[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M793EEBCWNZGPCK2FCPGP4Q6":3,"skill-same:01M793EEBCWNZGPCK2FCPGP4Q6":71},{"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":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M793EEBCWNZGPCK2FCPGP4Q6","simulation",null,"Choose and operate PyQuil's in-process and service-backed simulators, inspect quantum states and observables, and diagnose ordering, noise, random-state, and scaling failures.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyquil\u002Fsub-skills\u002Fsimulation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: simulation\ndescription: \"Choose and operate PyQuil's in-process and service-backed\n  simulators, inspect quantum states and observables, and diagnose ordering,\n  noise, random-state, and scaling failures.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# PyQuil simulation\n\nUse this route when the task is to simulate a small Quil `Program`, inspect a\nwavefunction or density matrix, calculate Pauli expectations, sample outcomes,\nconstruct simulation matrices, or decide whether a QVM service is required.\nThis route assumes a usable PyQuil installation and a concrete qubit count.\nFor general program construction, use [program-authoring](..\u002Fprogram-authoring\u002FSKILL.md).\nFor compilation, `QuantumComputer`, QVM\u002FQPU jobs, or QCS orchestration, use\n[compile-execute](..\u002Fcompile-execute\u002FSKILL.md). For complete channel,\nreadout, and Experiment workflows, use [noise-experiments](..\u002Fnoise-experiments\u002FSKILL.md).\n\n## First decision: local or service-backed\n\n- **Service-free local simulation:** choose `PyQVM` for a QAM-shaped execution\n  path, or use `ReferenceWavefunctionSimulator`\u002F`NumpyWavefunctionSimulator`\n  directly for a gate-only numerical path. `PyQVM(n_qubits=..., seed=...)`\n  supplies a shared random state and is the safest default when measurement,\n  sampling, control flow, or repeatable noise is involved.\n- **Service-backed wavefunction:** `pyquil.api.WavefunctionSimulator` is a\n  client for the QVM HTTP wavefunction\u002Fexpectation\u002Fmeasurement endpoints. It\n  is **not** an in-process simulator. With no QVM service, its\n  `.wavefunction(...)` call attempts HTTP and raises `api.QVMError` (typically\n  beginning `Could not communicate with QVM at ...`). Do not use it to prove\n  service-free execution.\n- **Density\u002Fnoise:** `PyQVM` with `post_gate_noise_probabilities` selects\n  `ReferenceDensitySimulator` by default. This is an experimental post-gate\n  single-qubit Kraus path, not the full noise\u002FExperiment API; route the latter\n  to [noise-experiments](..\u002Fnoise-experiments\u002FSKILL.md).\n\nRead [simulator-selection.md](references\u002Fsimulator-selection.md) before choosing\nan engine, especially when a request mentions QVM, noise, state injection, or\nmany qubits.\n\n## Minimal local workflow\n\n1. Build or receive a `Program` from [program-authoring](..\u002Fprogram-authoring\u002FSKILL.md).\n   Count the qubits explicitly; `PyQVM` allocates the full Hilbert space.\n2. For a gate-only state, use `ReferenceWavefunctionSimulator(n_qubits)` or\n   `NumpyWavefunctionSimulator(n_qubits)`, then `.do_program(program)`.\n3. For Quil\u002FQAM semantics, use `PyQVM(n_qubits, seed=integer).execute(program)`.\n   Execution requires a `Program`, resets the simulator at each `execute` call,\n   and returns the stateful `PyQVM`; inspect `qam.wf_simulator`.\n4. Validate the state before interpreting it: a wavefunction has `2**n`\n   amplitudes; the NumPy tensor has shape `(2,) * n`; a density matrix has\n   shape `(2**n, 2**n)`, is Hermitian, and has trace one.\n5. Convert results into the requested representation. Read\n   [state-and-observables.md](references\u002Fstate-and-observables.md) for exact\n   bit ordering, `Wavefunction` helpers, expectations, density observables,\n   sampling, and matrix lifting.\n6. Run the [bundled deterministic Bell check](scripts\u002Fbell_state_inprocess.py)\n   when a service-free smoke test is needed:\n   `python scripts\u002Fbell_state_inprocess.py`. Use\n   `python scripts\u002Fbell_state_inprocess.py --help` to inspect its interface;\n   it performs no network call or file write.\n\n## Engine-specific operating rules\n\n- `ReferenceWavefunctionSimulator` stores a flat canonical vector and favors\n  readable reference behavior. `NumpyWavefunctionSimulator` stores an\n  n-dimensional tensor and is the default `PyQVM` backend without noise.\n  Compare the NumPy tensor after reversing axes and flattening when comparing\n  it with the reference vector.\n- Direct simulators can apply gates and compute expectations, but stochastic\n  measurement\u002Fsampling needs `rs`. Instantiate them with a\n  `numpy.random.RandomState`, or prefer `PyQVM(seed=...)` so all stochastic\n  actions share one deterministic stream.