「cache」の検索結果

HTTP/HTTPS application-layer reconnaissance after a web service is identified: fingerprinting, content/API discovery, JS/source maps, proxy/cache topology, WAF, CMS, and known CVE/PoC candidates. Recon only — do not exploit, write files, or obtain a shell. Hand CVE candidates and attack surface to the operator, who may select /web-attack. Non-HTTP ports belong to /recon.

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。

CI/CD pipeline and software-supply-chain exploitation: Jenkins, GitHub Actions, GitLab CI/CD, Azure DevOps, Gitea/Forgejo, self-hosted runners/agents, poisoned pipeline execution, artifact/cache abuse, dependency confusion, third-party Action trust, GitOps/registry poisoning, workload identity/OIDC, and emerging agentic CI/CD. Use this skill when the operator has access to a CI/CD system, source repository, build/deploy configuration, runner/agent, artifact/package/registry path, or software delivery trust chain.

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。

HTTP/Web exploitation until a server shell or equivalent OS execution. Use after /web-recon has mapped the application. Covers injection, upload, LFI, SSRF/XXE, SSTI, deserialization, JWT/SAML, API logic, desync/cache/parser, and Web-controlled backend abuse. WAF stays here. Endpoint blocks after OS execution hand off to /edr-bypass then return. Direct non-HTTP service ports belong to /recon or /service-attack.

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。

Build, test, and lint Cadmus from a jj sibling workspace that has no .git (non-colocated checkout). Use when jj workspace root is a sibling tmp/agent workspace and builds fail with git submodule or .gitmodules errors, empty thirdparty/ sources, cache-marker misses, or missing sqlite.

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。

Regenerate `.sqlx/` cached metadata when adding or modifying `sqlx::query!`, `sqlx::query_as!`, or `sqlx::query_scalar!` macros.

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。

Migrate a Mycelium project from legacy install (npx-degit, framework files in .claude/) to plugin install (framework lives in plugin cache, .claude/ holds project state only). Detects current install form, walks the user through plugin installation, runs the migration script, and verifies project state survived. Idempotent — safe to invoke on already-migrated projects.

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。

Session-start lifecycle hooks for cross-plugin dependency resolution. Creates symlinks so cross-package references work in cached plugin environments.

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 verifying that a model in the imp inference engine produces coherent output without repetition loops, token-stuck states, or state corruption across turns or streams. Triggers on "degenerates", "check degeneration", "repetition loop", "own own own", "stuck token", "empty content", "multi-turn regression", "does it still work", "NIAH", and after enabling CUDA graphs / changing forward pass / MoE routing / KV cache or KV dtype / GDN state or scan / sparse attention / PDL / speculation (MTP, n-gram) / ragged prefill / batched-decode kernels (smallm, producer quantize) / FA2 softmax.

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。

Render a dashboard of the current Claude Code session — message counts, token usage, cache read/write, dollar cost, context %, lines changed, cost-per-turn sparkline, and a tool-call histogram — parsed from the session transcript JSONL by a bundled bash script. One bash call, zero analysis, zero confirmation. Optionally pass a session id to inspect a different session. Use when the user asks for session stats, usage, token or cost breakdown, or a session dashboard.

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。

Run GGUF models directly, load LoRA adapters, benchmark inference speed, and serve models via llama-server using llama.cpp. Includes Qwen 3.5 serve scripts (9B dense + F16, 35B MoE) with asymmetric KV cache and thinking mode. Secondary to Ollama; use when needing direct model control or LoRA hot-loading. Triggers on 'llama.cpp', 'GGUF', 'LoRA adapter', 'benchmark inference', 'llama-server'.

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。

This skill enables cross-model dialogue between Claude and Gemini with shared visual memory. Use when the user wants to generate images, have visual dialogues with AI, create scientific illustrations with continuity, or have multiple AI perspectives respond to the same prompt. Key trigger phrases: "generate an image", "visual dialogue", "ask the daimones", "resonance field", "Minoan tarot", "cross-model", "KV cache", "MESSAGE TO NEXT FRAME".

