Coding & Dev Tools

thkt Bundle

Web search, page fetch, and GitHub repo exploration via scout CLI.

thkt Skill

Reads Google Sheets and Docs through gsheet and gdoc. Authentication comes from a gcloud access token.

thkt Skill

Search past Claude Code/Codex sessions via recall CLI.

thkt Skill

Structural search and rewrite by AST pattern via ast-grep CLI.

thkt Skill

Symbol-level code structure queries via codegraph CLI. Callers, callees, change impact, and symbol source trails.

pr-pm Skill

Semantic code search using natural language queries. Use when users ask "where is X implemented", "how does Y work", "find the logic for Z", or need to locate code by concept rather than exact text. Returns file paths with line numbers and code snippets.

biwakonbu Skill

Use when user wants to push commits, push to remote, or sync with remote repository. Git プッシュワークフローを実行し、現在のブランチをリモートリポジトリに安全にプッシュする。

thkt Bundle

Root cause analysis by eliminating hypotheses.

trecek Skill

Interactive selection of experimental design lens for visualizing experiment methodology. Routes to the appropriate exp-lens-* skill.

trecek Skill

Create a comparison fairness matrix assessing whether alternatives are evaluated under symmetric constraints. Fairness lens answering "Are alternatives compared under symmetric constraints?"

trecek Skill

Create Estimand Clarity experimental design analysis decomposing the implicit estimand from code vs. explicit claims from prose. Evidential lens answering "What exactly is the claim?"

trecek Skill

Analyze severity of experimental tests — adversarial cases, negative controls, falsification tests, easy-pass detection, and confirmatory theater. Falsificationist lens answering "Would this design have caught the error?"

trecek Skill

Create Unit Interference experimental design diagram showing unit hierarchy, cluster structure, shared resources, and SUTVA violation pathways. Causal-Structural lens answering "What is the unit, and can treatments spill over?"

trecek Skill

Create Causal Assumptions experimental design diagram showing confounders, mediators, colliders, and identification strategy. Causal-structural lens answering "What causal assumptions support this design?"

trecek Skill

Create Iterative Learning experimental design diagram showing factor space exploration, adaptive allocation, and next-experiment recommendations. Decision-Theoretic lens answering "How does this maximize learning per cost?"

trecek Skill

Create a variance analysis profile assessing whether signals exceed noise and whether results are stable across random seeds. Stability lens answering "Is the signal larger than the noise?"

trecek Skill

Analyze measurement validity for experimental design — auditing metric-construct alignment, proxy validity, reliability, sensitivity, and consequential validity. Argumentative lens answering "Do measurements justify the interpretation?"

aeyeops Bundle

Use when moving, importing, copying, or migrating a Claude Cowork session, conversation, or project from one Windows machine to another, or when troubleshooting symptoms of a broken import like "session shows blank", "only the latest messages show", "scratchpad files don't open", "can't scroll past the last compaction", or "Loaded N messages (truncated via tail/compaction)" in the Cowork log. Delivers full history, working file links, and no truncated-transcript rendering bug, handling the undocumented two-layer compact_boundary truncation filter in app.asar that silently clips imported transcripts. Covers orphan sessions on Windows to Windows under the same Cowork account. Does not handle Cowork Spaces/Projects, Linux/macOS, or cross-account migration.

aeyeops Skill

Use when working through the findings of a preceding ultrareview validation — systematically addressing the reported errors, alignment issues, gaps, and improvements by priority and applying each fix to the plan or the code. Trigger phrases include "ultrareview-fix", "fix the review findings", "address the ultrareview", and "apply those fixes". Expects an ultrareview summary in the conversation; the `ultrareview` skill produces it.

aeyeops Bundle

Use when a plan or a code change should go through a code review loop that keeps reviewing and fixing until no actionable findings remain: PR review before merge, plan review before implementation, or validation after a refactor. Runs /ultrareview, applies /ultrareview-fix to the findings, and re-reviews until the review passes or the iteration cap is reached. Unlike a single-pass reviewer, the loop closes its own findings. Usage: /ultrareview-loop [focus_area] [--max-iterations N].

