「erd」の検索結果

Produce an accounts-receivable aging report and surface overdue invoices for a Well workspace. Use when the user asks who owes them money, an AR aging report, overdue invoices, days sales outstanding (DSO), or which customers to chase.

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。

Rust の性能改善を「計測 → 仮説 → 変更 → 再計測」のループで地道に回すためのスキル。プロファイラの選び方、Cargo の最適化設定、データ構造・アロケーション・ハッシュ・分岐などの定石をフェーズ順に適用する。1 回 1 変更 1 計測の規律を厳守する。rsvelte 固有の既知ボトルネック（`serde_json::Value` 駆逐、`bumpalo` 導入、`Atom<'a>`、codegen 直書き）と OXC 対応表、NAPI 検証手順も §7 に収録。「Rust の性能改善」「ボトルネック調査」「プロファイル取って最適化」などの依頼で使用。

Cloudflare Hyperdrive for Workers-to-database connections with pooling and caching. Use for PostgreSQL/MySQL, Drizzle/Prisma, or encountering pool errors, TLS issues, connection refused.

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 this skill when working with RenderDoc capture files (.rdc), analyzing GPU frames, tracing shaders, inspecting draw calls, or running CI assertions against GPU captures. Trigger phrases: "open capture", "rdc file", ".rdc", "renderdoc", "shader debug", "pixel trace", "draw calls", "GPU frame", "assert pixel", "export render target".

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。

Restructure and optimize alert rules for monitoring platforms (Sentry, PagerDuty, Datadog, OpsGenie). Use when someone asks to "reduce alert noise", "fix alert fatigue", "create alert rules", "set up escalation policies", "tune alerting thresholds", or "create on-call runbooks". Generates platform-specific alert configurations and tiered escalation policies.

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。

Family-G proof & derivation integrity forensics: does a THIRD PARTY's written proof/derivation actually establish its theorem, or does it skip an obligation, assume its own conclusion, take an invalid step, drift a symbol's meaning, or smuggle an unstated assumption? Decides from the WRITTEN proof/derivation — verdict-bearing at L1 (the LaTeX source; PDF-extracted math is unreliable, so an L0 PDF-only run surfaces info only) — never asserts 'fabricated', only that the step shown does not hold. A fresh cross-model reviewer reads the theorem/proof + an extraction-only obligation scaffold and proposes per-obligation findings, each span-anchored to the evidence ledger (claims.json); reviewer≠adjudicator. Emits proof-derivation-forensics.findings.json; NEVER computes the verdict. dimension=proof, can be critical. Triggers: "proof forensics", "check this proof", "derivation integrity", "audit the math", "证明审计", "推导有没有漏洞".

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。

Audit experiment integrity against the evidence ledger. At L2 (repo + result files present) a fresh cross-model reviewer reads the eval code line-by-line for fake/derived ground truth, score self-normalization, phantom results (a paper number with no backing file/key), dead/uncalled metric code, verified-scope inflation, method-described ≠ method-evaluated drift, synthesized-looking results, placeholder/fake data still wired into a released result, code-output ≠ reported-number mismatch, and missing reproducibility artifacts (an empirical/agent/LLM paper shipping neither code nor the prompts/configs its results need) — every finding span-anchored to a ledger claim_id. At L0/L1 (PDF / source only) the same patterns are surfaced as info-level 'could-not-verify' signals where the ledger gives an anchor (observability_level_required:2) — NEVER a fraud verdict from a PDF. The reviewer PROPOSES findings; tools/adjudicate_findings.py computes the verdict. Detect-only. Triggers: "experiment forensics", "audit the results", "check the eval code", "实验诚实度".

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。

Audit whether a paper's baseline comparisons are COMPLETE, FAIR, and SIGNIFICANT: a required recent SOTA baseline is missing while 'best/SOTA' is claimed (HP-MISSING-BASELINE); a baseline is undertuned / given less compute-tuning-data, run at a mismatched config, or the equal-budget ablation-as-baseline is absent (HP-WEAK-BASELINE); 'outperforms' is asserted over overlapping error bars or with no variance/seeds (HP-SIG-OVERLAP); and a cross-row 'improves over baseline by X%' is arithmetically wrong (HP-DELTA-ERROR, cross-row form only). A versioned per-domain baseline profile + a live leaderboard/recency search are assembled by the EXECUTOR as structured facts; a fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per dimension) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Works at L0 (stated comparisons) and deepens at L2 (configs/result files). A completeness question it cannot settle internally becomes needs_external_check, never a guessed missing baseline. Emits baseline-comparison-audit.findings.json; computes NO verdict. Detect-only. Triggers: "baseline audit", "missing baselines", "is the comparison fair", "weak baseline", "baseline 误报", "SOTA earned?".

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 channels the strategic and empathetic reasoning of Whitney Wolfe Herd, founder and CEO of Bumble. Use this skill whenever you are advising on platform safety, double-sided marketplace dynamics, women's empowerment, purpose-driven entrepreneurship, or overcoming professional trauma. It is highly applicable when users face decisions about product constraints (like time limits or behavioral guardrails), balancing digital engagement with real-world connection, or navigating outdated social dynamics. Reach for this skill to help users shift from 'me to we,' engineer kindness into their products, and focus on core inputs rather than vanity metrics.

