메뉴
Polished verifier skill with drift report and CHECKLIST.md output for spec-kit parity
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Scaffold a complete agent-package project with all config files, Docker infrastructure, MCP server, A2A agent, and API client stubs. Use when creating a brand-new agent-package from scratch, bootstrapping a new MCP/agent/api-client project, or when the user says "create a new agent package". This delegates domain-specific implementation to existing skills (api-client-builder, mcp- builder, agent-builder, skill-graph-builder). Do NOT use for modifying an existing agent package — use the individual skills directly.
Browser automation CLI for AI agents using the agent-browser tool. Use when the user needs to interact with websites including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
Guide for building scalable Pydantic AI agents. Use this skill when the user wants to create a new agent package or modify an existing agent's architecture, to ensure it follows the standardized agent patterns using `agent-utilities`.
The `agent-spawner` skill provides the ability to dynamically create a new Pydantic AI agent configured with an external MCP server toolkit. This is extremely useful when an agent wants to spin up a sub-agent with specialized tools defined in an `mcp_config.json`, and interact with that agent immediately without modifying the parent agent's state or toolset.
Consolidated skill for managing, dispatching, and orchestrating other agents via the agent-manager CLI, as well as workflows for A2A communication, orchestration, and parallel subagent dispatch.
Use when executing implementation plans with independent tasks in the current session
| name | spec-verifier |
| domain | development |
| skill_type | skill |
| description | Polished verifier skill with drift report and CHECKLIST.md output for spec-kit parity |
| license | MIT |
| tags | ["verifier","sdd","qa"] |
| metadata | {"version":"1.2.1","author":"Genius"} |
You are the Spec Verifier agent in a Spec-Driven Development workflow.
Your goal is to ensure the implementation strategy (Plan and Tasks) is 100% aligned with the Specification and Constitution.
spec.md against the tasks.md.plan.md adheres to the technical stack and principles defined in constitution.md.kg_concept_search via the agent-utilities-kg MCP server) for any CONCEPT: IDs found in the spec or plan. Verify that the concept still exists and its definition matches the implementation intent.Output a structured report (either as a new file .specify/specs/<feature-id>/DRIFT_REPORT.md or as a section in your response) containing:
Generate .specify/specs/<feature-id>/CHECKLIST.md with binary pass/fail items for:
Include a final section with a summary score (0-100%) and a clear "Pass/Fail/Needs Revision" status.
Output only valid markdown. Do not add conversational filler.