github-evidence-research Agent Skill

Research GitHub as an evidence base: inspect code implementations, execution paths, project claims, releases, issues, pull requests, discussions, and repository signals, then synthesize them into traceable evidence-backed conclusions with explicit limits.

Install

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

For a global Codex installation without prompts:

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

Review-first installation prompt

Install this Agent Skill for me.

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

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/
└── github-evidence-research/
    ├── SKILL.md
    └── agents/
        └── openai.yaml

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

Security and privacy notes

• The Skill defaults to read-only GitHub research. It tells the agent not to create, edit, comment, label, merge, star, or otherwise mutate GitHub unless the user explicitly requests it.
• The Skill does not grant GitHub access. The receiving agent can only inspect repositories permitted by its connected GitHub account, CLI session, browser session, or public access.
• An authenticated tool may expose private repositories. Before sharing an answer publicly, review it for private source code, internal issue content, non-public repository names, confidential links, user data, and organization-specific conclusions.
• Never paste GitHub tokens or other credentials into chat. Configure authorization through the receiving product or GitHub CLI instead.
• Issue samples are not prevalence data, closed issues do not prove a fix, and stars or forks do not prove correctness or effectiveness. The Skill enforces these boundaries, but users should still inspect the direct links supporting important decisions.
• The install command follows the current repository state unless the receiver pins a tag or commit. Security-sensitive users should install or review an immutable release.

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.