GuillaumeLessard
OrganizationOfficial Claude Code plugin and claude.ai skill bundle for QECTOR: local quantum error correction decoding with qector-decoder-v3 via MCP. 24 skills, 5 agents, local stdio MCP server.
Categories
Indexed Skills (71)
algorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
claude-api
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST
docx
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
frontend-design
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
pptx
Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.
slack-gif-creator
Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
xlsx
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
algorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
claude-api
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST
docx
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
frontend-design
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
pptx
Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.
slack-gif-creator
Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
xlsx
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
qector-core
Core domain knowledge and verified facts for the QECTOR quantum error correction platform (plugin v1.0.6, decoder wheel 1.0.0). Covers the app-free library MCP server (8 stable tools), the opt-in research server (29 provisional tools including the evidence layer), the privileged admin server (3 tools), 11 slash commands, 5 specialized agents, and mathematical grounding against all 16 Theorems and Appendices A-E from Reference Manual v1.0.0 (DOI 10.5281/zenodo.21941046). Enforces strict-math obligations (H c = s mod 2, logical coset scoring, Wilson 95% CI) and local-by-default operation with an opt-in PyPI freshness check.
qector-developer
Software engineering integration content for QECTOR: wiring the MCP servers into applications, driving the stdio JSON-RPC 2.0 protocol, high-performance batch / mmap decoding, building codes from matrices, the verified library API, and the companion bench server (Provisional). Load when a user is writing code, integrating QECTOR, or debugging an integration against qector-decoder-v3 or the Workbench MCP server.
qector-educator
Teaching and documentation content for quantum error correction with QECTOR: beginner-to-advanced tutorials, ELI5 explanations of syndromes / decoders / parity checks, Tanner-graph visual explanations, and local Markdown teaching material. Load for explanations, course material, or documentation generation.
qector-math-foundations
The strict mathematical ground rules for every QECTOR claim. Encodes the F2 notation, the 16 correctness theorems, the Wilson 95% score interval for LER, the required-artifact- metadata contract, safe-wording rules, and the published limitations that must travel with every claim (reference manual v1.0.0, DOI 10.5281/zenodo.21941046). Load whenever any number, theorem, comparison, or benchmark is produced, repeated, or quoted - the rules here are the authority and nothing may contradict them.
qector-researcher
Quantum error correction research workflows on the QECTOR platform: threshold discovery, finite-size scaling, LER benchmarking with confidence intervals, decoder comparison, and publication-grade reproducibility artifacts. Uses the library MCP server (8 frozen tools) and the bench MCP server (29 provisional tools) for the math and DEM utilities. Load when a user wants to evaluate a code family, estimate a threshold, compare decoders, or produce paper-ready results.
qector-sysadmin
Operations, runtime configuration, security, and device-local health of QECTOR deployments. The library path uses `compat_report` and `get_license_info`; the companion research server adds `hardware_probe`, `license_active_check`, and `env_block`. Workbench probing is an admin tool. `compat_report` is also available via the library. Any Workbench health tools must be discovered on the target device. Load for uptime, hardware, or security questions.
qector-hardware-engineer
Physical-layer quantum circuits, detector-error-model preparation, qLDPC reasoning, and honest target-device hardware reporting for QECTOR. The bundled library MCP server is app-free; the companion bench server adds DEM inspection, DEM collapse, code-family introspection, and hardware probes (all Provisional). Optional Stim, GPU, and Workbench surfaces require separate dependency and API checks. Load for circuit-to-decode workflows, target-device reporting, and any question that involves a real QPU.
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
qector-architecture
QECTOR architecture overview: the Rust core / Python layer FFI boundary, the module map, the threading and memory models, the layering of services, and the bit-determinism guarantee. Load for any question about the engine's internals, where a class lives, how the GIL interacts with the decode call, or why batch decode is reproducible across worker counts.
qector-batch-decoding
Batch, streaming, and GPU-accelerated decoding paths for QECTOR. Covers the manual 13 CUDA / OpenCL bit-identity contract, the per-thread scratch sizing formula (manual 13.4), the warm-up / dispatch / hot-path pattern, the worker-thread determinism guarantee (manual 26.3), and the cold-path / hot-path reporting rule. Load when a question involves millions of shots, GPU acceleration, batch decode, or performance tuning.
