taku-compactCreate a recoverable active-work brief for context-heavy coding, design, debugging, review, research, or handoff sessions. Multi-mode context-control habit w...
Install via ClawdBot CLI:
clawdbot install kkenny0/taku-compactGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://clawhub.ai/user/kkenny0Audited Jun 5, 2026 · audit v1.0
Generated Aug 13, 2026
A developer works on a large monolithic application across multiple sessions. They use Taku Compact to create a resume brief before ending each session, capturing the next step, open todos, and recent decisions, ensuring seamless continuation without re-reading code.
A team member completes the initial implementation of a feature and hands it off to a colleague in a different timezone. They use the handoff mode to provide a detailed brief including background, decisions, changed files, and verification state, so the next person can pick up without needing a full sync.
An on-call engineer investigates an intermittent production bug. They use debug mode to track symptoms, reproduction steps, evidence collected, and failed hypotheses, allowing the next on-call engineer to continue the investigation without losing progress.
A UX designer is working on a new feature and needs to capture design constraints, tradeoffs, and open questions. They use design mode after each thinking session to preserve context for later discussions with stakeholders and developers.
Offer Taku Compact as part of a larger AI assistant free tier, with premium features like advanced analytics or collaboration tools for paid subscribers.
Provide Taku Compact as a collaboration feature for teams, allowing members to share and manage compact briefs in a shared workspace.
License Taku Compact to enterprises for internal use, with integration into their existing development workflows and security compliance.
💬 Integration Tip
Integrate Taku Compact as a slash command in your existing AI chat interface, and ensure it can read project files and git status to generate accurate briefs.
Scored Jun 5, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.