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。

Suede AI blunt A-F ship grade for a code change across correctness, security and permissions, data and state, domain truth, UX and release behavior, tests and verification, and deploy readiness, with Instant-F triggers and evidence-based grade caps on auth, payment, migration, and public-API surfaces. Use when asked to grade this, give it a letter, is this an A, how ready is this to ship, or should this merge: when the caller wants the verdict without a findings list. NOT FOR: findings, evidence, and fix briefs (use suede-code-review, or suede-code for findings plus grade); enforcing the verdict in CI (use suede-ci-gate); eval coverage for AI behavior (use suede-ai-eval).

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 inspecting or operating Herdr sessions, workspaces, tabs, panes, agents, terminal output, agent messaging, or waits.

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 installing, updating, configuring, or troubleshooting Herdr, including missing commands, PATH errors, version differences, or Pi integration setup.

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 deciding the verdict of a security review - severity and confidence scales, when to block, approve with notes, drop or reject as unreviewable, and the exact comment templates

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 before any review_criterion approval or column move - the evidence each verdict needs, how to treat skipped, blocked and intermittent cases, and which exit a blocker takes

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。

Orchestrate several ank agents in parallel, each on its own task, worktree and branch. Use only inside a herdr pane, when asked to fan ank tasks out across agents in a repository with a .ank/ directory.

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。

Map curriculum connections across multiple subjects for a real-world problem or authentic context. Use when planning cross-curricular projects or connecting content to real 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。

Organische Social-Media-Inhalte für Deutschland und den DACH-Raum planen, verfassen, wiederverwenden, prüfen und messen. Nutze diesen Skill, wenn Posts, Redaktionspläne, Content-Serien oder Kanalstrategien für LinkedIn, X, Instagram, TikTok, Facebook, YouTube oder Mastodon entstehen sollen, wenn vorhandene Inhalte für Social wiederverwendet werden, oder wenn ein Beitrag auf Werbekennzeichnung, Persönlichkeits- und Markenrechte, Alt-Texte und aktuelle Plattformregeln geprüft werden soll. Deckt Briefing, Evidenz, Formatwahl, Interaktion und Messung ab. Nicht für bezahlte Kampagnen und nicht für das tatsächliche Veröffentlichen.

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。

Design a cache invalidation and eviction strategy — event-driven invalidation and thundering herd prevention. Use when asked to "design cache invalidation", "fix stale cache data", or "prevent a thundering herd".

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。

Updated to cover both pre-code PRD/ERD/Docs generation AND post-code continuous documentation updates / Diperbarui untuk mencakup pembuatan PRD/ERD/Docs pra-kode DAN pembaruan dokumentasi kontinu pasca-kode.

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。

Synthesize multiple independent structured review verdicts into one lossless deduplicated punch list. Use when findings from several review perspectives must be merged without inventing, dropping, or changing source 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。

Load the shared verdict, punch-list, SKIP, and gate schema used by the dh multi-perspective review orchestrator, reviewers, and synthesizer. Use only when one of those components must produce, parse, validate, or gate 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。

Cloudflare platform management via Wrangler CLI, Agents SDK (v0.13+), and Browser Rendering API. Deploy Pages, Workers, KV, R2, D1, Queues, Vectorize, Workflows, Hyperdrive. Build stateful AI agents with the full SDK stack — Agent, AIChatAgent, Think, Voice, sub-agents, fibers, HITL, scheduling, observability, Code Mode (Dynamic Worker sandboxes). Budget web scraping via cf_browser.py. Use when deploying to Cloudflare, managing CF infrastructure, configuring wrangler.toml/wrangler.jsonc, building AI agents or chat agents on Workers, adding voice, orchestrating sub-agents, or for cheap web scraping. Triggers: Cloudflare, wrangler, Pages, KV, R2, D1, Workers, Vectorize, Queues, Workflows, Hyperdrive, cf_browser, Browser Rendering, Agents SDK, Code Mode, codemode, MCP, Think, AIChatAgent, Voice agent, sub-agents, fibers, HITL, Dynamic Workers.

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。

One committed verdict on something that exists, cited. Use when something exists and a claim about it needs a 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。

Before any material decision — code chunk, plan, strategy, design, scope cut, push to GitHub — convene a war-room. The session driver takes the CEO seat: frame the tradeoff, summon specialist seats from whatever agent roster the user has built, dispatch a cross-family voice via `ato dispatch` so priors actually disagree, decide. A failure-mode filter (wrong assumptions / overcomplexity / orthogonal edits / imperative-over-declarative — Karpathy's four are one good default, swap in your own) runs on every dispatch. Place in the v2.16 stack: war-rooms DECIDE before code starts; `ato-mission` EXECUTES the work between decisions (multi-step, goal-driven, persisted across days); `ato-review` VERIFIES the resulting commits. Use a war-room for the design verdict, hand the verdict to a Mission, review the merged result. Fires before: sending a code draft to the user as final, opening a PR, pushing to a remote-tracking branch, committing >50 LOC of behavior change, or delivering a plan or strategic recommendation as the final answer.

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。