qector-bp-osd
Belief propagation with ordered-statistics post-processing (BP-OSD) for QECTOR. Covers the box-plus kernel phi(x) = -ln(tanh(x/2)), the log-domain sum-product / min-sum / relay schedules, the OSD-0 / OSD-W solve (Theorem 11), the ambiguity-cluster partition (Theorem 12), and the worked examples from the v1.0.0 reference manual (chapters 8 and 9). Load for any qLDPC, hyperedge, or non-graphlike question, or for the BP-OSD tuning surface.
qector-codes-builder
Building and inspecting QEC codes for QECTOR. Covers the v1.0.0 library code families (repetition, ring, rotated_surface, unrotated_surface, toric, heavy_hex, color_code), the legacy `generate_*_checks` generators, and the custom-matrix / hypergraph-product / bicycle paths. Load when a question asks "what code should I use?", "how do I build a code from H?", or "is this code graphlike?".
qector-decoders-deep-dive
Per-decoder internals from the v1.0.0 reference manual. For each of the fifteen specialised backends, gives the algorithm, the theorem(s) it inherits, its claim boundary, and a one-line code snippet. Load when a question asks "how does X work", "which decoder is right for Y", or "what is the difference between A and B" at the algorithmic level (manual chapters 4-13).
qector-dem-pipeline
Detector error model (DEM) parsing, collapse, priors, and routing for QECTOR. Covers the manual 14 collapse rule (independent-XOR combination p = p1(1-p2) + p2(1-p1)), per-mechanism prior recalibration, the graphlike/hyperedge boundary, and the worked example p1=0.01, p2=0.02 -> p=0.0296, weight=ln(0.9704/0.0296)=3.489. Load for any DEM-related work: parsing .stim DEMs, building decoders from a DEM, weight calculations, and the matching-graph vs BP-OSD routing decision.
qector-deployment
QECTOR deployment modes, security posture, and the production checklist. Covers the six deployment modes (manual 24, Table 24.1), the production checklist (manual 24.1, 10 items), the service hardening rules (10 MB cap, bearer token, strict decoder-type enum), the zero-egress policy, the package-provenance rule, the SHA-256 checksums-sha256.txt rule, and the "service behind TLS and a reverse proxy" rule. Load for any question about deploying, hosting, exposing, or shipping QECTOR in any non-local context.
qector-glossary
QECTOR terminology, notation, and symbols from the v1.0.0 reference manual (Appendix A and B). Load for any question about what a term means, what symbol is used, or how the notation is written.
qector-ler-methodology
Logical error rate (LER) methodology for QECTOR. Covers the Wilson 95% score interval, the chapter 22.3 required-artifact metadata block, the code_capacity / circuit_level tagging rule, safe / unsafe wording, and the screening-estimate caveat. Load for any LER report, threshold sweep, or competitive comparison.
qector-licensing
QECTOR licensing, tier enforcement, and key activation. Covers the three license tiers (Community d<=7, Pro d<=19, Enterprise d<=63), the Ed25519-signed token formats (QECT-PRO-*, QECT-ENT-*, v2), the resolution order (QECTOR_LICENSE_KEY, QECTOR_LICENSE_FILE, ~/.qector/license.key), the QECTOR_ENFORCE / QECTOR_SILENT / QECTOR_CRL_PATH environment variables, the offline verification, and the licensing-gate vs hardware-probe distinction. Load for any question about license tiers, key activation, tier limits, or what an Enterprise key unlocks.
qector-orchestration
Routing, dispatch, and orchestration in QECTOR (manual chapter 11). Covers the structural validity predicate (max qubit degree), the recommend_decoder policy, Theorem 14 (AutoDecoder dispatch faithfulness), the 7-tier self-debugging fallback chain (native auto, CUDA, OpenCL, Rayon batch, CPU batch, single-thread, Blossom, lookup table, BP-OSD), the syndrome-verification between tiers, the GPU-permanent-disable rule, and the hybrid cascade pre-filter (UF + exact fallback). Load for any question about which decoder to choose, why a particular backend was picked, or how the fallback chain works.
