Session Insights
技能 已验证 活跃Analyze past Claude Code sessions to extract patterns, metrics, and recommendations.
To provide developers and teams with a clear understanding of their Claude Code usage patterns, identify areas for improvement, and suggest actionable steps to enhance productivity and code quality.
功能
- Analyzes past Claude Code sessions
- Extracts patterns, metrics, and recommendations
- Collects data from various project sources
- Generates actionable recommendations
- Feeds into a practices pipeline
使用场景
- Understanding team's Claude Code usage and effectiveness
- Identifying areas where new Claude Code rules or practices are needed
- Tracking project configuration quality over time
- Improving developer productivity by optimizing Claude Code utilization
非目标
- Replacing the core Claude Code functionality
- Directly executing code or making project modifications
- Analyzing code unrelated to Claude Code sessions or configurations
工作流
- Gather session data from project sources
- Compute metrics from available data
- Generate recommendations based on metrics
- Feed top recommendations into practices pipeline
- Output a structured report
实践
- insights
- configuration
先决条件
- Claude Code runtime
- Access to project session data (`~/.claude/metrics/`, `CLAUDE_ERRORS.md`, git log, `.claude/agent-memory/`, registry history)
安装
请先添加 Marketplace
/plugin marketplace add luiseiman/claude-kit/plugin install claude-kit@dotforge质量评分
已验证类似扩展
Measure OKR Grader
99Scores completed OKR sets at cycle close with KR-level scoring per the canonical OKR type enum (committed | aspirational | learning | operational_health | compliance_or_safety), committed-vs-aspirational interpretation, evidence quality assessment, learning synthesis, and next-cycle recommendations. Refuses to retroactively change targets or shrink committed scope, average away guardrail KRs, treat 0.7 as success for committed or compliance_or_safety KRs, equate effort with impact, or use scores for individual performance. Hands off to iterate-lessons-log, iterate-retrospective, define-hypothesis, measure-dashboard-requirements, measure-instrumentation-spec, and foundation-okr-writer.
Metal
100Extract the conceptual essence of a repository as skills, agents, and teams — the project's roles, procedures, and coordination patterns expressed as agentskills.io-standard definitions. Reads an arbitrary codebase and produces generalized definitions that capture WHAT the project does and WHO operates it, without replicating HOW it does it. Use when onboarding to a new codebase and wanting to understand its conceptual architecture, when bootstrapping an agentic system from an existing project, when studying a project's organizational DNA for cross-pollination, or when creating a skill/agent/team library inspired by a reference implementation.
Lean Ctx
100AI 代理的上下文运行时 — 包含 59 个 MCP 工具、10 种读取模式、95+ 种 shell 模式、支持 18 种语言的 tree-sitter AST。将 LLM 上下文压缩高达 99%。用于读取文件、运行 shell 命令、搜索代码或探索目录。如果不存在，则自动安装。
Pathfinder
100将代码库映射为按功能分组的流程图，识别不同功能之间的重复关注点，并提出统一的架构。在被要求“寻找理想路径”、统一重复系统或在重构前审计架构时使用。输出一个建议的统一流程图以及针对每个系统的“制定计划”提示。
Codacy Audit
100Codacy Cloud workflow for this repository -- run Codacy's analyzers locally before `git push` (mirrors what Codacy CI runs), and fetch/cluster Codacy issues for any PR via the v3 API. Use when the user mentions Codacy, "codacy analysis", `codacy-analysis-cli`, "codacy issues on PR", "fix codacy CI", "codacy markdownlint findings", or any Codacy gate failing on a netdata-org PR. Ships scripts analyze-local.sh (docker/binary runner for codacy-analysis-cli) and pr-issues.sh (paginated v3 issue fetch + group-by tool/pattern/severity/file). Token-safe -- CODACY_TOKEN never reaches assistant-visible stdout. Read-only by design in the current SOW; write actions (mark FP, mark fixed) are deferred.
Domain Extract
100Extract domain knowledge from existing project sources and generate domain rules. Also handles vault sync and domain listing.