recall-reasoning
Search past reasoning for relevant decisions and approaches
浏览 carmandale 维护的已发布 AI 技能,比较用途与说明,并通过来源仓库了解安装方式。
已收录技能
116收录技能的仓库 Stars 合计
115仓库 Forks
0平均每个技能的仓库 Stars
1同一仓库中的多个技能可能共享 Stars,合计包含重复仓库数据。
Search past reasoning for relevant decisions and approaches
Wiring Verification
Consult Oracle (GPT-5 Pro) for complex debugging, architecture questions, or code review. Use when stuck on a problem, need a second opinion, or want deep analysis of code. Invoked when user says "ask the oracl...
Index at Creation Time
Problem-solving strategies for proof theory in mathematical logic
Explicit Identity Across Boundaries
Check reference SDK implementations using btca ask
QLTY During Development
Parallel Agent Type Contracts
Transform feature descriptions, bug reports, or improvement ideas into well-structured project plans. Use when starting new work, creating issues, or needing to research a codebase before implementation. Includ...
Repo Updater - automation-friendly CLI for synchronizing GitHub repositories. Keep dozens or hundreds of repos in sync with a single command. Pure Bash with git plumbing, JSON output, meaningful exit codes, par...
Repo Prompt CLI - proxy MCP client for AI agents to access Repo Prompt's context engineering tools via bash. Build prompts, search code, manage file selections, chat with AI, and export context without MCP conf...
Document codebase as-is with thoughts directory for historical context
Observe Before Editing
This sop guides the implementation of code tasks using test-driven development principles, following a structured Explore, Plan, Code, Commit workflow. It balances automation with user collaboration while adher...
Analyze repository structure, patterns, conventions, and documentation for understanding a new codebase
Create git commits with user approval and no Claude attribution
Runs Ralph orchestrator with the code-assist configuration to implement code tasks autonomously. Spawns Ralph as a subprocess that handles the full TDD workflow (Explore, Plan, Code, Commit) for the given code...
No Polling for Background Agents
Named Tmux Manager - orchestrate multiple AI coding agents (Claude Code, Codex, Gemini) in tiled tmux panes with visual dashboards, command palette, context rotation, Agent Mail integration, and robot mode for...
Agentica server + Claude proxy setup - architecture, startup sequence, debugging
Completion Check Verify Infrastructure Is Wired
System health check (MOT) for skills, agents, hooks, and memory
Interactive workspace discovery - learn what tools, workflows, agents, and hooks are available
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。