n\n```python\nfrom qiskit.visualization import plot_histogram\n\nqc.draw('mpl')           # Circuit diagram\nplot_histogram(counts)   # Results histogram\n```\n\n## Core Capabilities\n\n### 1. Setup and Installation\nFor detailed installation, authentication, and IBM Quantum account setup:\n- **See `references\u002Fsetup.md`**\n\nTopics covered:\n- Installation with uv\n- Python environment setup\n- IBM Quantum account and API token configuration\n- Local vs. cloud execution\n\n### 2. Building Quantum Circuits\nFor constructing quantum circuits with gates, measurements, and composition:\n- **See `references\u002Fcircuits.md`**\n\nTopics covered:\n- Creating circuits with QuantumCircuit\n- Single-qubit gates (H, X, Y, Z, rotations, phase gates)\n- Multi-qubit gates (CNOT, SWAP, Toffoli)\n- Measurements and barriers\n- Circuit composition and properties\n- Parameterized circuits for variational algorithms\n\n### 3. Primitives (Sampler and Estimator)\nFor executing quantum circuits and computing results:\n- **See `references\u002Fprimitives.md`**\n\nTopics covered:\n- **Sampler**: Get bitstring measurements and probability distributions\n- **Estimator**: Compute expectation values of observables\n- V2 interface (StatevectorSampler, StatevectorEstimator)\n- IBM Quantum Runtime primitives for hardware\n- Sessions and Batch modes\n- Parameter binding\n\n### 4. Transpilation and Optimization\nFor optimizing circuits and preparing for hardware execution:\n- **See `references\u002Ftranspilation.md`**\n\nTopics covered:\n- Why transpilation is necessary\n- Optimization levels (0-3)\n- Six transpilation stages (init, layout, routing, translation, optimization, scheduling)\n- Advanced features (virtual permutation elision, gate cancellation)\n- Common parameters (initial_layout, approximation_degree, seed)\n- Best practices for efficient circuits\n\n### 5. Visualization\nFor displaying circuits, results, and quantum states:\n- **See `references\u002Fvisualization.md`**\n\nTopics covered:\n- Circuit drawings (text, matplotlib, LaTeX)\n- Result histograms\n- Quantum state visualization (Bloch sphere, state city, QSphere)\n- Backend topology and error maps\n- Customization and styling\n- Saving publication-quality figures\n\n### 6. Hardware Backends\nFor running on simulators and real quantum computers:\n- **See `references\u002Fbackends.md`**\n\nTopics covered:\n- IBM Quantum backends and authentication\n- Backend properties and status\n- Running on real hardware with Runtime primitives\n- Job management and queuing\n- Session mode (iterative algorithms)\n- Batch mode (parallel jobs)\n- Local simulators (StatevectorSampler, Aer)\n- Third-party providers (IonQ, Amazon Braket)\n- Error mitigation strategies\n\n### 7. Qiskit Patterns Workflow\nFor implementing the four-step quantum computing workflow:\n- **See `references\u002Fpatterns.md`**\n\nTopics covered:\n- **Map**: Translate problems to quantum circuits\n- **Optimize**: Transpile for hardware\n- **Execute**: Run with primitives\n- **Post-process**: Extract and analyze results\n- Complete VQE example\n- Session vs. Batch execution\n- Common workflow patterns\n\n### 8. Quantum Algorithms and Applications\nFor implementing specific quantum algorithms:\n- **See `references\u002Falgorithms.md`**\n\nTopics covered:\n- **Optimization**: VQE, QAOA, Grover's algorithm\n- **Chemistry**: Molecular ground states, excited states, Hamiltonians\n- **Machine Learning**: Quantum kernels, VQC, QNN\n- **Algorithm libraries**: Qiskit Nature, Qiskit ML, Qiskit Optimization\n- Physics simulations and benchmarking\n\n## Workflow Decision Guide\n\n**If you need to:**\n\n- Install Qiskit or set up IBM Quantum account → `references\u002Fsetup.md`\n- Build a new quantum circuit → `references\u002Fcircuits.md`\n- Understand gates and circuit operations → `references\u002Fcircuits.md`\n- Run circuits and get measurements → `references\u002Fprimitives.md`\n- Compute expectation values → `references\u002Fprimitives.md`\n- Optimize circuits for