103 件 ・ 関連度順
概要と使いどころ
Execute incident response procedures for Claude API outages and degradation. Use when Claude API is returning errors, experiencing high latency, or showing degraded performance in production. Trigger with phrases like "anthropic incident", "claude api down", "anthropic outage", "claude degraded", "anthropic runbook".
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。
Scaffold a graded problem set with sections, problems, worked solutions, and short "why this matters" explainers across analytical, empirical, and coding types. Use when user says "make a problem set on X", "scaffold exercises for this lecture", "create practice problems", "generate homework with a solution key", "build a graded assignment on topic Y". Emits a clean student set plus a separate solution key — NOT for grading submissions or auto-checking student answers.
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。
Martial arts as body discipline — the shared pedagogical structure across striking, grappling, and weapon arts (stance, distance, timing, ukemi, live partner work, graded ranking, and the ethical container the best schools enforce). Covers karate, judo, jiu-jitsu (Brazilian and traditional Japanese), aikido, kendo/kenjutsu, boxing, muay Thai, and wrestling at enough depth that an agent can place a user into a reasonable first-month practice and recognize the safety failures that matter most. Leans on Moshé Feldenkrais's judo background and Yang Jwing-Ming's martial scholarship for the internal-to-external bridge. Use for any query about beginning a martial art, training injury patterns, graded progression, or the ethics of combat training.
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。
Diagnoses ArgoCD application sync failures and degraded states using the ArgoCD REST API and argocd CLI. Queries /api/v1/applications/{name} for sync status, resource health, and operation state. Provides automated remediation steps for OutOfSync, Degraded, and Missing resource conditions.
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。
Detects seven structural anti-patterns in Claude Projects that cause unpredictable output, ignored instructions, and degraded quality. Diagnoses Monolith, Orphan File, Echo Chamber, Phantom Conversation, Kitchen Sink, Misaligned Hierarchy, and Blurred Layers. Use when user says "what's wrong with my project," "Claude ignores my instructions," "diagnose my project," "why is output inconsistent," "review my project setup." Also trigger on symptom-phrased: "Claude doesn't follow my rules," "my instructions keep getting overridden," "my Project isn't behaving as designed." Use alongside rootnode-project-audit if available for deeper structural analysis. Activate whenever the user describes symptoms of unreliable, inconsistent, or degraded Claude Project output, even if they do not name a specific pattern. Do NOT use when the user's primary request is Memory-layer rebalancing (use rootnode-memory-optimization if available) or scoring a single prompt (use rootnode-prompt-validation if available).
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。
Add an external probabilistic classifier to a decision path without letting it take the path over. Covers finding the externally-graded rows you are already logging, measuring the confidence separation between the overrides it got right and the ones it got wrong, choosing an operating point your data licenses, failing open at the call site, and proving the whole arrangement offline with no API key. Applies to any service returning a score you can order — TypeSafe AI's System One models (Jev) are the worked example. Most of the method transfers to a local model or a second heuristic, with the parts that do not called out where they arise. Use when a rule-based path is wrong often enough to hurt, when someone proposes replacing a heuristic with a model, when a confidence threshold needs a defensible value, or when an oracle already in production has never been graded.
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 threat assessment methodology. Intent + Capability + Opportunity = Threat Level. Use when formally evaluating a threat. Prefers graded evidence items from /quality-of-information-check and runs that skill first when handed raw URLs or text. Confidence is capped by the weakest load-bearing claim, and at Moderate when the evidence is ungraded.
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 write a threat / risk / vulnerability assessment, or wants the appropriate template for each type. Distinct structures and section ordering per assessment kind. Prefers graded evidence items from /quality-of-information-check and runs that skill first when handed raw URLs or text. Confidence is capped by the weakest load-bearing claim, and at Moderate when the evidence is ungraded.
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。
Analysis of Competing Hypotheses — structured technique for evaluating multiple explanations against evidence. Use when facing ambiguous attribution or multiple plausible scenarios. Prefers graded evidence items from /quality-of-information-check and runs that skill first when handed raw URLs or text. Runs on ungraded evidence when asked, labelled as such, unweighted, and capped at Moderate confidence.
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。
Investigate Azure incidents and service degradations with a read-only workflow using Azure CLI, Resource Health, Activity Log, metrics, resource logs, and official Microsoft docs. Use when troubleshooting Azure outages, Resource Health alerts, Azure Firewall or DNS failures, ExpressRoute or BGP instability, VM availability problems, AKS incidents, App Service failures, database connectivity issues, Entra ID sign-in problems, load balancer issues, platform-vs-workload cutover, or drafting a troubleshooting report. Triggers on 'Azure トラブルシューティング', '障害調査', '切り分け', 'Resource Health', '復旧確認', 'Azure Firewall', 'DNS', 'ExpressRoute', 'VPN Gateway', 'BGP', 'AKS', 'App Service', 'SQL', 'PostgreSQL', 'Cosmos DB', 'Entra ID', 'incident', 'degraded', 'unavailable'.
Use when loading, listing, composing, or validating graded evaluation rubrics — PASS/WARN/FAIL grading with weighted criteria and balanced PASS/FAIL anchor examples. Triggers on /mk:rubric, "load rubric", "compose rubric preset", "validate rubric", or evaluator-style code review that needs anchor-grounded judgments.