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。

Search and download images from 15 APIs in parallel (Openverse, Pexels, Pixabay, Met Museum, Cleveland Museum, Art Institute of Chicago, Getty Museum, NASA, Rijksmuseum, Wikimedia Commons, Unsplash, Smithsonian, Europeana, Iconify, Pollinations AI). Supports license filtering, presets (military, museum, stock), cached results, and bulk download with metadata sidecars. Triggers on find images, stock photos, public domain artwork, museum images, CC-licensed, NASA photos, icons.

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。

Analyze and tune a running llama.cpp server for local coding agents: propose config (ctx, prompt cache, MTP), benchmark before/after, report deltas. Use to optimize llama-server for Claude Code or Aider. Don't use for vLLM, ollama, or non-llama.cpp.

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。

Summarize videos, audio files, and podcasts into key takeaways. Give it a YouTube/podcast URL or a local audio/video file — it transcribes locally (cached; repeat requests reuse the transcript) and distills the transcript into key points, summaries, or translations. Use when the user asks to summarize, get key points from, translate, or TL;DR any audio or video content.

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。

Probe the runtime state of a named feature flag in a CLI binary. Covers the four-pronged evidence protocol (binary strings, live invocation, on-disk state, platform cache), the four-state classification (LIVE / DARK / INDETERMINATE / UNKNOWN), gate-vs-event disambiguation, conjunction-gate handling, and skill-substitution scenarios where a flag appears DARK but the capability is delivered by other means. Use when verifying whether a documented or inferred capability has rolled out, when auditing dark-launched features, or when a prior probe's conclusions need refreshing against a new binary version.

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。

Profile and optimize Shiny application performance using profvis, bindCache, memoise, async/promises, debounce/throttle, and ExtendedTask for long-running computations. Use when the app feels slow or unresponsive during user interaction, when server resources are exhausted under concurrent load, when specific operations create bottlenecks, or when preparing an app for production deployment with many concurrent users.

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 analyzing warp divergence, memory coalescing, shared memory bank conflicts, cache behavior, atomics, or occupancy tradeoffs on NVIDIA and AMD GPUs. Not for tool commands: use cuda-profiling.

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 diagnosing scheduler latency, kmalloc vs vmalloc, page cache, meminfo under pressure, or OOM victim choice, or when reading kernel/sched, mm, or fs source.

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 designing bytecode dispatch loops, choosing stack or register VM shapes, adding inline caches, or building a first JIT with mmap. Not for a language toolchain: use compiler-frontend.

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 adding code generation with LLVM ORC or LLJIT, Cranelift, or dynasm, lazy compilation or inline caches, or fixing W^X faults. Not for AST-to-IR: use compiler-frontend.

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。

Speed up Rust development iteration when `cargo build --release` takes 10+ minutes even for one-line edits. Use when: (1) every release rebuild takes minutes despite tiny edits, (2) Cargo.toml has `lto = "fat"` and/or `codegen-units = 1` in `[profile.release]`, (3) you want a production- shaped build for testing without paying the LTO cost on every iteration, (4) you suspect cargo is re-linking the whole binary instead of doing incremental work, (5) developing rfdb/grafema-orchestrator/large Rust binaries where full LTO is enabled for shipped builds. Adds a `fast` profile that inherits release but disables LTO, raises codegen-units, enables incremental compilation — first build still slow because it populates a fresh `target/fast/` dep cache, but every subsequent rebuild drops from ~13 min to ~13 s (≈60×).

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。

Generate an explorable HTML report of Claude Code session usage (tokens, cache, subagents, skills, expensive prompts) from ~/.claude/projects transcripts.

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。

Type-safe URL query state management with nuqs 2.x. Use when writing or reviewing code that uses useQueryState, useQueryStates, URL search params, query parameters, nuqs parsers, createLoader, createSearchParamsCache, createSerializer, or URL state in Next.js, React, Remix, React Router, or TanStack Router.

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。