「iter」の検索結果

Validates agent outputs against schemas and quality criteria, scores confidence, detects hallucinations, monitors convergence, decides when to iterate, and synthesizes actionable feedback. Use when checking if a node's output is acceptable, scoring confidence, detecting fabricated content, deciding whether to re-execute, or generating improvement feedback. Activate on "validate output", "check quality", "confidence score", "hallucination check", "should we iterate", "improvement feedback". NOT for executing DAGs (use dag-runtime), planning DAGs (use dag-planner), or matching skills (use dag-skills-matcher).

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 determines whether an adolescent or adult patient meets DSM-5 criteria for gender dysphoria (gender incongruence) by evaluating the presence of at least two of six specified criteria over a minimum 6-month duration, accompanied by clinically significant distress or impairment. It is triggered when a clinician queries whether the patient's reported symptoms align with gender dysphoria, such as persistent incongruence between experienced/expressed gender and designated gender.

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。

OBLITERATUS: abliterate LLM refusals (diff-in-means).

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 work produces a deliverable, factual claim, dataset, code change, decision, publication, deployment, automation, or irreversible action whose failure would matter; when the user asks for a quality gate, acceptance criteria, QA, completeness, validation, audit, evidence, preflight, release readiness, or a definition of done; or before claiming completion on medium- or high-risk work. Automatically decide whether a formal gate is warranted, derive task-specific pass/fail criteria, gather evidence, and block unsupported completion. Make sure to use this skill even when the user does not say "quality gate" if consequential work needs acceptance criteria or completion evidence. Skip formal gating for trivial, reversible, low-impact requests.

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 strategic-consultant-grade meeting minutes from transcripts or notes in Japanese OR English (matching the source language), then run a self-review loop (max 3 iterations) that checks for internal contradictions, action-item omissions, speaker-name errors, and date/day-of-week mistakes before reporting completion. Use this skill whenever the user asks to draft meeting minutes, summarize a transcript, or document a meeting discussion — including Japanese-language transcripts (議事録 / 会議メモ / 文字起こし) and English-language transcripts.

Track design iteration history and apply consistent styling decisions across revision cycles. Use when handling follow-up change requests that reference previous design decisions (e.g., '前回も色で良いんだけど', 'same style as before', 'like we discussed').

Use when the user asks to "plan my launch tier", "how big should this launch be", or "build a launch risk register with kill criteria"; produces a tier decision (Tier 1 flagship all-channel / Tier 2 targeted / Tier 3 changelog-level), a launch-type declaration (new-product / feature / relaunch / partnership with co-marketing split), an effort calibration matrix (tier to channel intensity and asset scope), D0/W1/M1 KPI targets (labeled Estimated), a risk register (likelihood x blast-radius, owners, mitigations, kill criteria / rollback thresholds), and a T-8w to T+4w timeline skeleton. Not for picking the launch date or window — use launch-window-planner; not for creator-channel launch campaigns — use campaign-planner. 发布分级/发布类型/风险登记册/kill criteria

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。

Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review, devil's advocate challenges, ethics review, and post-research literature monitoring. Triggers on: research, deep research, literature review, systematic review, meta-analysis, PRISMA, evidence synthesis, fact-check, guide my research, help me think through, 研究, 深度研究, 文獻回顧, 文獻探討, 系統性回顧, 後設分析, 事實查核, 引導我的研究, 幫我釐清, 幫我想想, 我不確定要研究什麼, 研究方向, 研究主題.

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。

Japanese tech article writer with non-duplicate H2/H3 structure design, content generation, and image TODO placeholders. Triggers on requests for 記事作成, 記事を作って, 記事を書いて, 〇〇の記事, テック記事, 解説記事, ブログ記事作成.

Deep literature review — PubMed, EuropePMC, bioRxiv preprints, citation networks, evidence synthesis. Disambiguates queries, runs collision-aware searches, grades evidence T1-T4, and produces structured reports. Use for systematic literature review, meta-analysis evidence collection, and detailed answer-with-citations workflows.

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。

Write clear acceptance criteria for features. TRIGGERS - Use when user needs help with acceptance-criteria related tasks.

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。

Integrate Iteration Layer APIs for document, website, image, and sheet processing. Composable APIs — Document Extraction, Website Extraction, Document to Markdown, Image Transformation, Image Generation, Document Generation, and Sheet Generation — share one credit pool and chain together into workflows.

