spec-coachBuild-ready specification interviewer for coding agents. Use when the user has a vague app, feature, automation, product, or system idea and needs it clarifi...
Install via ClawdBot CLI:
clawdbot install brasco05/spec-coachGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Oct 8, 2026
A non-technical founder has a rough idea for a habit-tracking app but keeps getting stuck when trying to prompt a coding agent. Spec Coach interviews them one question at a time, rejects vague answers like 'make it fast', and produces a SPEC.md that Claude Code or Codex can implement directly.
A PM needs to translate a stakeholder request for an internal approvals workflow into engineering-ready requirements. Spec Coach enforces scope boundaries, measurable acceptance criteria, and explicit out-of-scope items before any sprint planning begins.
A small automation agency receives a vague client brief about 'automating our invoicing process.' The skill turns the brief into a concrete spec covering inputs, outputs, edge cases, and launch thresholds, reducing scope creep and misaligned expectations during fixed-bid projects.
A freelance developer is asked to add 'AI recommendations' to a client's e-commerce site but the request lacks detail. Spec Coach forces clarification of what data the AI can use, when humans override it, and what success looks like, preventing an open-ended build.
An operations team wants to connect their CRM to a reporting dashboard but hasn't defined data ownership or permissions. Spec Coach surfaces constraints, failure states, and decision owners, producing a spec that IT and data teams can safely implement.
Offer the core Spec Coach skill for free to individual developers to drive adoption, then charge for team features like shared spec libraries, approval workflows, and history. Upsell conversion happens when teams outgrow single-user spec files.
Use Spec Coach to run paid discovery and specification workshops for startups or enterprises before building anything. The spec becomes a paid deliverable and often leads into a follow-on development contract.
Package Spec Coach alongside coding agents, project templates, and CI checks as part of a paid developer productivity platform. The skill acts as a gatekeeper that ensures every agent task starts from an approved spec.
💬 Integration Tip
Pair Spec Coach with a coding agent like Claude Code or Codex so the approved SPEC.md can be consumed immediately in the same session. Store generated specs in version control to track scope changes and feed them back into future interviews for consistency.
Scored Oct 8, 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.
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.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.