Prompts
Prompt engineering and templates
sytex
by Sytex
Connect to Sytex platform API. Use when user mentions Sytex, app, claro, ufinet, dt, adc, atis, exsei, integrar, torresec, or app_eu instances. Handles tasks, projects, forms, materials, organizations, and chats.
dialectic
by beingcognitive
Harden a plan/design/algorithm/decision via a thesis→antithesis→synthesis loop: each round, two independent reviewers (a different model + a freshly-spawned subagent) critique the current draft; fold in only findings the draft doesn't already resolve, adjudicating reviewer disagreements by evidence; stop after two consecutive clean rounds (cap 10, usually 3–5). Independence is the engine — a different model and an isolated perspective expose blind spots one model can't see in itself. Use when the user says "dialectic" or "정반합". NOT for trivial or no-real-tension changes.
skill-creator
by zhuxining
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Funder Report Builder
by SNEHA-Org
Never write to the database; connect read-only.
humanizer-zh
by ai-zixun
Remove signs of AI-generated, translated, or overly mechanical Chinese prose. Use when rewriting, editing, or reviewing Chinese blog posts, essays, newsletters, nonfiction chapters, product analysis, or long-form commentary so they read like native Chinese writing. Trigger this skill when the user asks to 「去 AI 味」, 「润色成中文母语表达」, 「改得像博客或书里写的」, 「减少翻译腔」, or similar. Detect and fix translation-like phrasing, empty big words, formulaic contrast frames, sloganized endings, list inflation, punctuation misuse, terminology/casing inconsistencies, and paragraph rhythm that feels assembled rather than written.
update
by biruk741
Incrementally update AI documentation. Two modes — (1) add a new concept with the right doc types for each agent, (2) propagate a concept change across all existing AI docs. Use when you need to add, change, or remove a specific convention, rule, or pattern across your documentation. Triggers on "update docs", "change rule", "add convention", "propagate change", "update documentation".
issue-template-generator
by ehtbanton
Generate GitHub issue templates for bug reports, feature requests, and questions. Triggers on "create issue template", "generate github issue template", "bug report template", "feature request template".
cx-fix
by m19803261706
CX 工作流 — Bug 修复。 当用户提到"修 bug"、"fix"、"有个问题"、"报错"、"不工作"、 "出了问题"、"修复"、"debug" 时触发。 轻量流程：调查→定位→修复→测试→提交。
langfuse-prompt-upsert
by neuradex
Create or update Langfuse prompt with development label. Use when creating new prompts, updating existing prompts, or improving prompt content.
clawreel
by marylindaunpleasing8037
触发：制作短视频、知识科普视频、话题讲解短片、产品展示视频、宠物/美食/生活记录短片、任何需要配音+配图+合成为竖屏视频的场景。不触发：视频播放/编码问题、手动剪辑现有视频、纯图文内容。
error-diagnosis
by jamelna-apps
When user encounters "error", "exception", "failed", "stack trace", "crashed", or needs error categorization. Provides structured root cause analysis and prevention strategies.
ai-review
by ryoshimm
現在の worktree の実装を plan と照合してレビューし、PR コメント形式で報告する。コードの修正は行わない。
peer-review
by pietz
Ask a group of LLM tools for their opinion on a given task. Use this when stuck on a problem, seeking a second opinion, validating an approach, or wanting diverse viewpoints on complex decisions.
outliner
by hansonyyds
科技专栏提纲生成技能。当用户提供素材（文章、推文等）要求分析并生成写作提纲时使用。用户请求如"帮我分析这篇文章"、"生成提纲"、"写个专栏"等。生成 2-3 个差异化提纲方案，并行启动写作 agent，保存草稿供用户选择。
claude-extensibility
by brixtonpham
"Claude Code extensibility: agents, skills, output styles. Capabilities: create/update/delete agents and skills, YAML frontmatter, system prompts, tool/model selection, resumable agents, CLI-defined agents. Actions: create, edit, delete, optimize, test extensions. Keywords: agent, skill, output-style, SKILL.md, subagent, Task tool, progressive disclosure. Use when: creating agents/skills, editing extensions, configuring tool access, choosing models, testing activation."
Multi-Agent Consensus Engine
by ryanrdetzel
A structured debate system using defined cognitive frameworks (personas) to cross-examine technical proposals and force consensus.
starship
by jyasuu
Cross-shell prompt configuration and installation guide.
reflect-codex-skills
by go-go-golems
Generate reflections for past Codex session histories using the Reflection CLI. Use when asked to summarize or reflect on previous Codex conversations, list projects/sessions, filter by date or session id, or refresh cached reflections from ~/.codex/sessions.
github-issue-from-templates
by dfitchett
Create GitHub issues using data-driven templates. Supports any issue type via configurable template configs. Use when the user asks to create a GitHub ticket, issue, or support ticket, or when they want to add a new issue template.
chat-history-importer
by djc00p
"Import AI conversation exports (OpenAI ChatGPT and Anthropic Claude) into your agent's episodic memory. Parses export files, writes daily memory summaries, and deduplicates on re-runs. Trigger phrases: import chat history, ingest conversation export, import chatgpt export, import claude export, load AI conversation history."
execute
by biruk741
Execute phases from an orchestrator document by spawning parallel subagents. Reads the orchestrator, identifies available phases, and coordinates wave-based parallel execution. Pure orchestrator — never edits source files.
hermes-fake-moa
by kgmkm
Multi-LLM parallel orchestrator — list available models across all configured providers, select 2–5 models into a panel, and send the same prompt to all of them simultaneously. NOT true MoA (no aggregator model). Results are collected side-by-side for human comparison.
Plugin Structure
by aiagentskills
This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "use ${CLAUDE_PLUGIN_ROOT}", "add commands/agents/skills/hooks", "configure auto-discovery", or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or Claude Code plugin architecture best practices.
oh-my-opencode-update
by canyangliunian
Use when upgrading, reinstalling, or troubleshooting the oh-my-opencode plugin, especially when old caches, lockfiles, or permissions prevent the new version from taking effect.