[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M793EBVHMZKZFD8RK6SNHN1F":3,"skill-same:01M793EBVHMZKZFD8RK6SNHN1F":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},"01M793EBVHMZKZFD8RK6SNHN1F","program-authoring",null,"Enables construction, inspection, transformation, serialization, and diagram generation for PyQuil Programs, Quil, and Quil-T without executing a quantum job.","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\u002Fprogram-authoring\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: program-authoring\ndescription: \"Enables construction, inspection, transformation, serialization,\n  and diagram generation for PyQuil Programs, Quil, and Quil-T without executing\n  a quantum job.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Program authoring\n\nUse this route when the task is about writing or understanding Quil rather than\nsubmitting it: `Program`, standard gates, `DECLARE`, `MEASURE`, memory\nreferences, placeholders, custom gates, classical labels\u002Fbranches, `PRAGMA`,\nQuil-T definitions, `out()`, parsing, or LaTeX diagrams.\n\nThis sub-skill constructs and validates program text locally. It does **not**\ncompile, submit, simulate, estimate noise, query a processor, or prove that a\nQPU\u002FQVM\u002Fservice accepts a program.\n\n## Route the task first\n\n| Request | Use |\n|---|---|\n| Build, parse, compose, parameterize, address, inspect, or serialize Quil | This sub-skill |\n| Compile, select a `QuantumComputer`, call QAM\u002FQVM\u002FQPU, or inspect job results | [`compile-execute`](..\u002Fcompile-execute\u002FSKILL.md) |\n| Obtain statevectors, probabilities, expectations, or local numerical dynamics | [`simulation`](..\u002Fsimulation\u002FSKILL.md) |\n| Build `NoiseModel`, Pauli, `Experiment`, calibration, or estimation workflows | [`noise-experiments`](..\u002Fnoise-experiments\u002FSKILL.md) |\n| Build or inspect topology, ISA, processor connectivity, or gate availability | [`processor-isa`](..\u002Fprocessor-isa\u002FSKILL.md) |\n\nRead [`api-reference.md`](references\u002Fapi-reference.md) before relying on a\nsignature or subtle mutability\u002Fserialization rule. Read\n[`workflows.md`](references\u002Fworkflows.md) for end-to-end authoring recipes.\nRead [`quil-t-and-diagrams.md`](references\u002Fquil-t-and-diagrams.md) for pulse,\nframe, calibration, waveform, or LaTeX work. Read\n[`troubleshooting.md`](references\u002Ftroubleshooting.md) after an exception or\nwhen a program looks valid in Python but its Quil is suspect.\n\nFor a deterministic, service-free Bell construction and canonical Quil check,\nrun [`scripts\u002Fbuild_bell_program.py`](scripts\u002Fbuild_bell_program.py). It only\nconstructs and serializes a `Program`; it never calls a compiler, QVM, QPU, or\nexternal service:\n\n```bash\npython scripts\u002Fbuild_bell_program.py --help\npython scripts\u002Fbuild_bell_program.py --validate-only\npython scripts\u002Fbuild_bell_program.py\n```\n\n## Authoring contract\n\n1. Import `Program` from `pyquil`; import gates from `pyquil.gates`; use\n   `pyquil.quilatom` for `MemoryReference`, `Parameter`, placeholders, labels,\n   frames, and waveform invocations; use `pyquil.quilbase` for instruction and\n   definition classes.\n2. Construct from typed instructions where possible. `Program(...)`, `.inst`,\n   `+=`, `+`, and Quil strings are supported. Keep the source `Program` when a\n   second variant is needed: `+` and `.copy()` avoid accidental edits to the\n   original, while `.inst`, `+=`, `.measure`, `.declare`, and\n   `.wrap_in_numshots_loop` mutate it.\n3. Declare every memory region intentionally and retain the returned base\n   `MemoryReference`. Check offsets yourself, especially for parsed or manually\n   created references whose declaration size is unknown.\n4. Resolve every `QubitPlaceholder` and `LabelPlaceholder` before calling\n   `out()` for submission-shaped Quil. Prefer `address_qubits(program, mapping)`\n   when a physical mapping is part of the requirement; it returns a copy.\n5. Treat `program.out()` as a local serialization observation. Round-trip with\n   `Program(program.out()).out()` when a stable Quil representation is needed;\n   this is parsing\u002Fserialization validation, not execution validation.