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。

Turn vague preferences about employers into criteria that can actually be used to choose between them: for each one, what would have to be seen to confirm it, whether it comes from firsthand experience or from an untested assumption, whether it is a must, a nice-to-have, or something to avoid, and which pairs of criteria pull against each other while both being treated as required, then test the set against real candidates. Use when a new graduate is working out what to select employers on, when someone who has decided to move needs criteria for where to apply, or when a stated axis like "a place I can grow" needs to be made checkable; do not use to recommend an industry, job, or employer, to score or rank candidates, or to judge someone's stated preferences.

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。

Provides fault tolerance patterns for Spring Boot 3.x using Resilience4j. Use when implementing circuit breakers, handling service failures, adding retry logic with exponential backoff, configuring rate limiters, or protecting services from cascading failures. Generates circuit breaker, retry, rate limiter, bulkhead, time limiter, and fallback implementations. Validates resilience configurations through Actuator endpoints.

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。

Iteratively detects and auto-fixes technical debt in a codebase using three quality criteria from debt-analysis references: conditional branch simplification, encapsulation, and separation of concerns. Applies fixes directly to code, runs existing tests to verify no regressions, re-analyzes, and loops until all high-severity issues are resolved or max iterations (5) reached. Use this skill when you want to automatically improve code quality with real code changes, reduce technical debt systematically, or clean up code to meet quality standards. Trigger on phrases like "fix technical debt", "clean up code quality", "refactor and fix issues", "improve code quality automatically", "apply debt fixes", "fix code problems", "eliminate debt".

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。

Write and refine high-quality user stories — INVEST criteria, "As a X, I want Y, so that Z" format, Gherkin acceptance criteria when applicable, definition of ready, anti-patterns, and a review checklist. Use when creating or reviewing user stories, PRD section 6, backlog items, or acceptance criteria. Do NOT use for technical specs, architecture decisions, or task decomposition.

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。

When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform. Also use when the user mentions 'ad copy variations,' 'ad creative,' 'generate headlines,' 'RSA headlines,' 'bulk ad copy,' 'ad iterations,' 'creative testing,' 'ad performance optimization,' 'write me some ads,' 'Facebook ad copy,' 'Google ad headlines,' 'LinkedIn ad text,' or 'I need more ad variations.' Use this whenever someone needs to produce ad copy at scale or iterate on existing ads. For campaign strategy and targeting, see paid-ads. For landing page copy, see copywriting.

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。

Continuous localhost UI iteration loop with Arman, through full surface certification. Use when he asks to fix, refine, review, or iterate on a page, route, panel, overlay, or other UI while he may inspect localhost. NOT for a report-only UI audit.

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。

Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament evaluation, and telemetry-driven recommendations. Use when a user wants to uncensor, abliterate, or remove refusal from an LLM.

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 for the search-planning stage of a literature review, when database lanes and language layers must be chosen, when DOI coverage policy is unclear, or when inclusion and exclusion criteria need drafting before any source is read; not for running the screening and PRISMA pipeline of a formal review, which is prisma-scoping-review-pipeline.

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 agent outputs against schemas and quality criteria, scores confidence, detects hallucinations, monitors convergence, decides when to iterate, and synthesizes actionable feedback. Use when checking if a node's output is acceptable, scoring confidence, detecting fabricated content, deciding whether to re-execute, or generating improvement feedback. Activate on "validate output", "check quality", "confidence score", "hallucination check", "should we iterate", "improvement feedback". NOT for executing DAGs (use dag-runtime), planning DAGs (use dag-planner), or matching skills (use dag-skills-matcher).

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。

AIエージェントが読むスキルや指示文を、手順・参照情報・完了条件に整理し、必要な資料を読む条件の明確化や重複の削減まで支援する文書作成・編集のスキル。

• スキル文書を作成・編集したいとき
• AGENTS.mdやCLAUDE.mdの整理
• 参照資料を読む条件を明確にしたいとき

指定したコミットやブランチなどを基準にコードの変更を確認し、開発規約への適合と仕様の実現を別々にレビューします。二つの観点の指摘を分けて報告するスキルです。

• ブランチやPRの変更レビュー
• 指定コミットやタグ以降の確認
• 文書化された開発規約との照合

絞り込んだ競合を九つの観点で採点し、根拠付きの比較カードと戦略の二軸図に整理するスキル。各社の強みや、自社が狙う領域の競合を確認します。

• 競合を共通の基準で比較したいとき
• 出典付きの競合紹介カード作成
• 戦略の二軸で競合を配置したいとき