提示词
提示词工程与模板
GoAI SDK - AI Agent Skill
zendev-sh
Result() on streams is blocking - it waits for the entire stream to complete. Call it after consuming TextStream()/Stream(), or on its own if you don't need incremental output.
openai-image-gen
NeverSight
Generate images using OpenAI's DALL-E 3 API. Use when needing to create graphics, icons, backgrounds, or any visual assets. Requires OPENAI_API_KEY in environment.
doc-scanner
NeverSight
"Scans for project documentation files (AGENTS.md, CLAUDE.md, GEMINI.md, COPILOT.md, CURSOR.md, WARP.md, and 15+ other formats) and synthesizes guidance. Auto-activates when user asks to review, understand, or explore a codebase, when starting work in a new project, when asking about conventions or agents, or when documentation context would help. Can consolidate multiple platform docs into unified AGENTS.md."
claude-code-headless
NeverSight
"Run Claude Code programmatically without interactive UI. Triggers on: headless, CLI automation, --print, output-format, stream-json, CI/CD, scripting."
claude-code-templates
NeverSight
"Boilerplate templates for Claude Code extensions. Triggers on: create agent, new skill, command template, hook script, extension scaffold."
extract-transcripts
NeverSight
Extract readable transcripts from Claude Code and Codex CLI session JSONL files
image-generation
guinacio
Generates professional AI images using Google Gemini. ALWAYS invoke this skill when building websites, landing pages, slide decks, presentations, or any task needing visual content. Invoke IMMEDIATELY when you detect image needs - don't wait for the user to ask. This skill handles prompt optimization and aspect ratio selection.
claude-code-debug
NeverSight
"Troubleshoot Claude Code extensions and behavior. Triggers on: debug, troubleshoot, not working, skill not loading, hook not running, agent not found."
videocut-self-update
zrt-ai-lab
自更新 skills。记录用户反馈，更新方法论和规则。触发词：更新规则、记录反馈、改进skill
claude-skills-sync-init
Adonis0123
Bootstrap Claude skill-sync automation in any repository. Use when users ask to set up .agents/skills to .claude/skills syncing, generate skills:sync:* scripts, inject package.json scripts/postinstall hooks, or initialize this sync workflow in a new or existing project.
ruler-rules-init
Adonis0123
Migrate and bootstrap Ruler-based AI rules across repositories with English-first templates, preset-based project detection, and safe, idempotent setup. Use when creating or standardizing .ruler/* files, generating AGENTS.md/CLAUDE.md, wiring ruler:apply into package.json, adding generated-file ignores in .gitignore, and designing applyTo scoping patterns such as ` and web/`.
videocut-clip
zrt-ai-lab
执行视频剪辑。根据确认的删除任务执行FFmpeg剪辑，循环直到零口误，生成字幕。触发词：执行剪辑、开始剪、确认剪辑
owasp-llm-top10
mastepanoski
Security audit for LLM and GenAI applications using OWASP Top 10 for LLM Apps 2025. Assess prompt injection, data leakage, supply chain, and 7 more critical vulnerabilities.
videocut-clip-oral
zrt-ai-lab
口播视频转录和口误识别。生成审查稿和删除任务清单。触发词：剪口播、处理视频、识别口误
faion-business-analyst
faionfaion
"Business analysis: requirements engineering, stakeholder analysis, process modeling."
faion-claude-code
faionfaion
"Claude Code: skills, agents, hooks, commands, MCP servers, IDE integrations."
portfolio-project-architect
ChunkyTortoise
"Transform service catalog into high-ticket portfolio assets with memory-persistent scoping and optimized Auto Claude handoff generation"
portfolio-project-architect-enhanced
ChunkyTortoise
"Advanced portfolio development with Claude Code 2.1.0 agent lifecycle management, hot-reloadable skills, and parallel processing optimization"
keiba-prediction
Atoyr
JRA重賞レースの予想・振り返り・ログ記録をこのリポジトリの評価体系（ベース点×係数＋加算層・ルールゲート・荒れ度配分）で実行する。ユーザーが「#準備」「#収録」「#予想」「#更新」「#振り返り」「#集計」「#設計」の起動フレーズを使ったとき、およびレース名を挙げて「予想して」「振り返り」「回顧」「ボードで」「ログ追記」「◎は誰」「買い目」「オッズ更新」「馬場更新」など予想関連の依頼をしたら、内容の大小にかかわらず必ずこのスキルを使う。個別馬の評価照会、荒れ度やR値の計算、analyze.pyでの集計、ルール追加の相談もすべて対象。一般知識で予想を組み立ててはならない。
debug-codex-session
weave-os
Investigate a specific Codex CLI session by session ID — correlate the local rollout transcript (~/.codex/sessions/YYYY/MM/DD/rollout-*-<SESSION_ID>.jsonl) with the router's production logs to understand what Codex rendered vs. what the upstream served on the /v1/responses path. Use when given a session ID and asked "why did X render?" (missing thinking, missing routing marker, wrong model, tool-call weirdness) for a Codex conversation routed through the router.
test-codex-locally
weave-os
Run the Weave router locally in docker compose and drive it with codex exec to reproduce and verify routing/translation/marker behavior for Codex's Responses API path. Use when verifying a router fix end-to-end for Codex, reproducing a prod Codex routing bug, confirming routing-marker / force-model / subscription-passthrough behavior, or testing a /force-model route — without touching the user's global Codex config.
debug-claude-session
weave-os
Investigate a specific Claude Code session by session ID — correlate the local transcript (~/.claude/projects/...jsonl) with the router's production logs to understand what the client rendered vs. what the upstream served. Use when given a session ID and asked "why did X render?" for a Claude Code conversation routed through the router.
Cancel Auto Command
anton-abyzov
EMERGENCY ONLY - Cancel running auto session and generate summary report.
SpecWeave Framework Expert
anton-abyzov
SpecWeave framework expert for structure, rules, spec-driven conventions. Use for SpecWeave best practices, increment lifecycle, hooks, tasks.md/spec.md, living docs sync.