Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
following-conventions
Tenzir Python coding standards and tooling setup. Use when writing python code, running ruff/mypy/pytest, encountering pyproject.toml/uv.lock, or setting up a new Python project.
majiayu000/claude-skill-registry 163
-
safe-file-removal
Use safe-rm command to safely 'remove' files by renaming them to .obsolete instead of permanent deletion. Reversible, collision-safe, hook-compliant.
majiayu000/claude-skill-registry 163
-
weather-data-fetcher
Fetch current weather and forecast data from a free weather API (Open-Meteo).
majiayu000/claude-skill-registry 163
-
reference-builder
Creates exhaustive technical references and API documentation. Generates comprehensive parameter listings, configuration guides, and searchable reference materials. Use PROACTIVELY for API docs, configuration references, or complete technical specifications.
majiayu000/claude-skill-registry 163
-
free-monad-gen
Free Monad Generation Skill (PLUS +1)
majiayu000/claude-skill-registry 163
-
scratchpad
Working memory for thinking out loud.
majiayu000/claude-skill-registry 163
-
clj-kondo
A guide to using clj-kondo for Clojure code linting, including configuration, built-in linters, and writing custom hooks.
majiayu000/claude-skill-registry 163
-
operation-tracker
Maintain awareness of operation counts across the conversation to prevent cumulative context exhaustion. Use when you notice multiple operations accumulating or when working on iterative tasks across turns.
majiayu000/claude-skill-registry 163
-
bundle-size-analyzer
Bundle Size Analyzer - Auto-activating skill for Frontend Development.
Triggers on: bundle size analyzer, bundle size analyzer
Part of the Frontend Development skill category.
majiayu000/claude-skill-registry 163
-
experiment-analysis
Analyze GRPO training runs for learning dynamics and pipeline performance. Use when diagnosing training issues, reviewing Elo progression, checking throughput, or updating experiment results.
majiayu000/claude-skill-registry 163
-
param-parameterized-class-rules
Rules related to Param, to be applied when defining models. Models use Param to define parameters with validation and reactivity.
majiayu000/claude-skill-registry 163
-
procedural-rhetoric
Rules persuade. Structure IS argument. Design consciously.
majiayu000/claude-skill-registry 163
-
multi-agent-integration
Integrate Claude agents into training and live trading (v3.0). Trigger when: (1) setting up multi-agent training, (2) adding agent consultation to live trading, (3) configuring orchestrator, (4) understanding agent roles and safety mechanisms.
majiayu000/claude-skill-registry 163
-
evaluating-new-technology
Help users evaluate emerging technologies. Use when someone is assessing new tools, making build vs buy decisions, evaluating AI vendors, or deciding on technical architecture.
majiayu000/claude-skill-registry 163
-
env-config-management
환경변수(.env.*), Spring 프로파일(application-*.yml) 수정 시 사용. app/backend/CLAUDE.md 참조 필수. 서비스별 포트 중복 검증, 민감 정보는 .env.local만, application-*.yml은 플레이스홀더만(기본값 금지). 의미없는 override 지양. SQS 엔드포인트 정확성 확인.
majiayu000/claude-skill-registry 163
-
knowledge-validator
pce-memory + shirushiを活用した知識検証・整合性チェックスキル。
以下の場合に使用:
(1) 資料・ドキュメント間の矛盾チェック
(2) 指示・意思決定の追跡と検証
(3) 作業途中のリアルタイム整合性チェック
(4) 成果物と要件の照合検証
(5) shirushi Doc-IDとコードのトレーサビリティ検証
「チェックして」「整合性確認」「矛盾ない？」「検証して」「トレーサビリティ」等で起動。
majiayu000/claude-skill-registry 163
-
conversation-memory
Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history.
majiayu000/claude-skill-registry 163
-
enablement-kit
Use to plan rollout communications, trainings, and assets after pricing changes.
majiayu000/claude-skill-registry 163
-
nango-dry-run
Use when testing Nango syncs locally - runs dry-run command with proper parameters for integration testing without affecting production data
majiayu000/claude-skill-registry 163
-
finetune-generate
Use when generating synthetic training data for multi-turn conversation fine-tuning. Triggers - have design artifacts ready, need to generate conversations, ready to assess quality. Requires finetune-design first.
majiayu000/claude-skill-registry 163
-
epic-caching
Guide on caching with cachified, SQLite cache, and LRU cache for Epic Stack
majiayu000/claude-skill-registry 163
-
harmonic-centrality-transport
Harmonic centrality gadgets with GF(3) conservation for topological transport of ablative case structure via abelian extensions of ℚ
majiayu000/claude-skill-registry 163
-
synchronization
Convergence to common trajectory in coupled systems
majiayu000/claude-skill-registry 163
-
tts-train
Build TTS datasets and train Qwen3-TTS voice models from audiobooks or curated clips. Use for voice cloning, dataset prep, WhisperX alignment, Qwen3-TTS training, and inference.
majiayu000/claude-skill-registry 163