提示词
提示词工程与模板
init-project-research
flonat
"Bootstrap a research project: interview for details, scaffold directory, create Overleaf symlink, init git, and sync with context library and Notion. Triggers: 'new research project', 'start a new paper'. Not for lightweight setups — use /init-project-light instead."
project-safety
flonat
"Set up safety rules and folder structures for research projects. Prevent accidental data loss when Claude reorganizes files. Triggers: 'protect my data', 'set up project safety rules'. Not for auditing structure — use /audit-project-research."
update-project-doc
flonat
"Update a project's own documentation (CLAUDE.md, README.md, docs/*.md) to reflect its current state. Detects stale file trees, timestamps, counts, and next steps. Includes a leanness audit: flags CLAUDE.md > 200 lines, sections > 15 lines of reference material, SKILL.md > 300 lines, agents > 400 lines, and context files > 200 lines — with auto-extraction to docs/ or references/."
parallel-task
am-will
Only to be triggered by explicit /parallel-task commands.
llm-council
am-will
Orchestrate a configurable, multi-member CLI planning council (Codex, Claude Code, Gemini, OpenCode, or custom) to produce independent implementation plans, anonymize and randomize them, then judge and merge into one final plan. Use when you need a robust, bias-resistant planning workflow, structured JSON outputs, retries, and failure handling across multiple CLI agents.
gemini-computer-use
am-will
Build and run Gemini 2.5 Computer Use browser-control agents with Playwright. Use when a user wants to automate web browser tasks via the Gemini Computer Use model, needs an agent loop (screenshot → function_call → action → function_response), or asks to integrate safety confirmation for risky UI actions.
skill-creator
WellApp-ai
Template and guide for creating new skills
tool-hooks-doctor
Heyvhuang
"Detect whether Claude Code evolution hooks are installed/enabled, and print a copy-paste fix. Use when you expect runs/evolution artifacts but nothing is being written. Triggers: hooks, evolution, runs/evolution, settings.json, PreToolUse, PostToolUse."
workflow-template-seeder
Heyvhuang
"Seed a new runnable template under templates/NNN-slug/ from a short spec by chaining existing skills (intake → ship-faster stages) while keeping it clean and shareable (no secrets, minimal scope). Use when creating a new template quickly."
workflow-template-extractor
Heyvhuang
"Extract a shareable runnable template under templates/NNN-slug/ from a real project: copy + de-brand + remove secrets + add env examples + docs, with minimal refactors. Use when you have a working project and want to turn it into a template."
workflow-template-seeder
Heyvhuang
"Seed a new runnable template under templates/NNN-slug/ from a short spec by chaining existing skills (intake → ship-faster stages) while keeping it clean and shareable (no secrets, minimal scope). Use when creating a new template quickly."
skill-creator
Heyvhuang
"Create or refactor Ship Faster-style skills (SKILL.md + references/ + scripts/). Use when adding a new skill, tightening trigger descriptions, splitting long docs into references, defining artifact-first I/O contracts, or packaging/validating a skill."
workflow-template-extractor
Heyvhuang
"Extract a shareable runnable template under templates/NNN-slug/ from a real project: copy + de-brand + remove secrets + add env examples + docs, with minimal refactors. Use when you have a working project and want to turn it into a template."
Frame
simota
Figma MCP Serverを活用してデザインコンテキストを抽出・構造化し、実装エージェントに渡すブリッジエージェント。Figmaデザインからコードへの橋渡し、Code Connect管理、デザインシステムルール抽出が必要な時に使用。
Latch
simota
Claude Codeããã¯ï¼PreToolUse/PostToolUse/Stopçã®ã¤ãã³ãã·ã¹ãã ï¼ã®ææ¡ã»è¨å®ã»ãããã°ã»ä¿å®ãæ å½ãããã¯ã«ããã¯ã¼ã¯ããã¼èªååãå質ã²ã¼ããã»ãã¥ãªãã£æ¤è¨¼ã®å°å ¥ãå¿ è¦ãªæã«ä½¿ç¨ã
opik-optimizer
vincentkoc
Optimize LLM prompts, tools, and agents in Opik using standardized optimizer workflows (prompt optimization, tool optimization, and parameter tuning), dataset/metric wiring, and result interpretation.
gui-agent
Fzkuji
"GUI automation via visual perception. Screenshot → detect → click → verify. Use when asked to operate a desktop app, interact with a VM, or complete an OSWorld benchmark task."
claude-code-hooks
vasilyu1983
Create event-driven hooks for Claude Code automation. Configure hook events in settings or frontmatter, parse stdin JSON inputs, return decision-control JSON, and implement secure hook scripts.
ai-rag
vasilyu1983
Complete RAG and search engineering skill. Covers chunking strategies, hybrid retrieval (BM25 + vector), cross-encoder reranking, query rewriting, ranking pipelines, nDCG/MRR evaluation, and production search systems. Modern patterns for retrieval-augmented generation and semantic search.
data-lake-platform
vasilyu1983
"Data lake and lakehouse platform patterns: ingestion/CDC, transformations, open table formats (Iceberg/Delta/Hudi), query and serving engines (Trino/ClickHouse/DuckDB), orchestration, governance/lineage, cost and operations. Self-hosted and cloud options."
ops-devops-platform
vasilyu1983
"Production-grade DevOps and platform engineering patterns: Kubernetes, Terraform, containers, GitOps, CI/CD, observability, incident response, security hardening, and cloud-native operations (AWS, GCP, Azure, Kafka)."
claude-code-agents
vasilyu1983
Create and maintain Claude Code agents/subagents (.claude/agents/*.md) with YAML frontmatter (name/description/tools/model/permissionMode/skills/hooks), least-privilege tool selection, delegation patterns (Task), context budgeting, and safety best practices.
claude-code-project-memory
vasilyu1983
Configure CLAUDE.md project memory files for persistent context, coding standards, architecture decisions, and team conventions. Reference for the 4-tier memory hierarchy, cross-platform AGENTS.md compatibility, and quick-add commands.
data-sql-optimization
vasilyu1983
"Production-grade SQL optimization for OLTP systems: EXPLAIN/plan analysis, balanced indexing, schema and query design, migrations, backup/recovery, HA, security, and safe performance tuning across PostgreSQL, MySQL, SQL Server, Oracle, SQLite."