hardware → `references\u002Ftranspilation.md`\n- Visualize circuits or results → `references\u002Fvisualization.md`\n- Execute on IBM Quantum hardware → `references\u002Fbackends.md`\n- Connect to third-party providers → `references\u002Fbackends.md`\n- Implement end-to-end quantum workflow → `references\u002Fpatterns.md`\n- Build specific algorithm (VQE, QAOA, etc.) → `references\u002Falgorithms.md`\n- Solve chemistry or optimization problems → `references\u002Falgorithms.md`\n\n## Best Practices\n\n### Development Workflow\n\n1. **Start with simulators**: Test locally before using hardware\n   ```python\n   from qiskit.primitives import StatevectorSampler\n   sampler = StatevectorSampler()\n   ```\n\n2. **Always transpile**: Optimize circuits before execution\n   ```python\n   from qiskit import transpile\n   qc_optimized = transpile(qc, backend=backend, optimization_level=3)\n   ```\n\n3. **Use appropriate primitives**:\n   - Sampler for bitstrings (optimization algorithms)\n   - Estimator for expectation values (chemistry, physics)\n\n4. **Choose execution mode**:\n   - Session: Iterative algorithms (VQE, QAOA)\n   - Batch: Independent parallel jobs\n   - Single job: One-off experiments\n\n### Performance Optimization\n\n- Use optimization_level=3 for production\n- Minimize two-qubit gates (major error source)\n- Test with noisy simulators before hardware\n- Save and reuse transpiled circuits\n- Monitor convergence in variational algorithms\n\n### Hardware Execution\n\n- Check backend status before submitting\n- Use least_busy() for testing\n- Save job IDs for later retrieval\n- Apply error mitigation (resilience_level)\n- Start with fewer shots, increase for final runs\n\n## Common Patterns\n\n### Pattern 1: Simple Circuit Execution\n\n```python\nfrom qiskit import QuantumCircuit, transpile\nfrom qiskit.primitives import StatevectorSampler\n\nqc = QuantumCircuit(2)\nqc.h(0)\nqc.cx(0, 1)\nqc.measure_all()\n\nsampler = StatevectorSampler()\nresult = sampler.run([qc], shots=1024).result()\ncounts = result[0].data.meas.get_counts()\n```\n\n### Pattern 2: Hardware Execution with Transpilation\n\n```python\nfrom qiskit_ibm_runtime import QiskitRuntimeService, SamplerV2 as Sampler\nfrom qiskit import transpile\n\nservice = QiskitRuntimeService()\nbackend = service.least_busy(operational=True, simulator=False)\n\nqc_optimized = transpile(qc, backend=backend, optimization_level=3)\n\nsampler = Sampler(mode=backend)\njob = sampler.run([qc_optimized], shots=1024)\nresult = job.result()\n```\n\n### Pattern 3: Variational Algorithm (VQE)\n\n```python\nfrom qiskit_ibm_runtime import Session, EstimatorV2 as Estimator\nfrom scipy.optimize import minimize\n\nwith Session(backend=backend) as session:\n    estimator = Estimator(mode=session)\n\n    def cost_function(params):\n        bound_qc = ansatz.assign_parameters(params)\n        qc_isa = transpile(bound_qc, backend=backend)\n        result = estimator.run([(qc_isa, hamiltonian.apply_layout(qc_isa.layout))]).result()\n        return result[0].data.evs\n\n    result = minimize(cost_function, initial_params, method='COBYLA')\n```\n\n## Additional Resources\n\n- **Official Docs**: https:\u002F\u002Fquantum.ibm.com\u002Fdocs\n- **Qiskit Textbook**: https:\u002F\u002Fqiskit.org\u002Flearn\n- **API Reference**: https:\u002F\u002Fdocs.quantum.ibm.com\u002Fapi\u002Fqiskit\n- **Patterns Guide**: https:\u002F\u002Fquantum.cloud.ibm.com\u002Fdocs\u002Fen\u002Fguides\u002Fintro-to-patterns\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n","## Bundled upstream support\n\nSupporting files are included at skill-relative paths. See [UPSTREAM-NOTICE.md](UPSTREAM-NOTICE.md) for their pinned sources, licenses, hashes, and import changes.\n\n# Qiskit\n\n## When to Use\n- You are building or optimizing quantum circuits with Qiskit for simulators or real hardware.\n- You need IBM Quantum-style tooling for transpilation, execution, visualization, or algorithm libraries.\n- You want guidance on moving from a simple circuit prototype to backend-aware execution.