\n6. Use `wrap_in_numshots_loop(shots)` only to set `program.num_shots`; it does\n   not add a Quil loop and does not run shots. For an actual Quil loop, use\n   `with_loop` with an `INTEGER` counter and explicit labels.\n7. Use `out(calibrations=False)` only to omit calibration definitions. It can\n   still contain other Quil-T\u002Fglobal definitions such as frames and waveforms.\n   Use `remove_quil_t_instructions()` only when a deliberately stripped,\n   non-Quil-T variant is wanted; it is not a general compiler compatibility\n   proof.\n8. For custom gates, validate matrix shape\u002Funitarity, parameter count, and\n   qudit argument count explicitly before composing. For classical branches,\n   declare and populate the condition memory, then resolve generated labels.\n9. For LaTeX, prefer `to_latex(program)` when the required output is source\n   text. `display(program)` additionally needs IPython plus `pdflatex`,\n   ImageMagick `convert`, and a suitable LaTeX installation; neither function\n   executes the program.\n\n## Quick local skeleton\n\n```python\nfrom pyquil import Program\nfrom pyquil.gates import CNOT, H, MEASURE\n\nprogram = Program()\nro = program.declare(\"ro\", \"BIT\", 2)\nprogram += [H(0), CNOT(0, 1)]\nprogram += [MEASURE(0, ro[0]), MEASURE(1, ro[1])]\nquil_text = program.out()\nassert Program(quil_text).out() == quil_text\n```\n\nThe expected output is ordinary Quil beginning with `DECLARE ro BIT[2]`, then\n`H 0`, `CNOT 0 1`, and the two measurements. This confirms construction and\nround-trip parsing only. Hand the validated `Program` to\n[`compile-execute`](..\u002Fcompile-execute\u002FSKILL.md), [`simulation`](..\u002Fsimulation\u002FSKILL.md),\nor [`noise-experiments`](..\u002Fnoise-experiments\u002FSKILL.md) only when that later\nworkflow is explicitly requested.\n","# Program authoring\n\nUse this route when the task is about writing or understanding Quil rather than\nsubmitting it: `Program`, standard gates, `DECLARE`, `MEASURE`, memory\nreferences, placeholders, custom gates, classical labels\u002Fbranches, `PRAGMA`,\nQuil-T definitions, `out()`, parsing, or LaTeX diagrams.\n\nThis sub-skill constructs and validates program text locally. It does **not**\ncompile, submit, simulate, estimate noise, query a processor, or prove that a\nQPU\u002FQVM\u002Fservice accepts a program.\n\n## Route the task first\n\n| Request | Use |\n|---|---|\n| Build, parse, compose, parameterize, address, inspect, or serialize Quil | This sub-skill |\n| Compile, select a `QuantumComputer`, call QAM\u002FQVM\u002FQPU, or inspect job results | [`compile-execute`](..\u002Fcompile-execute\u002FSKILL.md) |\n| Obtain statevectors, probabilities, expectations, or local numerical dynamics | [`simulation`](..\u002Fsimulation\u002FSKILL.md) |\n| Build `NoiseModel`, Pauli, `Experiment`, calibration, or estimation workflows | [`noise-experiments`](..\u002Fnoise-experiments\u002FSKILL.md) |\n| Build or inspect topology, ISA, processor connectivity, or gate availability | [`processor-isa`](..\u002Fprocessor-isa\u002FSKILL.md) |\n\nRead [`api-reference.md`](references\u002Fapi-reference.md) before relying on a\nsignature or subtle mutability\u002Fserialization rule. Read\n[`workflows.md`](references\u002Fworkflows.md) for end-to-end authoring recipes.\nRead [`quil-t-and-diagrams.md`](references\u002Fquil-t-and-diagrams.md) for pulse,\nframe, calibration, waveform, or LaTeX work. Read\n[`troubleshooting.md`](references\u002Ftroubleshooting.md) after an exception or\nwhen a program looks valid in Python but its Quil is suspect.\n\nFor a deterministic, service-free Bell construction and canonical Quil check,\nrun [`scripts\u002Fbuild_bell_program.py`](scripts\u002Fbuild_bell_program.py). It only\nconstructs and serializes a `Program`; it never calls a compiler, QVM, QPU, or\nexternal service:\n\n```bash\npython scripts\u002Fbuild_bell_program.py --help\npython scripts\u002Fbuild_bell_program.py --validate-only\npython scripts\u002Fbuild_bell_program.py\n```\n\n## Authoring contract\n\n1. Import `Program` from `pyquil`; import gates from `pyquil.gates`; use\n   `pyquil.quilatom` for `MemoryReference`, `Parameter`, placeholders, labels,\n   frames, and waveform invocations; use `pyquil.quilbase` for instruction and\n   definition classes.