spec-developer自动化 Spec 驱动开发流程 (spec-draft, spec-plan, spec-execute)
Install via ClawdBot CLI:
clawdbot install soponcd/spec-developerGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/soponcd/timeflow-skills/tree/main/teams/skills/spec-developerAudited Apr 17, 2026 · audit v1.0
Generated May 9, 2026
Developers quickly create structured specs from brief descriptions, reducing time from idea to documented requirements. Ideal for teams adopting spec-driven development to maintain consistent documentation.
Automatically extract tasks from specs and maintain a unified task board. This ensures all features are broken down into actionable items with continuous task numbering, benefiting project management.
From spec reading to code writing, test execution, and status update, the agent autonomously implements features. This accelerates development cycles, especially for routine or well-defined functionalities.
During execution, the agent enforces coding standards (e.g., Swift 6 concurrency) and runs tests, ensuring code quality and adherence to project guidelines without manual oversight.
New developers can use the spec-developer skill to quickly contribute by drafting specs and executing tasks, following established templates and processes without deep prior knowledge of the codebase.
Offer basic spec-drafting and planning for free, with advanced features like automated execution and priority support as paid tiers.
Charge per developer per month, providing access to the full skill package including unlimited spec executions and integration support.
Package spec-developer with other skills (e.g., testing or deployment) and sell as a comprehensive development suite to enterprises.
💬 Integration Tip
Integrate with existing task management tools (e.g., Jira) by mapping spec tasks to issues via API, and ensure the agent has access to your code repository and test scripts.
Scored Jun 29, 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.