\n- `ReferenceDensitySimulator` stores a dense matrix and supports the\n  experimental post-gate noise names `relaxation`, `dephasing`,\n  `depolarizing`, `phase_flip`, `bit_flip`, and `bitphase_flip`. Its current\n  `expectation` method raises `NotImplementedError`; compute `Tr(rho O)` with\n  a lifted Pauli matrix for a local diagnostic, or route full observable and\n  Experiment work to [noise-experiments](..\u002Fnoise-experiments\u002FSKILL.md).\n- A direct simulator's `do_program` is gate-only. `PyQVM` adds classical\n  memory\u002Fcontrol-flow plumbing, measurement, and ordinary `Program`\n  execution, but still rejects several instructions and parameterized\n  `DEFGATE`s. Treat a failure as a backend capability issue, not automatically\n  as a malformed program. See [api-reference.md](references\u002Fapi-reference.md)\n  and [troubleshooting.md](references\u002Ftroubleshooting.md).\n\n## Numerical and resource guardrails\n\n- PyQuil's canonical basis vector order is `00, 01, 10, 11, ...`, with qubit\n  `0` as the least-significant\u002Frightmost bit. Thus index `1` is bitstring `01`\n  and means q0=1. Measurement arrays and user-selected qubit lists can use a\n  different column presentation; never infer labels from array positions alone.\n- A complex128 statevector needs `16 * 2**n` bytes; a dense complex128 density\n  matrix needs `16 * 4**n` bytes, before temporary lifted matrices. Estimate\n  memory before allocating and stop early for an exponential-size request.\n- Use [api-reference.md](references\u002Fapi-reference.md) for verified signatures\n  and [state-and-observables.md](references\u002Fstate-and-observables.md) for\n  concrete shapes and matrix-ordering recipes. Use\n  [troubleshooting.md](references\u002Ftroubleshooting.md) for recovery when a\n  state is invalid, random state is absent, noise is incompatible, or a QVM\n  boundary was mistaken for local execution.\n\n## Handoff checks\n\nBefore claiming a simulation result, record the engine and version, qubit\ncount, seed policy, whether noise was applied, state shape, basis convention,\nand whether any service was contacted. Assert normalization and the expected\nordering for at least one basis state. For Bell-like checks, compare vector,\nprobabilities, `XX`\u002F`YY`\u002F`ZZ` expectations, and sampled bitstring columns across\nreference and PyQVM paths rather than comparing only a pretty-printed string.\n","# PyQuil simulation\n\nUse this route when the task is to simulate a small Quil `Program`, inspect a\nwavefunction or density matrix, calculate Pauli expectations, sample outcomes,\nconstruct simulation matrices, or decide whether a QVM service is required.\nThis route assumes a usable PyQuil installation and a concrete qubit count.\nFor general program construction, use [program-authoring](..\u002Fprogram-authoring\u002FSKILL.md).\nFor compilation, `QuantumComputer`, QVM\u002FQPU jobs, or QCS orchestration, use\n[compile-execute](..\u002Fcompile-execute\u002FSKILL.md). For complete channel,\nreadout, and Experiment workflows, use [noise-experiments](..\u002Fnoise-experiments\u002FSKILL.md).\n\n## First decision: local or service-backed\n\n- **Service-free local simulation:** choose `PyQVM` for a QAM-shaped execution\n  path, or use `ReferenceWavefunctionSimulator`\u002F`NumpyWavefunctionSimulator`\n  directly for a gate-only numerical path. `PyQVM(n_qubits=..., seed=...)`\n  supplies a shared random state and is the safest default when measurement,\n  sampling, control flow, or repeatable noise is involved.\n- **Service-backed wavefunction:** `pyquil.api.WavefunctionSimulator` is a\n  client for the QVM HTTP wavefunction\u002Fexpectation\u002Fmeasurement endpoints. It\n  is **not** an in-process simulator. With no QVM service, its\n  `.wavefunction(...)` call attempts HTTP and raises `api.QVMError` (typically\n  beginning `Could not communicate with QVM at ...`). Do not use it to prove\n  service-free execution.\n- **Density\u002Fnoise:** `PyQVM` with `post_gate_noise_probabilities` selects\n  `ReferenceDensitySimulator` by default. This is an experimental post-gate\n  single-qubit Kraus path, not the full noise\u002FExperiment API; route the latter\n  to [noise-experiments](..\u002Fnoise-experiments\u002FSKILL.md).\n\nRead [simulator-selection.md](references\u002Fsimulator-selection.md) before choosing\nan engine, especially when a request mentions QVM, noise, state injection, or\nmany qubits.\n\n## Minimal local workflow\n\n1. Build or receive a `Program` from [program-authoring](..\u002Fprogram-authoring\u002FSKILL.md).\n   Count the qubits explicitly; `PyQVM` allocates the full Hilbert space.\n2. For a gate-only state, use `ReferenceWavefunctionSimulator(n_qubits)` or\n   `NumpyWavefunctionSimulator(n_qubits)`, then `.do_program(program)`.\n3. For Quil\u002FQAM semantics, use `PyQVM(n_qubits, seed=integer).execute(program)`.\n   Execution requires a `Program`, resets the simulator at each `execute` call,\n   and returns the stateful `PyQVM`; inspect `qam.wf_simulator`.\n4. Validate the state before interpreting it: a wavefunction has `2**n`\n   amplitudes; the NumPy tensor has shape `(2,) * n`; a density matrix has\n   shape `(2**n, 2**n)`, is Hermitian, and has trace one.