skill-creator
Create new skills following a structured 4-phase workflow. Use when you need to build reusable agent skills with proper validation.
mcaf-skill-curation
Create, update, and validate repository skills under your agent’s skills directory (Codex: `.codex/skills/`, Claude: `.claude/skills/`) so they match the real codebase and `AGENTS.md` rules; tune YAML `description` triggers, apply feedback, and generate `<available_skills>` metadata blocks.
syneidesis
Gap surfacing before decisions. Raises procedural, consideration, assumption, and alternative gaps as questions to transform unknown unknowns into known considerations.
reflexion
This skill should be used when the user asks to "reflect on session", "extract insights", "analyze this conversation", "save learnings to memory", "run /reflect", "what did we learn?", "capture this for future sessions", "session wrap-up", or wants to persist session knowledge to User/Project memory. Conversational memory reconstruction through guided dialogue.
requirement-detector
探测用户的写作规范需求并加载对应文档。当用户提到AI味重、去AI味、自然、爽文、快节奏、爽点、无毒点、不降智、严肃文学、有深度、强情绪、打动人、甜文、撒糖、虐文、虐心、BE等关键词时自动激活。适用于讨论写作要求、AI去味方法、节奏控制、情感表达时使用。
natural-dialogue-techniques
在写作对话场景或用户询问角色对话时使用 - 提供自然、符合角色性格的对话技巧，展现角色并推进情节
using-superpowers
Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists; if a skill exists for your task, you MUST use it
conference-talk-builder
Create conference talk outlines and iA Presenter markdown slides using the Story Circle narrative framework. Use when the user wants to structure a tech talk, create presentation slides, or needs help organizing talk ideas into a story-driven format.
natural-dialogue-techniques
Use when writing dialogue scenes or when user asks about character conversations - provides techniques for natural, character-consistent dialogue that reveals character and advances plot
ideation
Transform raw brain dumps (dictated freestyle) into structured implementation artifacts. Use when user has messy ideas, scattered thoughts, or dictated stream-of-consciousness about something they want to build. Produces contracts, phased PRDs, and implementation specs written to ./docs/ideation/{project-name}/.
requirement-detector
探测用户的写作规范需求并加载对应文档。当用户提到AI味重、去AI味、自然、爽文、快节奏、爽点、无毒点、不降智、严肃文学、有深度、强情绪、打动人、甜文、撒糖、虐文、虐心、BE等关键词时自动激活。适用于讨论写作要求、AI去味方法、节奏控制、情感表达时使用。
natural-language-processing
Build NLP applications using transformers library, BERT, GPT, text classification, named entity recognition, and sentiment analysis
ralph
Implement the Ralph Wiggum iterative AI loop for Codex/Claude Code: create /ralph-loop and /cancel-ralph commands, wire a stop hook or wrapper loop, persist a fixed prompt, track iterations, and detect a completion promise with safety limits. Use when asked to build or integrate self-referential AI iteration loops, stop hooks, or command wrappers for repeated agent runs.
your-skill-name
Brief description of what this Skill does and when to use it. Include specific trigger phrases users would say. Use when user asks "trigger phrase 1", "trigger phrase 2", or wants to [outcome]. Max 1024 characters.
weaviate-query-agent
Search and retrieve data from local Weaviate using semantic search, filters, RAG, and hybrid queries
memory-optimizer
Refactors CLAUDE.md into minimal startup context by extracting path-specific rules, skills, commands, and agents. Use when CLAUDE.md exceeds 50 lines, startup feels slow, memory needs restructuring, or splitting monolithic project instructions.
external-consensus
Synthesize consensus implementation plan from multi-agent debate reports using external AI review
pact-memory
Persistent memory for PACT agents. Save context, goals, lessons learned, decisions, and entities. Semantic search across sessions. Use when: saving session context, recalling past decisions, searching lessons. Triggers: memory, save memory, search memory, lessons learned, remember, recall