\n2. Construct from typed instructions where possible. `Program(...)`, `.inst`,\n   `+=`, `+`, and Quil strings are supported. Keep the source `Program` when a\n   second variant is needed: `+` and `.copy()` avoid accidental edits to the\n   original, while `.inst`, `+=`, `.measure`, `.declare`, and\n   `.wrap_in_numshots_loop` mutate it.\n3. Declare every memory region intentionally and retain the returned base\n   `MemoryReference`. Check offsets yourself, especially for parsed or manually\n   created references whose declaration size is unknown.\n4. Resolve every `QubitPlaceholder` and `LabelPlaceholder` before calling\n   `out()` for submission-shaped Quil. Prefer `address_qubits(program, mapping)`\n   when a physical mapping is part of the requirement; it returns a copy.\n5. Treat `program.out()` as a local serialization observation. Round-trip with\n   `Program(program.out()).out()` when a stable Quil representation is needed;\n   this is parsing\u002Fserialization validation, not execution validation.\n6. Use `wrap_in_numshots_loop(shots)` only to set `program.num_shots`; it does\n   not add a Quil loop and does not run shots. For an actual Quil loop, use\n   `with_loop` with an `INTEGER` counter and explicit labels.\n7. Use `out(calibrations=False)` only to omit calibration definitions. It can\n   still contain other Quil-T\u002Fglobal definitions such as frames and waveforms.\n   Use `remove_quil_t_instructions()` only when a deliberately stripped,\n   non-Quil-T variant is wanted; it is not a general compiler compatibility\n   proof.\n8. For custom gates, validate matrix shape\u002Funitarity, parameter count, and\n   qudit argument count explicitly before composing. For classical branches,\n   declare and populate the condition memory, then resolve generated labels.\n9. For LaTeX, prefer `to_latex(program)` when the required output is source\n   text. `display(program)` additionally needs IPython plus `pdflatex`,\n   ImageMagick `convert`, and a suitable LaTeX installation; neither function\n   executes the program.\n\n## Quick local skeleton\n\n```python\nfrom pyquil import Program\nfrom pyquil.gates import CNOT, H, MEASURE\n\nprogram = Program()\nro = program.declare(\"ro\", \"BIT\", 2)\nprogram += [H(0), CNOT(0, 1)]\nprogram += [MEASURE(0, ro[0]), MEASURE(1, ro[1])]\nquil_text = program.out()\nassert Program(quil_text).out() == quil_text\n```\n\nThe expected output is ordinary Quil beginning with `DECLARE ro BIT[2]`, then\n`H 0`, `CNOT 0 1`, and the two measurements. This confirms construction and\nround-trip parsing only. Hand the validated `Program` to\n[`compile-execute`](..\u002Fcompile-execute\u002FSKILL.md), [`simulation`](..\u002Fsimulation\u002FSKILL.md),\nor [`noise-experiments`](..\u002Fnoise-experiments\u002FSKILL.md) only when that later\nworkflow is explicitly requested.\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\u002Fprogram-authoring",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 program-authoring",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill program-authoring",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill program-authoring","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyquil\u002Fsub-skills\u002Fprogram-authoring\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",10183,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyquil\u002Fsub-skills\u002Fprogram-authoring\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fquil-t-and-diagrams.md",7194,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyquil\u002Fsub-skills\u002Fprogram-authoring\u002Freferences\u002Fquil-t-and-diagrams.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",8880,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyquil\u002Fsub-skills\u002Fprogram-authoring\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fworkflows.md",8433,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyquil\u002Fsub-skills\u002Fprogram-authoring\u002Freferences\u002Fworkflows.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fbuild_bell_program.py","SCRIPT","脚本",2604,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyquil\u002Fsub-skills\u002Fprogram-authoring\u002Fscripts\u002Fbuild_bell_program.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",[],[]]