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。
Graded exposure for anxiety disorders: Fear hierarchy, SUDs scale, exposure planning and guidance. Psychoeducation only, not implementation.
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。
Claude API (platform.claude.com) のプロンプトエンジニアリング・評価リファレンス。 prompt engineering, XML タグ, few-shot, system prompts, モデル別プロンプティング（Fable 5 / Opus 5 / Sonnet 5）。 evals, grading（LLM-graded 等）, jailbreak・prompt leak 対策, hallucination 低減, classification, ticket routing 等ユースケース実装。
CodeScene MCPでコード構造の保守しやすさを評価するスキル。編集前後のスコアを比較し、コミットやPRの前にAIによる変更で品質が下がっていないか確認します。
One-shot chat completion against DeepSeek's `deepseek-chat` model via the OpenAI-compatible /v1/chat/completions endpoint. Reads DEEPSEEK_API_KEY from the environment; degrades gracefully (exit 0 with a JSON status:degraded envelope) when the key is missing or the API is unreachable. Use for non-reasoning tasks — summarization, extraction, quick classification — where deepseek-reasoner would be overkill.
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。
Reasoning-mode completion against DeepSeek's `deepseek-reasoner` model (R1) via /v1/chat/completions. Surfaces the model's chain-of-thought (`reasoning_content`) separately from the final answer (`content`), so callers can display or discard the CoT without re-parsing. Reads DEEPSEEK_API_KEY; degrades gracefully (exit 0 with status:degraded envelope) when unset or the API is unreachable. Ignores temperature/top_p per DeepSeek's spec for reasoner models.
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。
Build AI-focused SRE incident response practices for LLM outages, degraded quality, runaway cost events, and safety regressions.
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。
Convert evaluation traces and production logs into SFT examples and preference pairs. Use when graded traces or failure examples exist and need to become training data, when applying rejection sampling to model outputs, or when building DPO pairs from passing and failing runs.
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 3 of building a Claude Managed Agent — the bounded grade→iterate loop. Define a CMA outcome (a required markdown rubric graded by an isolated grader), read each verdict, decide the next move (sharpen / re-run / promote to schedule), and once a version passes, run held-back eval cases in parallel. Use when the user says "grade my agent", "make it pass the rubric", "iterate until it's good", "is it good enough", or when the orchestrator routes phase=grade-iterate. outcome_builder.py builds the user.define_outcome payload (rubric required, max_iterations clamped 1..20 — never unbounded); verdict_reader.py reads the grader result and recommends the next move; eval_scaffold.py generates held-back cases + a parallel run plan (capped at the 25-thread CMA ceiling). Distinct from stage-launch (first launch) and run-without-you (scheduling).
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 of building a Claude Managed Agent — make it run without you. Turn a graded agent into a recurring scheduled deployment (POSIX-cron), an event-driven curl trigger, or confirmed on-demand use, then finalize the versioned roadmap. Use when the user says "run it every morning", "put it on a schedule", "nightly", "weekly", "automate this", "make it recurring", or when the orchestrator routes phase=run-without-you. deployment_builder.py builds the POST /v1/deployments payload (initial_events must include user.message; optionally nests a user.define_outcome so each firing self-grades); cron_validator.py validates the 5-field cron + IANA timezone and prints the wall-clock DST note; next_directions_writer.py writes NEXT-DIRECTIONS.md. No tool makes API calls — the deployment is created via BYOK curl. Distinct from grade-iterate (the in-session loop) and wrap-up (closeout).
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。
Guide the user through an independent iFixAi audit of their own agent, checking whether it does the job it is supposed to do given their business rules and org structure. Prefer pointing it at the user's REAL deployed agent over its HTTP endpoint (its actual tools, retrieval, and governance) with `--provider http --endpoint <url>`; only when no endpoint is reachable, fall back to replicating the model beneath as a bare stand-in (Anthropic, OpenAI, Gemini, Azure, Bedrock, etc.). Graded by the judge(s) of their choice (the same model, one independent judge, or a cross-vendor panel). You are the operator who walks them through it and explains the scorecard, running the SAME `ifixai run` engine as the guided CLI. Use when the user asks to run iFixAi or to audit an agent.
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。
Embed Mermaid diagrams in generated wiki pages. Use whenever documenting a runtime or request flow, a call sequence, a state machine or lifecycle, a data model or entity relationships, or non-trivial control flow, since these are clearer as a diagram than as prose. Also use when an update run touches a page that already contains a mermaid fence, or a page that contains a text fence a previous run degraded.
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。
About-you interview and materials intake — classes, bar jurisdiction, learning style (drill-me vs explain-to-me), past outlines, graded essays, old exams, MBE sets, syllabi, papers. Use on a fresh install, when the user says "set up" or "get started", or with --check-integrations to re-probe connectors.
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 the user asks for a publication-quality scientific figure or table, wants help choosing the right chart for results, needs a paper-ready pubfig or pubtab workflow, wants a figure + companion table for a results section, wants an Excel sheet turned into publication-ready LaTeX, or wants an existing scientific figure/table reviewed and upgraded.
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。