research-before-answer Agent Skill

Research the live web before answering, grade the strength of implementation evidence, test whether external cases transfer to the user's situation, and turn the result into an actionable recommendation with explicit uncertainty.

This repository is prepared for distribution through a public GitHub repository and installation with the skills CLI.

Install

npx skills add https://github.com/carrieluu/research-before-answer-agent-skill --skill research-before-answer

For a global Codex installation without prompts:

npx skills add https://github.com/carrieluu/research-before-answer-agent-skill --skill research-before-answer --agent codex --global --copy --yes

The skills CLI documents that it collects anonymous telemetry by default, including the skill name, skill files, and a timestamp. To opt out for the install command:

DISABLE_TELEMETRY=1 npx skills add https://github.com/carrieluu/research-before-answer-agent-skill --skill research-before-answer

Review-first installation prompt

Install this Agent Skill for me.

Skill page: https://github.com/carrieluu/research-before-answer-agent-skill
Source URL: https://github.com/carrieluu/research-before-answer-agent-skill/tree/main/skills/research-before-answer
Skill name: research-before-answer
Creator: carrieluu
Preferred install command: npx skills add https://github.com/carrieluu/research-before-answer-agent-skill --skill research-before-answer

Please open the skill page and source, review SKILL.md plus any companion files, and explain anything risky before installing.

If shell commands are available, prefer the install command above. If you install manually, copy the complete skill directory that contains SKILL.md, including scripts, references, assets, agents, and any other files shown on the skill page. Preserve the relative folder structure. Do not install SKILL.md alone. After installing, verify the target skills folder contains SKILL.md and all companion files needed by this skill.

Package contents

skills/
└── research-before-answer/
    ├── SKILL.md
    └── agents/
        └── openai.yaml

The Skill is instruction-only. It contains no scripts, executables, binary assets, symlinks, network endpoints, credentials, or bundled dependencies.

Security and privacy notes

• The Skill asks the agent to use live search or browsing. It does not grant network access itself; the receiving agent must already provide an appropriate research tool.
• Search queries and opened pages may be processed by the receiver's search, browser, or connector provider. Do not include passwords, tokens, private customer data, or other secrets in research queries.
• If browsing is unavailable, the Skill requires the agent to disclose that limitation and must not claim that live verification occurred.
• The install command follows the current repository state unless the receiver pins a tag or commit. Publish immutable release tags and ask security-sensitive users to review the exact release they install.
• Review the full directory again after every update. A clean current version does not guarantee that a future version is safe.

License

MIT. See LICENSE.

Marketplace listing

The GitHub repository is the canonical Skill page until a marketplace listing exists. A public GitHub repository does not guarantee automatic listing by any particular marketplace. When a SkillsMP or skills.sh page is available, add its URL to the review-first installation prompt without changing the source URL.