exploration
romiluz13
Two-mode exploration skill: (1) design dialogue — turn rough ideas into validated designs through collaborative interview before planning; (2) spike — throwaway code ans…
ResearchClaude Code
164GitHub
OPENAGENTSKILL / DIRECTORY
AI Agent Skills
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
Results · “exploration”
1–7 / 7
More filters · 1
Results: 7
arbor
K-Dense-AI
Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinemen…
ResearchClaude Code
34KGitHub
agenthub
alirezarezvani
Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated…
ResearchClaude Code
25.1KGitHub
idea-discovery
wanshuiyin
Workflow 1: Full idea discovery pipeline to go from a broad research direction to validated, pilot-tested ideas. Use when user says \"找idea全流程\", \"idea discovery pipeli…
ResearchClaude Code
15.9KGitHub
interview-script
Owl-Listener
Write a structured interview guide — warm-up, core exploration, and wrap-up. Use before running interviews. For analysing what comes back, use `summarize-interview`.
ResearchClaude Code
2.5KGitHub
auto-task
yunshu0909
复杂长程任务的自主执行流程。当用户有一个复杂或模糊的任务（"帮我搞清楚 X / 帮我评估 Y / 帮我把这堆东西整理出来 / 帮我对比 N 个方案 / 帮我跑一次调研"），希望 AI 自己拆解、自己执行、自己校验、只在关键时刻找用户的场景。通过"任务确认 → 任务队列 → 分批执行 → 周期校验队列 → 触发式汇报"实现 1-2 小时无…
ResearchClaude Code
752GitHub
develop-spike-summary
product-on-purpose
Documents the results of a completed technical or design spike, capturing the original question, approach, evidence-backed findings, and a clear proceed-or-not recommend…
ResearchClaude Code
643GitHub
External platform skills
Browse external directory →Owner-curated external sources. Not filtered by the scores or compatibility controls above; excluded from GitHub rankings and automatic installation.
No external entries match this query.