Marvino-Fransisco
Marvino-Fransisco/agent-registry
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/Marvino-Fransisco/agent-registry --skill research命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Use this skill when working on tasks, answering questions, or brainstorming related to backend systems and engineering. Focus on architecture, project setup, system design patterns, and code quality standards.
Use this skill when you are creating new agent and editing an existing agent.
Create and configure new custom AI skills with specific standards, references, and instructions. Use this for requests like "make a skill", "create a custom skill", "build a new skill", or "set up a new skill".
正在显示 SKILL.md
基于 SOC 职业分类
| name | research |
| description | Use this skill when doing any researches |
This skill covers the full spectrum of researches best practice. Read the appropriate standards when doing research.
You must read every file in the table below before doing any work.
Do not skip any file. Do not skim. Read each one fully.
After reading all files, output this confirmation:
"✅ Standards loaded: [list each file you read] Key constraints I will follow: [2–3 sentences summarising the most critical rules] Proceeding."
You may not proceed to any task until this confirmation is emitted.
| File | Purpose |
|---|---|
standards/research-api-exploration.md | Map a third-party API's capabilities, constraints, auth, rate limits, and integration cost before building against it |
standards/research-architecture-pattern.md | Identify proven architecture patterns, explain trade-offs with evidence, and recommend the best fit for the project's scale and constraints |
standards/research-cve-scan.md | Determine whether specific CVEs affect the project, assess exploitability in context, and produce a remediation plan |
standards/research-dependency-audit.md | Produce a dependency health report covering security vulnerabilities, abandoned packages, license risks, duplicates, and unused dependencies |
standards/research-library-comparison.md | Compare libraries with an evidence-backed recommendation — functionality, performance, DX, maintenance, license, and migration cost |
standards/research-markdown-format.md | Canonical report template and writing style rules to enforce a consistent, scannable, decision-ready format across all research reports |
standards/research-performance-benchmark.md | Find or produce credible benchmark data and interpret it against the project's actual load profile and SLA |
standards/research-security-advisory.md | Surface known vulnerabilities, security anti-patterns, and best practices with actionable findings |
standards/research-tech-landscape.md | Map a technology's ecosystem readiness, adoption signals, community health, maturity, and trajectory before committing |
standards/research-toolchain-eval.md | Choose the right toolchain for build, test, lint, CI/CD, and IaC based on speed, DX, CI integration, and migration cost |