「path」の検索結果

生成芯片功能模块微架构文档（MAS、FSM、数据通路、验证计划、DFT）。Generate microarchitecture specification for chiplet modules. Trigger: /bb-mas, 微架构文档, MAS, FSM, datapath, verification plan, DFT

日本語の概要は準備中です。原文の説明を表示しています。

从 MAS（clock_domains / io_timing / path_exceptions）派生 Synopsys SDC 时序约束文件，OpenSTA 语法校验。触发场景：(1) bba-guru-synthesis 综合前；(2) post-PD timing fail 修订约束；(3) 显式 /bb-create-sdc。

日本語の概要は準備中です。原文の説明を表示しています。

调用 Yosys 0.35 对 RTL 进行逻辑综合并技术映射到 ASAP7 标准单元，产出门级网表 + QoR 报告。支持并行综合（基于空闲CPU数量）。Workflow: (1)生成综合脚本;(2)并行执行综合;(3)LLM检查结果并迭代优化。触发场景：(1) bba-guru-synthesis 已完成 SDC 与 CDC 检查、需要生成 netlist；(2) PD 反馈 area/path 超标需要重综合；(3) 显式 /bb-invoke-yosys。

日本語の概要は準備中です。原文の説明を表示しています。

**[DEPRECATED in v1.3 — common path uses bb-invoke-yosys' embedded ABC]** 独立调用 ABC（Berkeley Logic Synthesis）做逻辑优化，仅 `mapping_effort=high` 等高级调优场景使用。触发场景：(1) bb-invoke-yosys `chain_to_abc=true` 时；(2) 显式 /bb-invoke-abc 调试。

日本語の概要は準備中です。原文の説明を表示しています。

资深RTL设计工程师，根据微架构文档（MAS、FSM、datapath）编写可综合的 SystemVerilog HDL代码。Generate synthesizable SystemVerilog RTL from MAS documents. Trigger: /bb-rtl-coder, RTL实现, SystemVerilog代码, 可综合HDL

日本語の概要は準備中です。原文の説明を表示しています。

Use when the user asks a question about how things in the codebase or wiki relate — what connects two things, how something works end to end, what depends on what, or what a concept means in this repo. Answers from the knowledge graph in graphify-out/graph.json, with source-location citations. Trigger on "/graph-query", "ask the graph", "what connects X to Y", "trace how X works", "explain <concept> from the graph", "shortest path between".

日本語の概要は準備中です。原文の説明を表示しています。

Explainability (XAI) audit for products containing AI components. Five-stage tier-scaled check: risk classification, stakeholder×question matrix, fidelity audit, system card, recourse path. Honest about what was validated functionally vs what needs user testing.

日本語の概要は準備中です。原文の説明を表示しています。

Derive the binding properties your why/how/what impose on everything below them, so no solution can silently contradict your own product definition. Retrofit entry point for projects that started before v0.120.0; also the re-derive path when why/how/what change and every stance below them goes stale.

日本語の概要は準備中です。原文の説明を表示しています。

Use when writing, reviewing, or optimizing CUDA kernels targeting sm_120a (RTX 5090 / Consumer Blackwell, GB202) in the imp inference engine. Triggers on CUDA/PTX kernel code, shared-memory layout, bank conflicts, tensor-core MMA (mxf4nvf4, tf32, 3xTF32/3xFP16), GEMV/GEMM/attention/quantization/GDN-scan kernels, decode tok/s under expected, kernel emitting HMMA instead of mxf4nvf4, occupancy, register pressure, __launch_bounds__, spills, PDL. Pair with `benchmark-cuda` for measurement and `check-degeneration` after hot-path changes.

日本語の概要は準備中です。原文の説明を表示しています。

Use when imp outputs differ between two paths that should agree - chunk sizes, prefill vs decode, prefix-cache resend, two engines (imp vs llama.cpp vs HF), two builds or kernels - "output changes with chunk size", "first token differs", "logprobs moved", "which layer diverges", "who is right, imp or llama.cpp", "near-tie". Do NOT use for repetition loops or garbage output (check-degeneration), a new arch that loads wrong (add-model-arch), or perf (benchmark-cuda).

