agent-readiness
Assesses and improves a git repository's readiness for AI coding agents with the agentready tool, and reports the score, the certification level, the failing findings, and where the report was written. Covers one repository or every RHDH repository under a directory, and applies the fixes the report supports. Use for "assess agent readiness", "run agentready", "improve our agent readiness score", "prepare this repository for coding agents", or "assess all the RHDH repositories".
How do I install this agent skill?
npx skills add https://github.com/redhat-developer/rhdh-skills --skill agent-readinessIs this agent skill safe to install?
- Gen Agent Trust Hubfail
This skill downloads and executes a tool directly from a remote GitHub repository at runtime. It also analyzes various files within target repositories, which could potentially lead to indirect prompt injection if those files are malicious.
- Socketpass
No alerts
- Snykwarn
Risk: MEDIUM · 1 issue
What does this agent skill do?
RHDH Agent Readiness
Use an agentready report as the source of truth for repository-readiness work. The skill supports any git repository and adds RHDH context when the repository belongs to the RHDH ecosystem.
Principles
- Write assessment output to the OS temporary directory so reports never pollute the target repository.
- Apply only fixes supported by the report. Ask for project-specific facts; never invent architecture or design rationale.
- For a recognized RHDH repository, use
/rhdh-contextfor repository ownership, technology, key paths, and conventions. Continue generically when RHDH context is unavailable. - Treat a fresh post-change assessment as the completion criterion for every remediation run.
Route the request
| Request | Reference |
|---|---|
| Assess or improve one repository | references/assessment.md, then references/remediation.md when fixes are requested |
| Assess all RHDH repositories under a directory | references/batch.md |
When no path or mode is given, recommend the current repository as the default and offer batch assessment as the alternative.
Completion
- Assessment-only work is complete when the current score, certification, failing findings, and report location have been presented.
- Remediation work is complete when a fresh assessment shows the before/after result and every remaining failure is identified as unresolved, deferred, or inapplicable.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/redhat-developer/rhdh-skills/agent-readiness">View agent-readiness on skillZs</a>