biwakonbu Skill

Use when user wants to merge to main, integrate changes to main branch, or complete a feature branch. Git マージワークフローを実行し、feature ブランチを main にマージしてプッシュする。

biwakonbu Skill

Use when user wants to commit changes, create a commit, or stage and commit files. Git コミットワークフローを実行し、変更のステージング、コミットメッセージ生成、コミット実行を行う。

biwakonbu Skill

Use when any git operation (commit, push, merge, conflict resolution) runs in this project, or when user mentions git safety, 機密ファイル, force push, --amend 条件. 共通の安全規則・禁止事項・コミットメッセージ規約・機密ファイル検出を提供し、他 git スキルから自動参照される。

biwakonbu Skill

Use when creating, updating, or maintaining skills, understanding skill structure, or implementing SKILL.md files. Also use when user says スキル, SKILL.md, skills. Claude Code プラグインの skill 仕様知識で、スキルの正しい形式、フロントマター、description のベストプラクティスを提供する。

biwakonbu Skill

Use when validating plugin structure, checking plugin correctness, linting plugin files, or verifying plugin format. Claude Code プラグインの構造とメタデータを検証し、plugin.json の必須フィールド、各コンポーネントのフロントマター、パス整合性、JSON 構文をチェックする。

biwakonbu Skill

Use when user asks about rules folder, paths condition, rule files, or modular memory. Also use when user says rules フォルダ, paths 条件, ルール分離, モジュール化. .claude/rules フォルダの活用ガイドで、paths 条件の書き方、ディレクトリ構成、ルール分離のベストプラクティスを提供する。

biwakonbu Skill

Use when understanding plugin structure, creating plugins, or validating plugin components. Claude Code プラグインの全仕様知識を統合し、plugin.json、commands、skills、agents、hooks の概要と個別スキルへの参照を提供する。

biwakonbu Skill

Use when user wants to create a new plugin, scaffold a plugin, or generate plugin structure. Claude Code プラグインのスキャフォールディングを実行し、新規プラグインのディレクトリ構造生成、テンプレート展開、marketplace.json への登録を行う。

biwakonbu Skill

Use when merge conflicts occur, when git merge fails with conflicts, or when user needs help resolving git conflicts. Git コンフリクト解消を支援し、コンフリクトを分析して解消案を生成・提示し、ユーザー承認後に適用する。

biwakonbu Skill

Use when user asks about best practices, recommended patterns, memory tips, or how to write good memory. Also use when user says ベストプラクティス, 推奨, コツ, ヒント, 良い書き方. メモリ管理のベストプラクティス集で、推奨パターン、アンチパターン、実践的なヒントを提供する。

biwakonbu Skill

Use when user asks about CLAUDE.md, what to write in CLAUDE.md, memory configuration, or project instructions. Also use when user says CLAUDE.md の書き方, メモリ設定, 何を書くべき, プロジェクト指示. CLAUDE.md の記載ガイドで、何を書くべきか、推奨サイズ、避けるべき内容を提供する。

biwakonbu Skill

Use when user asks about memory system, what is memory, memory overview, or how memory works. Also use when user says メモリとは, メモリ管理, メモリシステム, 概要. Claude Code のメモリシステム全体の概要とナビゲーションを提供し、CLAUDE.md、rules フォルダ、imports 機能の関係性と使い分けを示す。

trecek Skill

Create Randomization & Blocking experimental design diagram showing assignment mechanisms, blocking factors, and comparability sources. Design-Structural lens answering "Where does comparability come from?"

trecek Skill

Create Sensitivity & Robustness experimental design analysis identifying load-bearing analytic choices and untested perturbations. Robustness lens answering "Which assumptions are load-bearing?"

trecek Skill

Create Comparator Construction experimental design analysis assessing whether baselines and controls are fair and relevant. Counterfactual lens answering "Is the comparator fair and relevant?"

trecek Skill

Create Benchmark Representativeness experimental design diagram showing coverage matrix, generalization gaps, and untested regions. Generalizability lens answering "Does this generalize beyond the test bed?"