874 件 ・ 関連度順
概要と使いどころ
Deep-dive framework for analyzing crypto tokens — market data, liquidity health, tokenomics, unlock schedules, and risk assessment. Combines on-chain data, API queries, and multi-source validation to generate actionable investment verdicts.
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。
Morning startup workflow for daily notes, yesterday summary, agenda, status comments, meeting sections, and daily branch setup. Use when invoked as `$work-start-day` or when the user asks to start the work day.
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。
Structured, risk-aware code review of a GitHub pull request using the gh CLI, with diff triage, unresolved-thread suppression, and severity-grouped findings ending in an approve/request-changes verdict.
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。
Pushes interfaces past conventional limits with technically ambitious implementations — shaders, spring physics, scroll-driven reveals, 60fps animations. Use when the user wants to wow, impress, go all-out, or make something that feels extraordinary.
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。
Read-only reviewer for agent-flow. Judges one diff against the acceptance criteria, AGENTS.md rules, protected paths and risk boundaries; returns a JSON verdict with line-anchored findings. Use when launched with AGENT_FLOW_ROLE=reviewer or asked for an agent-flow review of a diff.
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 a story or ticket implementation against its spec and acceptance criteria - per-AC verdicts with file:line evidence and proving tests, code reuse and design conformance, dead code, stale docs, comment discipline. Finds the spec from an explicit path, the ticket key in the branch name, or plan files - and asks rather than guessing. For defect-hunting code review use dotnet-techne-code-review instead. Keywords: story QA, acceptance criteria, spec conformance, AC coverage, definition of done, dead code check, reuse check, comment check, verify story, QA this branch.
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 to verify a story or ticket implementation against its spec - per-AC verdicts, code reuse and design conformance, dead code, then adversarial maintainer verification. Requires the qa/review agent roles registered by scripts/install-codex.sh. Keywords: story QA, acceptance criteria, spec conformance, AC coverage, QA this branch, verify story.
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。
Review gate for correctness, reuse, and simplification. Produces a structured verdict with actionable findings. Trigger on any PR before merge, or on any agent-generated code before it is committed.
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 rule set is over the Augment budget, when a new rule would breach it, or when asked to audit / merge / prune rules — runs the audit pipeline and proposes a verdict per rule.
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 to run a depth-bounded self-correction loop (attempt → critic verdict → re-attempt) as a tunable test-time compute knob — a do-and-judge specialisation, default off, capability-gated.
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 surfacing and prioritising risk before commit — blast-radius framing, mitigations, residual-risk verdict — even if the user just says 'what could go wrong here?'.
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 to consolidate multiple already-run judge verdicts into one report — consensus, conflicts, must-fix/should-fix with per-judge provenance. Consume-only, no opaque score, never auto-gates.
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 comparing this package to a peer / competitor — ours-vs-theirs verdict table, axis selection, adoption queue. Triggers on 'how do we compare to X', 'should we adopt their pattern'.
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。
Quantiza LLMs para 8-bit ou 4-bit com redução de memória de 50-75% e perda mínima de acurácia. Use quando a memória GPU é limitada, precisa ajustar modelos maiores ou quer inferência mais rápida. Suporta formatos INT8, NF4, FP4, treinamento QLoRA e otimizadores 8-bit. Funciona com HuggingFace Transformers.
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。
Ajuste fino com eficiência de parâmetros para LLMs usando LoRA, QLoRA e 25+ métodos. Use ao fazer fine-tuning de modelos grandes (7B-70B) com memória GPU limitada, quando precisa treinar <1% dos parâmetros com perda mínima de precisão, ou para serviços multi-adapter. Biblioteca oficial do HuggingFace integrada ao ecossistema transformers.
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。
Quantização pós-treinamento em 4-bits para LLMs com perda mínima de precisão. Use para implantar modelos grandes (70B, 405B) em GPUs de consumo, quando você precisa de redução de memória 4× com <2% de degradação de perplexidade, ou para inferência mais rápida (aceleração de 3-4×) vs FP16. Integra com transformers e PEFT para fine-tuning QLoRA.