\n\n## Overview\n\nQiskit provides circuit construction, transpilation and quantum-computing tools.\nProvider plugins and hardware access require their own supported versions,\nauthentication and account entitlements. Performance depends on the workload.\n\nHardware jobs, sessions and serverless calls can consume paid quota. Prepare and\ntest locally first; authorize the exact provider, target and budget before any\nremote submission. Examples are sketches requiring version checks and supplied\nvariables, not preauthorized workloads.\n\n## Quick Start\n\n### Installation\n\n```bash\nuv pip install qiskit\nuv pip install \"qiskit[visualization]\" matplotlib\n```\n\n### First Circuit\n\n```python\nfrom qiskit import QuantumCircuit\nfrom qiskit.primitives import StatevectorSampler\n\n# Create Bell state (entangled qubits)\nqc = QuantumCircuit(2)\nqc.h(0)           # Hadamard on qubit 0\nqc.cx(0, 1)       # CNOT from qubit 0 to 1\nqc.measure_all()  # Measure both qubits\n\n# Run locally\nsampler = StatevectorSampler()\nresult = sampler.run([qc], shots=1024).result()\ncounts = result[0].data.meas.get_counts()\nprint(counts)  # {'00': ~512, '11': ~512}\n```\n\n### Visualization\n\n```python\nfrom qiskit.visualization import plot_histogram\n\nqc.draw('mpl')           # Circuit diagram\nplot_histogram(counts)   # Results histogram\n```\n\n## Core Capabilities\n\n### 1. Setup and Installation\nFor detailed installation, authentication, and IBM Quantum account setup:\n- **See `references\u002Fsetup.md`**\n\nTopics covered:\n- Installation with uv\n- Python environment setup\n- IBM Quantum account and API token configuration\n- Local vs. cloud execution\n\n### 2. Building Quantum Circuits\nFor constructing quantum circuits with gates, measurements, and composition:\n- **See `references\u002Fcircuits.md`**\n\nTopics covered:\n- Creating circuits with QuantumCircuit\n- Single-qubit gates (H, X, Y, Z, rotations, phase gates)\n- Multi-qubit gates (CNOT, SWAP, Toffoli)\n- Measurements and barriers\n- Circuit composition and properties\n- Parameterized circuits for variational algorithms\n\n### 3. Primitives (Sampler and Estimator)\nFor executing quantum circuits and computing results:\n- **See `references\u002Fprimitives.md`**\n\nTopics covered:\n- **Sampler**: Get bitstring measurements and probability distributions\n- **Estimator**: Compute expectation values of observables\n- V2 interface (StatevectorSampler, StatevectorEstimator)\n- IBM Quantum Runtime primitives for hardware\n- Sessions and Batch modes\n- Parameter binding\n\n### 4. Transpilation and Optimization\nFor optimizing circuits and preparing for hardware execution:\n- **See `references\u002Ftranspilation.md`**\n\nTopics covered:\n- Why transpilation is necessary\n- Optimization levels (0-3)\n- Six transpilation stages (init, layout, routing, translation, optimization, scheduling)\n- Advanced features (virtual permutation elision, gate cancellation)\n- Common parameters (initial_layout, approximation_degree, seed)\n- Best practices for efficient circuits\n\n### 5. Visualization\nFor displaying circuits, results, and quantum states:\n- **See `references\u002Fvisualization.md`**\n\nTopics covered:\n- Circuit drawings (text, matplotlib, LaTeX)\n- Result histograms\n- Quantum state visualization (Bloch sphere, state city, QSphere)\n- Backend topology and error maps\n- Customization and styling\n- Saving publication-quality figures\n\n### 6. Hardware Backends\nFor running on simulators and real quantum computers:\n- **See `references\u002Fbackends.md`**\n\nTopics covered:\n- IBM Quantum backends and authentication\n- Backend properties and status\n- Running on real hardware with Runtime primitives\n- Job management and queuing\n- Session mode (iterative algorithms)\n- Batch mode (parallel jobs)\n- Local simulators (StatevectorSampler, Aer)\n- Third-party providers (IonQ, Amazon Braket)\n- Error mitigation strategies\n\n### 7. Qiskit Patterns Workflow\nFor implementing the