Prompts
Prompt engineering and templates
Oracle
by simota
AI/MLè¨è¨ã»è©ä¾¡ã®å°éã¨ã¼ã¸ã§ã³ããããã³ããã¨ã³ã¸ãã¢ãªã³ã°ãRAGè¨è¨ãLLMã¢ããªã±ã¼ã·ã§ã³ãã¿ã¼ã³ãAIå®å ¨æ§ãè©ä¾¡ãã¬ã¼ã ã¯ã¼ã¯ãMLOpsãã³ã¹ãæé©åãã«ãã¼ã
browser-use
by aAAaqwq
AI驱动的智能浏览器自动化工具。使用LLM理解页面并自动执行任务，比传统Playwright更智能、更省token。适用于复杂交互、动态页面、需要智能决策的浏览器操作。Chrome浏览器优先。
design-trends-2026
by guia-matthieu
"Apply 2026's top graphic design trends to any creative brief. Based on Kittl × Savee's 2026 Design Trends Report (10 trends + 2 honorable mentions), backed by Adobe, Figma, and Pinterest data. Use when: Designing a brand identity — pick the right aesthetic for your audience; Creating social media assets — use trending visual languages that perform; Briefing a designer or AI image tool — give precise style direction with vocabulary and references; Refreshing a visual identity — know what's rising vs saturating; Building mood boards — combine trends intentionally with data-backed rationale."
orchestrating-agents
by oaustegard
Orchestrates parallel API instances, delegated sub-tasks, and multi-agent workflows with streaming and tool-enabled delegation patterns. Use for parallel analysis, multi-perspective reviews, or complex task decomposition.
down-skilling
by oaustegard
Distill Opus-level reasoning into optimized instructions for Haiku 4.5 (and Sonnet). Generates explicit, procedural prompts with n-shot examples that maximize smaller model performance on a given task. Use when user says "down-skill", "distill for Haiku", "optimize for Haiku", "make this work on Haiku", "generate Haiku instructions", or needs to delegate a task to a smaller model with high reliability.
categorizing-bsky-accounts
by oaustegard
Analyze and categorize Bluesky accounts by topic using keyword extraction. Use when users mention Bluesky account analysis, following/follower lists, topic discovery, account curation, or network analysis.
codex-architect
by sd0xdev
"Codex architecture consulting. Use when: designing features, evaluating architecture, getting second opinion on design. Not for: implementation (use codex-implement), code review (use codex-code-review). Output: architecture advice + design recommendations."
Cancel Auto Command
by anton-abyzov
EMERGENCY ONLY - Cancel running auto session and generate summary report.
SpecWeave Framework Expert
by 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.
Ultrathink LLM-as-Judge Validation
by anton-abyzov
Ultrathink LLM-as-Judge validation of completed work. Uses extended thinking and Opus model for thorough, independent evaluation. Use when saying "judge my code", "judge-llm", "deep validate", or as part of /sw:done closure.
TDD Red Phase - Write Failing Tests
by anton-abyzov
Write failing tests that define expected behavior. Use when saying "TDD red", "write failing tests", or "test first".
Increment Progress
by anton-abyzov
Show progress for active increments with task/AC completion. Use when saying "show progress", "status", or "how far along".
infographic-template-updater
by antvis
Update template catalogs and UI prompts after adding new infographic templates (src/templates/*.ts), including SKILL.md template list, site gallery template mappings, and the AIPlayground prompt list.
Background Jobs Monitor
by anton-abyzov
View and manage background jobs (cloning, imports, living-docs). Shows job status, progress, and logs. Use when saying "check jobs", "job status", or "background tasks".
Close Increment (PM Validated)
by anton-abyzov
Close increment with PM 3-gate validation (tasks, tests, docs). Use when all tasks complete and saying "close increment", "we're done", or "finish up".
Doctor - Installation Health Scanner
by anton-abyzov
Run installation health diagnostics - detect ghost commands, stale cache, hash mismatches, and namespace pollution. Use when saying "doctor", "health check", "diagnose installation", or "check installation".
TDD Green Phase - Make Tests Pass
by anton-abyzov
Write minimal code to make failing tests pass. Use when saying "TDD green", "make tests pass", or "implement for tests".
project-brainstorming
by athola
"Guide project ideation through Socratic questioning and constraint analysis for actionable project briefs. Use for starting projects, exploring problems, comparing approaches, feasibility. Skip if requirements are clear."
agent-teams
by athola
Coordinate Claude Code Agent Teams through filesystem-based protocol. Use
skill-authoring
by athola
'Guide to effective Claude Code skill authoring using TDD methodology
war-room
by athola
"Multi-LLM deliberation for strategic decisions via expert pressure-testing and consensus building. Use for critical, irreversible, or high-stakes architecture choices and conflicts. Skip for trivial or reversible decisions."
hook-authoring
by athola
'Use this skill BEFORE writing any hook. Check even if unsure. Use when
claude-code-debug
by NeverSight
"Troubleshoot Claude Code extensions and behavior. Triggers on: debug, troubleshoot, not working, skill not loading, hook not running, agent not found."
openai-image-gen
by 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.