qector-pymatching-compat
The PyMatching-compatible shim in qector-decoder-v3 (manual 17.1). Covers `qector_decoder_v3.pymatching_compat.Matching` as a drop-in for `pymatching.Matching`, the supported methods (from_check_matrix, from_detector_error_model, add_edge, add_boundary_edge, decode, decode_batch, decode_to_edges_array), the fact that it is backed by the exact Blossom decoder, the one-line import swap, and the smoke test pattern via `qector-research.pymatching_compat_check`. Load for any question about PyMatching compatibility, Stim / PyMatching pipelines, or a one-line decoder swap.
qector-release-engineering
QECTOR release engineering, wheel-only distribution, the chunked base64 Rust-core delivery, feature flags in published wheels, the pre-flight gates, and the v2 token format. Load for any question about packaging, building, releasing, the RUST_SRC_B64_* secrets bundle, the promotion of a Provisional symbol to stable, or the qector.store / PyPI flow.
qector-reproducibility
Reproducibility and claim boundaries for QECTOR (manual 19, 22, 27, Appendix D). Covers the chapter 22.3 required-artifact metadata, the safe / unsafe wording rule (manual 22.5), the reproduction commands in Appendix D, the competitive-harness pipeline (same Stim circuit, same samples, same DEM, same observable scoring), the withdrawn benchmark policy, and the hot/cold path label. Load for any question about how to reproduce a result, what counts as evidence, or how to write a paper-ready claim.
qector-roadmap
QECTOR roadmap and promotion path (manual 27). Covers the four-step Provisional-to-stable promotion bar, the artifact roadmap, the candidate engineering items (CUDA primary context sharing, OpenCL side-wheel, hypergraph rejection testing), and the 1.x release policy. Load for any question about what is coming, what is a candidate, and when a Provisional symbol can be promoted.
qector-services
QECTOR service surfaces: REST (FastAPI / Flask), gRPC, MCP stdio, Prometheus metrics exporter (manual 17.4). Covers the Provisional status, the production checklist (manual 24.1), the request-size cap, the bearer-token check, the per-client rate limit, the strict decoder-type enum, the deployment modes (manual 24, Table 24.1), and the fact that the bundled local stdio wrapper is the supported service surface in this package. Load for any question about service hardening, deployment, REST, gRPC, metrics, or production posture.
qector-sinter
Sinter decoder entry points for QECTOR (manual 17.2). Covers `qector_sinter_decoders()` returning qector_blossom, qector_belief, qector_unionfind, qector_bposd, qector_unionfind_unweighted, the role of these in the community-standard sinter benchmark harness, and the qector-research.sinter_decoder_list probe. Load for any question about sinter, the community benchmark, or head-to-head LER comparisons.
qector-space-time
Space-time and streaming decoding for QECTOR. Covers the (2+1)D detector lattice, the detector-difference formulation d_{c,t} = s_{c,t} xor s_{c,t-1}, the space-time lifting theorem (manual 10.2), the streaming primitives (OR-accumulated history, exponentially decayed window), the truncation bound ||S_W - S_inf||_1 <= lambda^W / (1 - lambda) * ||s||_inf, and the Python layer's "decode per round" scope (manual 10.3). Load for any question about measurement errors, glitch absorption, multi- round decoding, or windowed commit latency.
qector-testing-strategy
The QECTOR testing and validation strategy (manual 23). Covers the eight validation layers (syndrome faithfulness, property- based, exhaustive oracle, cross-decoder equivalence, DEM pipeline, LER parity, qLDPC correctness, memory behaviour, API stability, GPU kernels), the stale test-count policy, the cross-decoder equivalence tests (batch == per-shot; UF == FastUF; GPU == CPU), and the hardware-gated GPU test policy. Load for any question about how a result is verified, what tests are required, or what the "stale" notice means.
qector-two-stage-css
Two-stage CSS decoding for QECTOR (manual chapter 12). Independent X and Z decoders assume P(X, Z) = P(X) P(Z); depolarising noise violates this. Two-stage decoding removes the cross-talk explicitly. Load for any question about depolarising noise, CSS sector coupling, feedforward X->Z syndrome updates, or the Theorem 13 joint-faithfulness guarantee.
qector-workbench
The optional QECTOR Workbench desktop application (manual 17.5, 20). Covers the device-local stdio MCP integration, the historical changelog (0.7.0 -> 1.0.0), the explicit provisional / non-frozen classification, the fact that the Workbench is absent from the shipped wheel, the headless application controller (workbench.py), the benchmark job queue, the JSON / CSV / PDF export, the environment snapshot, the git commit, and the qector-admin.workbench_probe tool. Load for any question about the Workbench, the optional app, or how to probe a target device.