four-step quantum computing workflow:\n- **See `references\u002Fpatterns.md`**\n\nTopics covered:\n- **Map**: Translate problems to quantum circuits\n- **Optimize**: Transpile for hardware\n- **Execute**: Run with primitives\n- **Post-process**: Extract and analyze results\n- Complete VQE example\n- Session vs. Batch execution\n- Common workflow patterns\n\n### 8. Quantum Algorithms and Applications\nFor implementing specific quantum algorithms:\n- **See `references\u002Falgorithms.md`**\n\nTopics covered:\n- **Optimization**: VQE, QAOA, Grover's algorithm\n- **Chemistry**: Molecular ground states, excited states, Hamiltonians\n- **Machine Learning**: Quantum kernels, VQC, QNN\n- **Algorithm libraries**: Qiskit Nature, Qiskit ML, Qiskit Optimization\n- Physics simulations and benchmarking\n\n## Workflow Decision Guide\n\n**If you need to:**\n\n- Install Qiskit or set up IBM Quantum account → `references\u002Fsetup.md`\n- Build a new quantum circuit → `references\u002Fcircuits.md`\n- Understand gates and circuit operations → `references\u002Fcircuits.md`\n- Run circuits and get measurements → `references\u002Fprimitives.md`\n- Compute expectation values → `references\u002Fprimitives.md`\n- Optimize circuits for hardware → `references\u002Ftranspilation.md`\n- Visualize circuits or results → `references\u002Fvisualization.md`\n- Execute on IBM Quantum hardware → `references\u002Fbackends.md`\n- Connect to third-party providers → `references\u002Fbackends.md`\n- Implement end-to-end quantum workflow → `references\u002Fpatterns.md`\n- Build specific algorithm (VQE, QAOA, etc.) → `references\u002Falgorithms.md`\n- Solve chemistry or optimization problems → `references\u002Falgorithms.md`\n\n## Best Practices\n\n### Development Workflow\n\n1. **Start with simulators**: Test locally before using hardware\n   ```python\n   from qiskit.primitives import StatevectorSampler\n   sampler = StatevectorSampler()\n   ```\n\n2. **Always transpile**: Optimize circuits before execution\n   ```python\n   from qiskit import transpile\n   qc_optimized = transpile(qc, backend=backend, optimization_level=3)\n   ```\n\n3. **Use appropriate primitives**:\n   - Sampler for bitstrings (optimization algorithms)\n   - Estimator for expectation values (chemistry, physics)\n\n4. **Choose execution mode**:\n   - Session: Iterative algorithms (VQE, QAOA)\n   - Batch: Independent parallel jobs\n   - Single job: One-off experiments\n\n### Performance Optimization\n\n- Use optimization_level=3 for production\n- Minimize two-qubit gates (major error source)\n- Test with noisy simulators before hardware\n- Save and reuse transpiled circuits\n- Monitor convergence in variational algorithms\n\n### Hardware Execution\n\n- Check backend status before submitting\n- Use least_busy() for testing\n- Save job IDs for later retrieval\n- Apply error mitigation (resilience_level)\n- Start with fewer shots, increase for final runs\n\n## Common Patterns\n\n### Pattern 1: Simple Circuit Execution\n\n```python\nfrom qiskit import QuantumCircuit, transpile\nfrom qiskit.primitives import StatevectorSampler\n\nqc = QuantumCircuit(2)\nqc.h(0)\nqc.cx(0, 1)\nqc.measure_all()\n\nsampler = StatevectorSampler()\nresult = sampler.run([qc], shots=1024).result()\ncounts = result[0].data.meas.get_counts()\n```\n\n### Pattern 2: Hardware Execution with Transpilation\n\n```python\nfrom qiskit_ibm_runtime import QiskitRuntimeService, SamplerV2 as Sampler\nfrom qiskit import transpile\n\nservice = QiskitRuntimeService()\nbackend = service.least_busy(operational=True, simulator=False)\n\nqc_optimized = transpile(qc, backend=backend, optimization_level=3)\n\nsampler = Sampler(mode=backend)\njob = sampler.run([qc_optimized], shots=1024)\nresult = job.result()\n```\n\n### Pattern 3: Variational Algorithm (VQE)\n\n```python\nfrom qiskit_ibm_runtime import Session, EstimatorV2 as Estimator\nfrom scipy.optimize import minimize\n\nwith Session(backend=backend) as session:\n    estimator = Estimator(mode=session)\n\n    def