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。
Quantização de pesos consciente da ativação para compressão de LLM de 4-bit com aceleração 3x e perda mínima de acurácia. Use ao implantar modelos grandes (7B-70B) em memória GPU limitada, quando precisa de inferência mais rápida que GPTQ com melhor preservação de acurácia, ou para modelos com instruções ajustadas e multimodais. Vencedor do Prêmio Melhor Artigo MLSys 2024.
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。
Reduza o tamanho de LLMs e acelere a inferência usando técnicas de pruning como Wanda e SparseGPT. Use para comprimir modelos sem retreinamento, alcançando 50% de esparsidade com perda mínima de acurácia, ou ativando inferência mais rápida em aceleradores de hardware. Cobre pruning não estruturado, pruning estruturado, esparsidade N:M, pruning por magnitude e métodos one-shot.
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。
[Process] Use when the developer wants something explained or taught, or wants to know HOW TO REVIEW a change — by default the current working tasks + changes in context, or whatever the prompt names (a plan, a subsystem, a decision, a concept, a bug). AI derives WHAT to explain from the prompt and ALWAYS delivers a teacher-and-coach review guide, high level first then detail: what was done, a VISUAL MAP (system flowchart, domain ERD, sequence diagrams), the user stories and business rules with their REAL test-case IDs, a REVIEW PATH naming which files to open first and in what order with an exit criterion per stage, the technical concepts needed to follow it, how it works, why THIS solution, every alternative option with pros/cons, the trade-offs accepted, the blast radius, HOW TO TEST AND DEMO the change, the developer's decision levers, and written challenge prompts that provoke the reader to pressure-test the work. Works at ANY scope — from one line of code to the whole project: it SIZES the target into a scope tier, DECOMPOSES a large one into understanding groups, BREAKS the work into tasks before the first deep read, and ACCUMULATES the report group by group on disk so a huge explanation stays complete instead of thinning out. Writes the full report to a single combined markdown file (plans/reports/understand-*.md) that opens with a detailed summary section — or delivers it in full in chat when Step 3 finds no git-ignored directory for it — and always summarizes it in chat. Regardless of coding level. Never interrogates, never quizzes, never blocks.
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。
[General] Use when you need to (re)generate a DERIVED navigation index, cross-capability ERD, or reimplementation guide assembled FROM the canonical Feature Specs under docs/specs/**. Never extracts a separate A-E engineering tree.
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。
[Architecture] Use when you need to analyze business domain: bounded contexts, aggregates, entities, ERD, domain events, and cross-context integration.
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 before building anything new — a pre-build gate that decides whether an idea deserves its own tool, judged from both the agent lens (legible, drivable, automatable) and the human lens (will I touch it, do I want to maintain it). Trigger on "should I build X", "starting a new project / app / tool / repo", "is this worth making", "want to spin up", or any new-build intent — even if the word "checklist" never appears. Outputs a backed GATE.md with checkmarks and a one-line verdict note in the project root docs. Do NOT load for small config tweaks, one-off scripts, bug fixes on existing things, or anything that is clearly a feature of something you already run.
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 on an existing project to decide KEEP / MERGE / ARCHIVE — never limbo. Forces a call on tools that already exist and may have stopped earning their keep. Trigger on "is this still worth keeping", "audit this repo", "tech-debt cleanup", "sweep the folder", "what's dead here", or any signal that something hasn't been touched in months. Judged from both the agent lens (still legible, still drivable, still safe) and the human lens (do I still reach for it, does it nag). Includes a non-negotiable footgun check for stale pipelines that can overwrite live data. Outputs a backed AUDIT.md and a one-line verdict note in the project root docs. Do NOT load for greenfield projects (use new-project-gate), one-off bug fixes, or when the answer is already obvious.
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。
Phase 4 Turn 2 of disease-market-sizing-orchestration (A6' upgrade). Audits compose output via Cite-or-Block strict — every anchor must reverse-resolve to an actual file in sources/, every fact claim must have an anchor. Returns verdict (ok/blocked) + violations list. Use AFTER cite-bound-content-generator (Turn 1), BEFORE report-bundle-builder (phase 5).
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。