collect-for-pr
Collect pending worktree commits into a PR for review. Use this skill when subdirectory worktrees have accumulated 4-7+ commits that should be batched together and submitted for review. Invoked with /collect-fo...
Discover Testing & security skills, compare source repositories and read the instructions for each workflow.
Collect pending worktree commits into a PR for review. Use this skill when subdirectory worktrees have accumulated 4-7+ commits that should be batched together and submitted for review. Invoked with /collect-fo...
Fix build issues for matched functions in the Melee decompilation project. Use this skill when builds are failing due to header mismatches, signature issues, or caller updates needed after a function has been m...
Use the decomp-permuter to automatically find C code variations that match target assembly. Useful when stuck at 99%+ match with stubborn register allocation issues. Invoked with /decomp-permuter or when manu...
Document and name functions, structs, and fields in Melee decompilation. Use for improving readability, discovering function purposes, and naming unknown fields. Invoked with /understand where target is a func...
[EXPERIMENTAL] Debug Melee in Dolphin emulator. Breakpoints are unreliable with JIT mode. Use for memory inspection only until stability improves.
根据用户的创意/故事想法,批量生成多张连贯的图片和视频,并以专业分镜表(Storyboard)的形式展示。支持单镜头重新生成、图生视频、首尾帧视频生成等高级功能。适用于短视频脚本、动画分镜、广告创意、故事可视化等场景。
Use when planning market strategy, learning from Toss's 7 success patterns (Pain Point, Trojan Horse, Friction Removal, Viral Loop, Data-Driven, Ecosystem, Regulation).
Generate standardized document templates (DOCUMENT, TECHNICAL, PROPOSAL, RESEARCH, SECURITY-QA, INDEX) with YAML frontmatter, Quick Reference sections, and consistent structure for professional documentation.
Use this when complex problem-solving, root cause analysis, strategic decision-making, or systematic thinking is needed. Applies 15 thinking methods with multi-agent orchestration and Clear-Thought MCP integrat...
Use when researching markets, analyzing competitors, comparing technologies, or finding case studies. Ensures all findings include credible sources and URLs.
Apply Progressive Disclosure principles to organize large documentation projects. Restructure docs into hierarchical structure, reduce token usage by 95%+, and create README files for navigation.
Use when analyzing stakeholder psychology for negotiations, proposals, or persuasion. Creates research-backed personas revealing hidden motivations.
Use when planning market entry, designing PMF strategy, or applying Toss's 16-question framework. Includes Pain Point Score, Trojan Horse path, 10x improvement guide.
Keyword-based automatic skill detection and activation system for Claude conversations
Frappe Bench CLI command reference for site management, app management, development, and production operations. Use when running bench commands, managing sites, migrations, builds, or deployments.
Frappe DocType creation patterns, field types, controller hooks, and data modeling best practices. Use when creating DocTypes, designing data models, adding fields, or setting up document relationships in Frapp...
Frappe client-side JavaScript patterns for form events, field manipulation, dialogs, and UI customization. Use when writing form scripts, handling field changes, creating dialogs, or customizing the Frappe desk...
Frappe Python and JavaScript API reference including document operations, database queries, utilities, and REST API patterns. Use when working with frappe.get_doc, frappe.db, frappe.call, or any Frappe API meth...
Frappe server-side Python patterns for controllers, document events, whitelisted APIs, background jobs, and database operations. Use when writing controller logic, creating APIs, handling document events, or pr...
Use when committing code - ensures atomic, descriptive commits that leave the codebase in a merge-ready state at every point
MANDATORY when working with time-series data, hypertables, continuous aggregates, or compression - enforces TimescaleDB 2.24.0 best practices including lightning-fast recompression, UUIDv7 continuous aggregates...
Use after implementing features - verifies each acceptance criterion with structured testing and posts verification reports to the GitHub issue
Use when documentation drift is detected. Comprehensively audits codebase and creates/updates Swagger, features docs, and general documentation to achieve full sync.
Use when asked to detect silent failures/weak error handling or explicitly asked to run the silent-failure-hunter subagent.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.