cost_function(params):\n        bound_qc = ansatz.assign_parameters(params)\n        qc_isa = transpile(bound_qc, backend=backend)\n        result = estimator.run([(qc_isa, hamiltonian.apply_layout(qc_isa.layout))]).result()\n        return result[0].data.evs\n\n    result = minimize(cost_function, initial_params, method='COBYLA')\n```\n\n## Additional Resources\n\n- **Official Docs**: https:\u002F\u002Fquantum.ibm.com\u002Fdocs\n- **Qiskit Textbook**: https:\u002F\u002Fqiskit.org\u002Flearn\n- **API Reference**: https:\u002F\u002Fdocs.quantum.ibm.com\u002Fapi\u002Fqiskit\n- **Patterns Guide**: https:\u002F\u002Fquantum.cloud.ibm.com\u002Fdocs\u002Fen\u002Fguides\u002Fintro-to-patterns\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n",{"name":5,"risk":25,"source":22,"license":14,"metadata":34,"date_added":36,"description":7},{"skill-author":35},"K-Dense Inc.","2026-03-06","main","7bf2279c8a65758319526a721d5c4b75683aec9c","skills\u002Fantigravity-qiskit",3,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections","https:\u002F\u002Fgithub.com\u002Fboisenoise","2026-11-10 14:20:15",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add boisenoise\u002Fskills-collections --skill qiskit",{"tool":50,"command":51},"bunx","bunx skills add boisenoise\u002Fskills-collections --skill qiskit",{"tool":53,"command":54},"pnpm","pnpm dlx skills add boisenoise\u002Fskills-collections --skill qiskit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-qiskit\u002FSKILL.md",true,[58,64,68,72,76,80,84,88,92,96],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Falgorithms.md","REFERENCE","参考文档",14620,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-qiskit\u002Freferences\u002Falgorithms.md",{"path":65,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fbackends.md",9327,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-qiskit\u002Freferences\u002Fbackends.md",{"path":69,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fcircuits.md",3471,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-qiskit\u002Freferences\u002Fcircuits.md",{"path":73,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fpatterns.md",13830,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-qiskit\u002Freferences\u002Fpatterns.md",{"path":77,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fprimitives.md",6272,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-qiskit\u002Freferences\u002Fprimitives.md",{"path":81,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fsetup.md",2173,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-qiskit\u002Freferences\u002Fsetup.md",{"path":85,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Ftranspilation.md",7445,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-qiskit\u002Freferences\u002Ftranspilation.md",{"path":89,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fvisualization.md",7673,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-qiskit\u002Freferences\u002Fvisualization.md",{"path":93,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":94,"sourceHtmlUrl":95},"UPSTREAM-LICENSE.txt",1069,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-qiskit\u002FUPSTREAM-LICENSE.txt",{"path":97,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":98,"sourceHtmlUrl":99},"UPSTREAM-NOTICE.md",2563,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-qiskit\u002FUPSTREAM-NOTICE.md",[101,129,156,182,201,224],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":105,"licenseFileUrl":106,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":29},"01M6WNH92BHVFXHGPDZCPJ0AG0","web-access","Use Treg for public web or platform data only when existing search, browser and connected tools cannot cover the task, with explicit cost and data boundaries.