qector-core
Core domain knowledge and verified facts for the QECTOR quantum error correction platform. Covers BOTH first-class surfaces with equal validity: (1) qector-decoder-v3, the pip-installed Rust/PyO3 library, fully functional with NO desktop app, and (2) the QECTOR Workbench MCP server (82 tools), optional extension. Load whenever a request involves quantum error correction, decoders, code families, thresholds, syndromes, benchmarking, or the QECTOR MCP tool surface. Enforces the strict-math ground-truth rules (skills/qector-math-foundations) and prevents API hallucination by grounding every tool name, decoder, and API signature in what was actually verified.
qector-developer
Software engineering integration content for QECTOR: wiring the MCP servers into applications, driving the stdio JSON-RPC 2.0 protocol, batch/mmap decoding, building codes from matrices, and the verified library API. Load when a user is writing code, integrating QECTOR, or debugging an integration against qector-decoder-v3 or the Workbench MCP server.
qector-educator
Teaching and documentation content for quantum error correction with QECTOR: beginner-to-advanced tutorials, ELI5 explanations of syndromes/decoders/ parity checks, Tanner-graph visual explanations, `export_figure` and Documentation Studio exports (Markdown/HTML/JSON/LaTeX/PDF/SVG + Zenodo metadata). Load for explanations, course material, or documentation generation.
qector-math-foundations
The flawlessly strict mathematical ground rules for every QECTOR claim. Encodes the F2 notation, the 16 correctness theorems, the Wilson score interval for LER, the required-artifact-metadata contract, safe-wording rules, and the published limitations that must travel with every claim (reference manual v1.0.0, DOI 10.5281/zenodo.21941046). Load whenever any number, theorem, comparison, or benchmark is produced, repeated, or quoted - the rules here are the authority and nothing may contradict them.
qector-researcher
Quantum error correction research workflows on the QECTOR platform: threshold discovery, finite-size scaling, LER benchmarking with confidence intervals, decoder comparison, and publication-grade reproducibility artifacts. Load when a user wants to evaluate a code family, estimate a threshold, compare decoders, or produce paper-ready results.
qector-hardware-engineer
Physical-layer quantum circuits to QECTOR decode workflows: importing Stim (.stim) circuits (`import_stim`), building Detector Error Models (`build_dem`, `decode_dem`), qLDPC/hyperedge decoding (`decode_hyperedge`, `bp_osd`, `bivariate_bicycle`), and honest hardware reporting (`get_hardware_info`, `self_diagnostics`). Load for circuit-noise, Stim, DEM, FPGA/GPU, or hardware-acceleration questions.
qector-sysadmin
Operations, licensing, security, and health of QECTOR deployments: MCP server health (`mcp_health`, `self_diagnostics`, `get_backend_health`, `doctor_diagnostics`), license tier verification (`get_license_info`, `verify_license_token`, `set_license_key_file`), environment variables, data directories, and the zero-egress governance rules. Load for uptime, licensing, hardware, or security questions.
doc-coauthoring
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
run-qector
Operating the QECTOR Workbench headlessly through the verified qector_decoder_v3.workbench controller: running real .stim / .dem decode benchmarks on a cancelable background job queue, computing LER when a circuit with observables is loaded, exporting artifacts to JSON / CSV / PDF, and checking license state. Load when a user wants to run QECTOR Workbench benchmarks, load circuits, generate benchmark artifacts, or use the rest_api HTTP surface.
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.
doc-coauthoring
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
run-qector
Operating the QECTOR Workbench headlessly through the verified qector_decoder_v3.workbench controller: running real .stim / .dem decode benchmarks on a cancelable background job queue, computing LER when a circuit with observables is loaded, exporting artifacts to JSON / CSV / PDF, and checking license state. Load when a user wants to run QECTOR Workbench benchmarks, load circuits, generate benchmark artifacts, or use the rest_api HTTP surface.
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.
qector-validator
Formal verification, mathematical obligation checks, and governance protocols for QECTOR quantum error correction workflows.
qector-validator
Formal verification, mathematical obligation checks, and governance protocols for QECTOR quantum error correction workflows.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.