Claude Skills · Code Review & Testing
Trampelpfadanalyse
ellmos-ai/skillsパイプラインおよびコントロールファイル・ワークフローのためのエラー分析：規約や手順がLLMにとって実際に可視かつ発見可能であるかを検証します。朴拙（ナイーブ）なサブエージェントを用いた実証的ベースライン → 介入 → 再テストの比較（孤立したサンドボックスコピー、同一のテストケース、定量的な成功測定）。エージェントがルール/README/規約を繰り返し無視したり間違ったナビゲーションを行ったりする場合に、ドキュメントの変更が実際に行動を変化させるかを測定するために使用します。トリガー：「is the convention even seen」、「why does no agent follow the rule」、「make a doc signpost measurably effective」、「desire-...
At a glance
This skill is for Code Review & Testing and helps you measure if agents follow documented rules, test whether documentation changes behavior, and analyze workflow instruction visibility.
git clone --depth 1 https://github.com/ellmos-ai/skills
cp -r skills/skills/dev/trampelpfadanalyse/JA ~/.claude/skills/JA
Setup, runtime and requirements describe ellmos-ai/skills, the repo this skill ships in.
agent-testingDocumentation EffectivenessWorkflow AnalysisInstruction VisibilityBaseline Comparison
Also in ellmos-ai/skills
View the repoAkademisches Studien- und Fristenmanagement mit Quellenprüfung, Datenschutz und realistischer Handlungsplanung.
Aktives Lernen, Erarbeitung von Fachinhalten und strukturierte Erstellung von Synthesen.
Prüfungsvorbereitung, Selbsttests, Probeklausuren und systematische Fehleranalyse.
スティーブン・ヘイズによるアクセプタンス＆コミットメント・セラピー（ACT）：心理的柔軟性の6つのコアプロセスを備えたヘキサフレックス・モデル。
Acceptance & Commitment Therapy (ACT) according to Steven Hayes: Hexaflex model with the six core processes of psychological flexibility.
Terapia de Aceptación y Compromiso (ACT) según Steven Hayes: modelo Hexaflex con los seis procesos nucleares de la flexibilidad psicológica.
Acceptance & Commitment Therapy (ACT) according to Steven Hayes: Hexaflex model with the six core processes of psychological flexibility.
Provider-neutral planner for synchronizing MCP configuration, skills and rule files across agent providers and app classes. It discovers evi...
Portable, provider-neutral file bridge for bootstrap surfaces, truth pointers, separate memory silos, messaging, presence, cooperative locks...
Creates a portable AI workspace on a USB drive or any drive. RAG pipeline with local LLM models (Ollama), vector database (ChromaDB), and pr...
Builds and operates a provider-neutral self-care core set for scheduled LLM tasks and desktop-app automations. Use when an agent should disc...
Ordnet Büroaufgaben, Korrespondenz und Fristen ohne Bindung an eine bestimmte Office-App.
Other Code Review & Testing skills
Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests,...
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.
Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold e...
Use when you need to resolve an in-progress git merge/rebase conflict.
A relentless interview that asks every frontier question at once, round by round.