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-web-access\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-web-access\u002FSKILL.md",[],[110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,25,125,126,127,128,28],"web","access","web access","official","development","browser","search","data","Tools","read","fetch","only","youtube","free tools","platform","free","cover","normal","when",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":105,"licenseFileUrl":133,"sourceHtmlUrl":134,"categories":135,"keywords":141,"publishedAt":29},"01M6WNF9XAYAB2CZDDJBAKNM93","treg","Use the Treg CLI or MCP catalog to discover, price and call authorized external tools with team-scoped credentials and a user-approved budget.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-treg\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-treg\u002FSKILL.md",[136],{"categoryNo":137,"categoryName":138,"taxonomyType":139,"taxonomyTypeDesc":140},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[131,142,143,144,113,114,145,118,146,147,148,149,150,151,152,25,153,26,154,155,28],"MCP","cli","github","license","Budget","credentials","team","catalog","use","call","discover","external tools","scoped","blob",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":105,"licenseFileUrl":160,"sourceHtmlUrl":161,"categories":162,"keywords":168,"publishedAt":29},"01M6WN93MEAZ4E41DYAHJRPHQT","recruit","Turn a job description into an evidence-linked candidate shortlist through Treg, with job-related ranking and optional authorized business contact enrichment.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-recruit\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-recruit\u002FSKILL.md",[163],{"categoryNo":164,"categoryName":165,"taxonomyType":166,"taxonomyTypeDesc":167},"01JBSEEDCAT000000000000038","人力资源","PROFESSION","适用职业",[158,144,113,145,169,170,171,172,173,174,25,175,176,177,26,178,179,180,181,155,131,28],"https","email","enrichment","business","evidence","phone","ranking","post","job description","for","person","candidate","reason",{"skillNo":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":105,"licenseFileUrl":186,"sourceHtmlUrl":187,"categories":188,"keywords":189,"publishedAt":29},"01M6WN8R5RXSMHM9B4D9FAFX42","rea-growth","Analyze a company’s public growth and content through Treg, distinguish observations from hypotheses, and produce an evidence-linked playbook within an approved budget.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-rea-growth\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-rea-growth\u002FSKILL.md",[],[190,191,192,144,113,145,193,194,169,195,146,196,197,198,173,25,199,200,155,131,28],"growth","rea","rea growth","produce","content","playbook","marketing","analyze","public","observations","company",{"skillNo":202,"name":203,"nameZh":6,"description":204,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":105,"licenseFileUrl":205,"sourceHtmlUrl":206,"categories":207,"keywords":208,"publishedAt":29},"01M6WN2EVE3RQRGWAKBT4S7YT2","make-ugc","Create original AI UGC-style product videos through Treg: research hooks, approve a licensed presenter and voice, generate clips, add captions and report costs.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-make-ugc\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-make-ugc\u002FSKILL.md",[],[209,210,144,211,113,212,145,213,214,215,216,217,25,218,219,220,221,222,223,155],"make","make ugc","research","create","Video","Captions","ads","short","hooks","head","style","niche","trending","talking-head","approve",{"skillNo":225,"name":226,"nameZh":6,"description":227,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":105,"licenseFileUrl":228,"sourceHtmlUrl":229,"categories":230,"keywords":231,"publishedAt":29},"01M6WN10ARAA63Y8K1YNGXJ2RM","lead-signals","Find and qualify public buying signals through Treg, rank fitting business accounts and optionally enrich authorized business contact information.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-lead-signals\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-lead-signals\u002FSKILL.md",[],[232,233,234,144,113,145,235,236,172,237,238,25,239,240,241,242,243,244,245,155],"signals","lead","lead signals","how","find","ready","as","how to","qualify","people","information","enrich","changes","funding"]