日本語の概要は準備中です。原文の説明を表示しています。

Use when working on imp's quantization formats, loaders, or dequant paths - GGUF Q4_0...Q8_0/Q*_K/IQ4/MXFP4, NVFP4 two-level scaling (Modelopt vs compressed-tensors layouts), FP8 E4M3, StorageTier, decode cache, KV-cache dtypes (auto/fp16/fp8/int8/int4/nvfp4/mxfp4), "which quant should I use", "which KV dtype", scale-factor layout, dequant kernel wiring, imp-quantize / AWQ, judging quant quality (PPL). Do NOT use for writing/optimizing GEMM/GEMV kernels (sm120-cuda-expert) or measuring quant perf (benchmark-cuda).

日本語の概要は準備中です。原文の説明を表示しています。

Explores codebases to find relevant files, trace execution paths, and map architecture with team communication capabilities for collaborative analysis (converted from agent)

日本語の概要は準備中です。原文の説明を表示しています。

Reference patterns for graph algorithm problems including BFS, DFS, Dijkstra, topological sort, union-find, MST, Bellman-Ford, and bipartite checking. Provides recognition signals, Python templates, edge cases, and common mistakes for each technique. Use when solving problems involving graphs, trees, shortest paths, connectivity, or dependency ordering.

日本語の概要は準備中です。原文の説明を表示しています。

Builds pricing models for barrier, Asian, lookback, and other path-dependent options with Monte Carlo simulation. Use when pricing exotic options, modeling complex payoffs, or evaluating structured product components.

日本語の概要は準備中です。原文の説明を表示しています。

Runs Monte Carlo simulations for portfolio analysis with return distribution, tail risk, and path-dependent scenario evaluation. Use when running portfolio simulations, estimating tail risk, or analyzing return distributions.

日本語の概要は準備中です。原文の説明を表示しています。

Evaluates capital efficiency with burn multiple, net new ARR per dollar burned, and path to profitability analysis. Use when analyzing burn efficiency, assessing capital needs, or modeling runway scenarios.

日本語の概要は準備中です。原文の説明を表示しています。

Hunt authentication and authorization bypasses — forced browsing, path traversal in auth, header injection, JWT downgrade, OAuth state confusion, role manipulation. Use when an endpoint returns 401/403 but appears reachable.

日本語の概要は準備中です。原文の説明を表示しています。

Hunt JSON Web Token (JWT) vulnerabilities — alg=none bypass, RS256→HS256 key confusion, weak HMAC secret cracking, kid path traversal, JWKS injection, jku/x5u header attacks, embedded JWK confusion, expired-token acceptance, claim mutability, and token replay. Use when an app uses JWT for authentication or stateless sessions.

日本語の概要は準備中です。原文の説明を表示しています。

Hunt file upload vulnerabilities — bypass content-type/extension/magic-byte/size filters, achieve XSS via SVG/HTML upload, achieve RCE via .phtml/.jsp/.htaccess, exploit path traversal in filenames, and use polyglot files. Use when an endpoint accepts file uploads.

日本語の概要は準備中です。原文の説明を表示しています。

Hunt Server-Side Request Forgery (SSRF) — internal network access, cloud metadata exploitation, gopher/file/dict protocol abuse, and 11 IP-filter bypass techniques. Use when an endpoint accepts a URL, hostname, or file path as input.

日本語の概要は準備中です。原文の説明を表示しています。

Hunt Insecure Direct Object Reference (IDOR) — test horizontal and vertical privilege escalation across user IDs, org IDs, tenant boundaries, and unguessable identifiers. Use when the user has an API endpoint with an identifier in the path/body that may be tested for unauthorized cross-user access.

日本語の概要は準備中です。原文の説明を表示しています。

Hunt full Account Takeover (ATO) by chaining lower-severity findings — IDOR-to-email-disclosure, password-reset-token-theft, OAuth-redirect-uri abuse, response-manipulation, cookie scope, CRLF in Set-Cookie, race-condition on signup. Use when the user wants to escalate small findings to ATO or thinks an ATO path exists.

日本語の概要は準備中です。原文の説明を表示しています。

Single gateway for all core↔tech-pack interactions. Reads manifests, resolves paths, loads skills/agents, routes commands.

日本語の概要は準備中です。原文の説明を表示しています。

Copy this repo's skills into another agent harness's skills directory by name — resolves the harness alias to its path via scripts/sync-targets.json and runs sync-skills.sh. Use only when the user asks to copy/sync/push the skills to another harness (oh-my-pi, opencode, kimi, codex, etc.) — never trigger automatically.

日本語の概要は準備中です。原文の説明を表示しています。