「fix」の検索結果

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 or testing imp-server and its HTTP APIs - OpenAI/Anthropic endpoints, /v1/chat/completions, /v1/messages, /v1/responses, SSE streaming, tool calling, json_schema/regex/GBNF constrained decoding, thinking/reasoning_content, cache_control/prefix cache, model loading and swapping, request priority, X-Request-Id, OTLP tracing / traceparent / Jaeger, /metrics, container env (IMP_SET), "server returns 404/garbage", API compliance. Do NOT use for CLI-only inference (imp-cli), kernel work (sm120-cuda-expert), or pure output-quality checks (check-degeneration).

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。

Analyzes structural interest rate exposure with fixed/floating mismatch, basis risk, and cap/floor adequacy assessment. Use when modeling structural rate risk, analyzing basis risk, or evaluating interest rate hedging needs.

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 bond market liquidity with bid-ask spread analysis, dealer inventory assessment, and electronic trading penetration. Use when analyzing bond liquidity, assessing execution conditions, or evaluating venue selection.

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。

ALIGN — Agentic Loop Image GeneratioN. Paint a subject in the craft of a reference artwork as executable p5.js, Canvas, SVG or another mark-based medium, replay that craft's real order of work, and improve it through pixel-only independent Codex subagent review. The reference fixes the craft; the subject may be the reference's own scene (千里江山图 → p5.js) or another (清明上河图 → 武汉). Not for one-shot raster image generation.

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。

ALIGN — Agentic Loop Image GeneratioN. Paint a subject in the craft of a reference artwork as executable p5.js, Canvas, SVG or another mark-based medium, replay that craft's real order of work, and improve it through pixel-only cross-model review. The reference fixes the craft; the subject may be the reference's own scene (千里江山图 → p5.js) or another (清明上河图 → 武汉). Not for one-shot raster image generation.

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。

All-in-one fullstack dev engine. /aura: 46 modes (build/fix/clean/deploy/review/spec/lore/ax/experiment/payment/debug/qa/orchestrate/escalate+), 6-layer security with 32 hooks, tiered models (ZERO/ECO/PRO/MAX), 8 languages, 16 specialized agents, SPEC/EARS/TRUST5/XLOOP/RALF/Autopus absorbed. ~55% token savings.

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 should be used when working with Rust code, reviewing Rust code, managing Rust dependencies, creating Rust projects, or fixing Rust compilation errors. It provides strict coding standards (especially FAIL FAST error handling), workspace architecture guidance, dependency management automation, and common Rust patterns.

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。

Living catalogue of 7 known hazard entries (SE-01 through SE-07) specific to agent-studio: Windows backslash paths, prototype pollution, hook exit codes, async swallowing, ReDoS in glob-to-regex, DST arithmetic, array mutation during iteration. Each entry: symptom, root cause, fix, test assertion.

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。

Validates code against coding standards and best practices. Reports compliance violations and suggests fixes.

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 and act on code review feedback. Use when receiving review results.

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。

Autonomous fixed-budget ML experiment loop — setup, iterative hypothesis testing, git-based keep/discard tracking, and indefinite autonomous execution. Implements the karpathy/autoresearch protocol.

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。

Detect missing docs, undocumented files, project health issues, and coverage gaps on session start or on-demand. Scans for README gaps, TODO/FIXME counts, and test coverage holes.

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。

Unit testing patterns with Vitest - mocking, fixtures, isolation, and fast feedback.

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。

Create change specification and implementation plan with dynamic phase generation. Supports feature, bugfix, refactor, and epic types.

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。

Extract tabular schedule data from construction drawings — door, window, finish, fixture, panel schedules — and output to Excel. Triggers: 'door schedule', 'extract schedule', 'schedule to Excel', 'panel schedule'.

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。

Count-based quantity takeoff and tag completeness auditing for construction drawings. Vision + OCR reconciliation, sheet markup, Excel QTO output. Triggers: 'tag audit', 'quantity takeoff', 'QTO', 'count fixtures'.

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。

Format commit messages following conventional commits standard. Use when: writing commit messages, git commit, reviewing commit history. Keywords: commit, git, message, conventional, 提交, 訊息, feat, fix, refactor.

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。

Act on the findings a review left on a PR or MR: take or decline each by severity, edit the code, one commit, reply. Use when handed a PR or MR URL that has already been reviewed. Edits real code.

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 multiple Claude agents to investigate and fix independent problems concurrently

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。

Refactor with tests first, one change at a time, never mix refactoring with bug fixes or new features

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。

Four-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions.

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。

Enforce Biome formatting and lint discipline in this repository. Use when making any file edits, when asked to run format/lint, and immediately before any commit. Always execute `bun run lint` (from package.json), apply resulting fixes, and re-run until clean. Treat `bun run lint:links` as optional by default, and recommend it when files under `content/` are changed.

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。

Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management, making interfaces robust and production-ready. Use when the user asks to harden, make production-ready, handle edge cases, add error states, or fix overflow and i18n issues.

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。