「ast」の検索結果

Scores and strengthens startup pitch decks (pre-seed through Series A) against 35 investor-grade criteria grounded in Sequoia, DocSend, YC, a16z, and Carta data. Use when the user has shared a pitch deck (PDF, PPTX, markdown, pasted slide text, or a link to one) and asks for a review, score, feedback, or critique. A full review takes about 15–25 minutes, 40 or more for a long investor deck, so for a general pitch question with no deck, answer briefly in chat and offer the review instead of starting it. When it runs, score with the rubric, never with deck advice from memory.

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。

Reviews startup financial models for investor readiness: validates unit economics, stress-tests runway scenarios, and benchmarks metrics against stage-appropriate targets. Use the full review, about 10–15 minutes, when the user provides a financial model (Excel, CSV, or a model pasted as text) and asks for review, validation, runway analysis, or unit-economics scoring. For a single money question with figures to compute, such as 'how long do I have?' or 'is a 4x burn multiple bad?', use its shorter quick check, so the answer comes from the calculator and dated benchmarks, not mental arithmetic.

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。

Print your own north-star row from your own record, and nothing else. Reads .claude/harness/decision-log.md, the canvas and the hook logs in this project; prints one line (decisions before the first source file, of which citing outside evidence, kills before code, sessions). Sends nothing anywhere. Opt-in; paste the line where you like or not at all.

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。

Interactive code simulation engine that spawns ghost personas to review your code before it ships. Each ghost walks through your code line-by-line from a different failure perspective: The Adversary (race conditions, double-submit, idempotency), The Enterprise Edge (business logic gaps, multi-currency, B2B tax exemptions, locale), Chaos Monkey (timeouts, partial failures, network partitions, OOM). Produces a chaos timeline, structured bug report with severity ratings, and three resolution tiers (quick fix, robust architecture, generated test suite). Use this skill whenever the user mentions code review, PR review, "find bugs", "what could go wrong", "will this break", "is this safe", "stress test", "edge cases", design review, pre-merge check, dry run, chaos test, or wants a second opinion on any code — even if they don't explicitly ask for "ghost personas" or "simulation". Also trigger when someone pastes a code snippet with any question about its correctness or safety.

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 opening, merging, or releasing a PR for imp - branching off main, `gh pr create`, enabling auto-merge, writing the PR body or a CHANGELOG entry, cutting a tagged release (version bump + CHANGELOG + tag + GitHub release). Symptoms - "PR stuck BLOCKED", "my last commit didn't land on main", "which check is required", "how do I cut a release", "auto-merge merged too early", "check-release failed", "STALE.md blocks git pull". Do NOT use for build/test mechanics (building-and-testing) or perf measurement / baseline refresh (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 a question is about *structure* rather than text - who calls or launches a symbol, where it is defined, what a change would reach, whether something is dead, how a request gets from the API to a kernel. Triggers on "who calls", "who launches this kernel", "where is X defined", "what breaks if I change", "is this still used", "is this dead", "trace the path from X to Y", "blast radius", "what depends on this header". Do NOT use for free-text search (`rg` is better and cheaper) or to open a file whose path you already know.

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 building imp, running its test suite, checking CI status, or debugging build/test failures - "make build", "run the tests", "test-gpu", "verify-fast", GTEST_FILTER, Docker/CUDA toolchain, dependency bumps, "CI is red/blocked", "which gate failed", stale objects / segfault after a header edit, hook edits, docker-entrypoint env vars, determinism or perplexity checks. Do NOT use for benchmarking/profiling (benchmark-cuda) or output-quality batteries (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。

Builds project finance models with construction period draws, operational cash flows, DSCR covenants, and sculpted debt repayment. Use when modeling project finance, calculating debt service coverage, or structuring project lending.

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。

Prices FX options and exotic structures with Garman-Kohlhagen, local volatility, and stochastic volatility models. Use when pricing FX derivatives, evaluating FX options, or modeling cross-currency products.

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 construction risk with EPC contract review, delay and cost overrun scenarios, and completion guarantee structures. Use when modeling construction risk, evaluating EPC terms, or stress testing project timelines.

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 concession terms with revenue sharing, performance requirements, hand-back conditions, and termination provisions. Use when evaluating concessions, analyzing PPP contracts, or assessing concession economics.

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。

Assesses critical mineral investments with supply chain mapping, geopolitical risk, and processing infrastructure analysis. Use when evaluating critical minerals, analyzing lithium/cobalt supply, or assessing rare earth investments.

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。

Structures technology diligence with architecture review, code quality assessment, scalability analysis, and technical debt evaluation. Use when evaluating startup technology, assessing engineering teams, or reviewing technical infrastructure.

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 master and special servicer performance with delinquency management, modification outcomes, and loss mitigation effectiveness. Use when assessing servicer quality, monitoring servicing metrics, or evaluating servicer transfers.

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 unitranche structures with first-out/last-out splits, blended pricing, and agreement among lenders provisions. Use when analyzing unitranche options, comparing unitranche vs traditional structures, or modeling blended costs.

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 ISDA Master Agreement provisions with close-out netting, termination events, and credit support annexes. Use when reviewing ISDA terms, analyzing CSA provisions, or assessing documentation risk.

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 midstream assets with throughput analysis, fee-based vs commodity-exposed revenue, and contract structure assessment. Use when analyzing midstream investments, evaluating pipeline assets, or assessing gathering systems.

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 regulated utility rate-setting with RAB methodology, allowed return analysis, and regulatory reset risk assessment. Use when analyzing regulatory frameworks, modeling rate cases, or evaluating allowed return mechanics.

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 renewable energy project economics with PPA structures, merchant tail risk, and production profile analysis. Use when analyzing wind/solar projects, evaluating PPA terms, or modeling renewable energy cash flows.

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 frontier market opportunities with liquidity constraints, custody risk, settlement infrastructure, and governance assessment. Use when analyzing frontier markets, assessing operational risk, or evaluating frontier market 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。

Evaluates non-traditional securitization collateral including solar, data centers, digital infrastructure, and IP royalties. Use when analyzing esoteric ABS, evaluating non-standard collateral, or structuring novel asset classes.

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 GitHub Actions CI for the current branch or open PR, triage failing checks, reproduce locally, and fix scoped issues until green. Use whenever the user mentions CI failures, red checks, failed pipeline, GitHub Actions, merge blocked, fix the build, babysit CI, gh run failed, ruff/ty errors, failing pytest, example run failed, or asks to check CI on this branch — even if they only paste a log snippet. Also use after implementing a feature when tests, lint, or typecheck might have broken.

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。

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。