reflect-critique-revisePerforms a multi-pass senior engineer critique and revision of code, improving quality by catching bugs, API misuse, and style issues across domains like iOS...
Install via ClawdBot CLI:
clawdbot install stephenlthorn/reflect-critique-reviseGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
http://localhost:8080/v1/chat/completionsAudited Apr 22, 2026 · audit v1.0
Generated May 20, 2026
After generating a Python data processing script over 30 lines, the skill automatically runs a senior engineer critique focusing on resource leaks, exception handling, and off-by-one errors. It then revises the code, closing quality gaps before deployment.
A developer generates SwiftUI code for an iOS app. The skill always triggers for iOS/Swift, checks for missing @MainActor, deprecated APIs, and concurrency issues, then produces a revised version with fixes. This prevents common SwiftUI pitfalls.
A quant developer writes a backtesting script. The skill applies the trading checklist to detect lookahead bias, survivorship bias, and missing slippage. After revision, the backtesting logic is more robust and production-ready.
A frontend developer generates a React component. The skill runs a web checklist covering missing keys, stale closures, accessibility issues, and XSS vulnerabilities. The revised code improves rendering and security.
An analyst generates a venture capital memo. The skill uses the VC checklist to catch unit confusion, overly optimistic TAM, and missing risk factors. The final report is more analytically rigorous.
Offer the skill as an integrated step in CI/CD pipelines for teams using M2.7 models. Automatically review and improve code before pull requests, reducing manual review overhead.
Provide free basic critique with general checklist. Charge for domain-specific checklists (iOS, trading, VC) and higher pass counts, targeting individual developers and small shops.
Integrate with larger AI coding platforms as an add-on for regulated industries (finance, healthcare). Guarantee code meets regulatory standards via custom checklists.
💬 Integration Tip
For best results, run on every generated code block over 30 lines, and ensure the OPENCLAW_LLM_ENDPOINT environment variable is set to your M2.7 model endpoint.
Scored May 20, 2026
Work with Obsidian vaults (plain Markdown notes) and automate via notesmd-cli.
Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.
LinkHut bookmark management API integration with managed OAuth. Save, organize, search, and manage bookmarks with tags, notes, and privacy settings. Use this...
Manage a personal knowledge base by adding, searching, organizing, and reviewing articles, links, and notes with tags and natural language queries.
Generate a daily work report by automatically discovering all git repositories the user worked on, collecting commit logs across all branches, and summarizin...
把一本书里沉淀的方法论蒸馏成一组原子化、可被Agent调用的skills,同时产出给人看的笔记和话术库。触发:用户说'帮我拆《XX》''把XX蒸馏成skill''distill this book into skills'时。不做书摘/读后感/作者人设角色扮演。