Skill Claude CodeCodex
Investigate agent-side failures in the autofix-skills plugin. Covers wrong verdicts, review loop issues, state machine bugs, and prompt problems. Use when the agent ran but produced wrong results.
Instructions file CodexOpenCode
Instructions for opendatahub-io/autofix-skills, covering autofix-skills, repository structure, hooks, architecture and artifact declarations.
Instructions file
Instructions for opendatahub-io/autofix-skills, a project described as: Claude Code plugin providing orchestrator skills, prompt files, and state management scripts for the Jira autofix pipeline.
Hook
Runs when a session starts on compact, executing dispatch-recovery.sh. From opendatahub-io/autofix-skills.
Skill Claude CodeCodex
Use when orchestrating CVE remediation for a Jira Vulnerability ticket. Uses a Python state machine (cvepipeline.py) for deterministic routing between scan, fix, verify, VEX, review, and PR creation agents. Never writes fix code directly.
Skill Claude CodeCodex
Disambiguate which repository URL is the actual target when a Jira ticket mentions multiple repos. Reads ticket context and candidate URLs, classifies each URL, and writes a verdict with the target and confidence level.
Skill Claude CodeCodex
Use when orchestrating a Jira ticket fix end-to-end. Dispatches to implement and review prompt agents in a loop, uses state.py for persistence, and evaluates findings to decide iteration. Never writes code directly.
Skill Claude CodeCodex
Use when assessing a Jira bug ticket for AI autofix readiness. Produces a structured JSON verdict (ready/needsinfo/notfixable) based on a three-gate rubric. Designed for CI pipeline use with the autofix pipeline orchestrator.
opendatahub-io/rhaii-cluster-validation
Instructions file
Instructions for opendatahub-io/rhaii-cluster-validation, covering claude.md, project overview, build and test commands, architecture and two execution modes.