retrospectSession retrospective that analyzes conversation history to produce structured feedback for both user and LLM. Use this skill whenever the user says '复盘', 'r...
Install via ClawdBot CLI:
clawdbot install zbc0315/retrospectGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Oct 7, 2026
A developer finishes a long coding session with Claude Code and wants a post-mortem on what went wrong, where time was wasted, and how they could have prompted more effectively. They invoke the retrospect skill to generate FEEDBACK_TO_HUMAN.md and FEEDBACK_TO_LLM.md.
Engineering managers or team leads use retrospect across projects to identify recurring prompting anti-patterns and LLM failure modes, then incorporate findings into their team's AI usage guidelines. This turns individual sessions into organizational learning.
An AI power user regularly runs retrospect on their sessions to sharpen their prompting skills, tracking how ambiguity in their instructions led to LLM rework. They use the responsibility analysis to distinguish their own faults from LLM misunderstandings.
A researcher or platform team runs retrospect on past sessions to capture counter-intuitive learnings about library quirks, environment gotchas, and recurring mistakes. These notes feed into fine-tuning datasets, eval sets, or internal knowledge bases.
Junior developers use retrospect to review their early AI-assisted sessions, receiving structured feedback on how clearly they framed problems and where the LLM's assumptions silently derailed work. This accelerates their skill development in AI-augmented coding.
The core session parsing and retrospective generation is free for individual developers, with paid tiers unlocking cross-project analytics, team dashboards, and historical trend tracking. Monetization occurs when usage spreads from individuals to teams.
Sell retrospectively analyzed session insights as a compliance and quality layer for companies deploying AI coding assistants at scale. Organizations get visibility into prompt quality, LLM error patterns, and team-wide learning to reduce wasted engineering hours.
Keep the retrospect skill and parser open source to drive adoption and community, while monetizing through workshops, prompt-engineering training, and custom retrospective pipelines for teams. This builds trust and network effects.
💬 Integration Tip
Requires Node.js and access to the Claude Code project transcript directory (~/.claude/projects/); pairs naturally with an Agent tool for spawning the analysis subagent, so ensure your platform supports subagent invocation or an equivalent LLM call.
Scored Jun 4, 2026
Generate ideas fast. Adapt depth and structure to what the user actually needs.
Evaluate any AI skill's quality through step-by-step diagnosis — measuring trigger accuracy, per-step execution (completion/correctness/quality), efficiency,...
通过调用 Prana 平台上的远程 agent 完成以下处理:基于100个热门TradingView Pine Script指标转换的Python技术分析工具集,提供专业的技术指标计算、分析和可视化功能 IMPORTANT: This skill has a mandatory step-by-step proc...
Provides a structured screening for stress perception using the PSS-10 scale as an independent skill in ClawHub.
Spawns real AI-powered OpenClaw sub-sessions to run multiple specialized agents concurrently for content, dev, QA, docs, and autonomous workflows.
Provides comprehensive analysis and comparison of global AI regulations, safety incidents, model evaluations, standards, and international governance for pol...