memory-management
Store and recall memories across Claude Code sessions. Cures AI amnesia - remember decisions, preferences, and learnings.
发现 测试与安全 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。
Store and recall memories across Claude Code sessions. Cures AI amnesia - remember decisions, preferences, and learnings.
Use when starting tasks to recall relevant context, or when completing work that should be remembered
原生搜索开发助手。提供高性能的 POI 搜索、输入提示、逆地理编码功能的开发指引。
Cancel an active Ralph Loop and clean up state files. Triggers on: '/cancel-ralph', 'cancel ralph', 'stop ralph', 'kill ralph loop', 'abort ralph'.
MUST be used when creating pull requests. Handles context gathering, title generation (conventional commit format), body formatting, and PR creation via GitHub CLI. Creates PRs as drafts by default. Triggers on...
Initialize or migrate to nested CLAUDE.md structure for progressive disclosure. Claude auto-loads CLAUDE.md from any directory it reads, enabling true contextual guidance. Triggers on: '/init-deep', 'deep init'...
Plan-then-execute workflow combining structured planning with autonomous Ralph Loop execution. Triggers on: '/ralph-plan ', 'plan and execute', 'plan then execute', 'smart ralph'. Creates plan via interview and...
Start a Ralph Loop - an autonomous iteration pattern for completing complex tasks. Triggers on: '/ralph-loop ', 'ralph loop', 'start ralph'. Creates state in .claude/ralph/, injects ultrawork mode, and iterates...
Structured planning with draft management. Use this skill when the user wants to plan a feature, task, or project before implementation. Triggers on: '/plan ', 'let's plan', 'plan for', 'help me plan'. Creates...
Git worktree automation for isolated feature development. Triggers on: '/worktree create', '/worktree list', '/worktree remove'. Creates isolated working directories with automatic setup.
MUST be used for ANY git workflow that involves committing code. This includes explicit commit requests AND implicit ones like 'ship it', 'wrap it up', or finishing implementation work. Handles staging, message...
Create new blog posts with proper frontmatter, structure, and ScottInk voice. Use when writing blog posts or starting technical articles.
Audit local analytics for bot traffic, referrer spam, and data quality. Use when investigating discrepancies between Fathom and local stats.
Validate blog posts for quality, consistency, en-GB spelling, and ScottInk style. Use when reviewing posts before publication.
Prepare newsletters for publication by validating format, structure, frontmatter, and content. Use when reviewing drafts before sending.
Write in Scott's authentic voice - British, conversational, self-deprecating, code-first. Use when writing blog posts, technical content, or documentation.
Lint content for spelling errors, en-GB compliance, and writing quality. Use when checking markdown files before publication.
Use when building, auditing, or reviewing SvelteKit remote functions for validation, batching, and optimistic UI patterns
Search, filter, and retrieve Claude/Codex history indexed by the memex CLI. Use when the user wants to index history, run lexical/semantic/hybrid search, fetch full transcripts, or produce LLM-friendly JSON out...
Search, filter, and retrieve Claude/Codex history indexed by the automem CLI. Use when the user wants to index history, run lexical/semantic/hybrid search, fetch full transcripts, or produce LLM-friendly JSON o...
Search memex for user feedback patterns (frustration, corrections, praise, successful outcomes) to identify recurring mistakes and wins, then generate CLAUDE.md or AGENTS.md improvements.
Stage meaningful diffs and create commits with WHY-focused messages. Use when agent needs to commit code changes.
Use this skill when the user asks to save, remember, recall, or organize memories. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check your notes', 'clean up memories'...
Claude Codeセッションの標準的なMarkdownフォーマット規約。セッションログ、対話履歴、ツール実行結果を一貫した構造で記録する必要がある場合に使用。不正確な情報への注釈方法とnb標準のハッシュタグ形式も定義
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。