\n5. Convert results into the requested representation. Read\n   [state-and-observables.md](references\u002Fstate-and-observables.md) for exact\n   bit ordering, `Wavefunction` helpers, expectations, density observables,\n   sampling, and matrix lifting.\n6. Run the [bundled deterministic Bell check](scripts\u002Fbell_state_inprocess.py)\n   when a service-free smoke test is needed:\n   `python scripts\u002Fbell_state_inprocess.py`. Use\n   `python scripts\u002Fbell_state_inprocess.py --help` to inspect its interface;\n   it performs no network call or file write.\n\n## Engine-specific operating rules\n\n- `ReferenceWavefunctionSimulator` stores a flat canonical vector and favors\n  readable reference behavior. `NumpyWavefunctionSimulator` stores an\n  n-dimensional tensor and is the default `PyQVM` backend without noise.\n  Compare the NumPy tensor after reversing axes and flattening when comparing\n  it with the reference vector.\n- Direct simulators can apply gates and compute expectations, but stochastic\n  measurement\u002Fsampling needs `rs`. Instantiate them with a\n  `numpy.random.RandomState`, or prefer `PyQVM(seed=...)` so all stochastic\n  actions share one deterministic stream.\n- `ReferenceDensitySimulator` stores a dense matrix and supports the\n  experimental post-gate noise names `relaxation`, `dephasing`,\n  `depolarizing`, `phase_flip`, `bit_flip`, and `bitphase_flip`. Its current\n  `expectation` method raises `NotImplementedError`; compute `Tr(rho O)` with\n  a lifted Pauli matrix for a local diagnostic, or route full observable and\n  Experiment work to [noise-experiments](..\u002Fnoise-experiments\u002FSKILL.md).\n- A direct simulator's `do_program` is gate-only. `PyQVM` adds classical\n  memory\u002Fcontrol-flow plumbing, measurement, and ordinary `Program`\n  execution, but still rejects several instructions and parameterized\n  `DEFGATE`s. Treat a failure as a backend capability issue, not automatically\n  as a malformed program. See [api-reference.md](references\u002Fapi-reference.md)\n  and [troubleshooting.md](references\u002Ftroubleshooting.md).\n\n## Numerical and resource guardrails\n\n- PyQuil's canonical basis vector order is `00, 01, 10, 11, ...`, with qubit\n  `0` as the least-significant\u002Frightmost bit. Thus index `1` is bitstring `01`\n  and means q0=1. Measurement arrays and user-selected qubit lists can use a\n  different column presentation; never infer labels from array positions alone.\n- A complex128 statevector needs `16 * 2**n` bytes; a dense complex128 density\n  matrix needs `16 * 4**n` bytes, before temporary lifted matrices. Estimate\n  memory before allocating and stop early for an exponential-size request.\n- Use [api-reference.md](references\u002Fapi-reference.md) for verified signatures\n  and [state-and-observables.md](references\u002Fstate-and-observables.md) for\n  concrete shapes and matrix-ordering recipes. Use\n  [troubleshooting.md](references\u002Ftroubleshooting.md) for recovery when a\n  state is invalid, random state is absent, noise is incompatible, or a QVM\n  boundary was mistaken for local execution.\n\n## Handoff checks\n\nBefore claiming a simulation result, record the engine and version, qubit\ncount, seed policy, whether noise was applied, state shape, basis convention,\nand whether any service was contacted. Assert normalization and the expected\nordering for at least one basis state. For Bell-like checks, compare vector,\nprobabilities, `XX`\u002F`YY`\u002F`ZZ` expectations, and sampled bitstring columns across\nreference and PyQVM paths rather than comparing only a pretty-printed string.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fpyquil\u002Fsub-skills\u002Fsimulation",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill simulation",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill simulation",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill simulation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyquil\u002Fsub-skills\u002Fsimulation\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",6477,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyquil\u002Fsub-skills\u002Fsimulation\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fsimulator-selection.md",5746,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyquil\u002Fsub-skills\u002Fsimulation\u002Freferences\u002Fsimulator-selection.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fstate-and-observables.md",5972,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyquil\u002Fsub-skills\u002Fsimulation\u002Freferences\u002Fstate-and-observables.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",6958,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyquil\u002Fsub-skills\u002Fsimulation\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fbell_state_inprocess.py","SCRIPT","脚本",2362,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyquil\u002Fsub-skills\u002Fsimulation\u002Fscripts\u002Fbell_state_inprocess.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]