compound-learnings
Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns should become skills".
发现 编程开发 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。
Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns should become skills".
Observe Before Editing
Never Use TaskOutput
Metacognitive check-ins during problem solving - detects when to pivot or persist
Create and use Claude Code slash commands - quick prompts, bash execution, file references
Implement technical plans from thoughts/shared/plans with verification
Problem-solving strategies for prime numbers in graph number theory
Release preparation workflow - security audit → E2E tests → review → changelog → docs
Unit-aware computation with Pint - convert units, dimensional analysis, unit arithmetic
Formal theorem proving with research, testing, and verification phases
Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity
Migration workflow - research → analyze → plan → implement → review
Interactive workspace discovery - learn what tools, workflows, agents, and hooks are available
Agentic Workflow Pattern
Problem-solving strategies for operator theory in functional analysis
Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging
Analyze brownfield codebase and create initial continuity ledger
Problem-solving strategies for source coding in information theory
Problem-solving strategies for natural transformations in category theory
Scrape web pages and extract content via Firecrawl MCP
Problem-solving strategies for rings in abstract algebra
Problem-solving strategies for gradient methods in optimization
Problem-solving strategies for graph algorithms in graph number theory
Problem-solving with Rudin's Real and Complex Analysis textbook
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。