skills/autoresearch/SKILL.md
Stateful validator-gated research loop with native-hook persistence
npx skillsauth add Goblin1024/oh-my-kimi autoresearchInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Autoresearch is the skill-first replacement for the deprecated omx autoresearch command.
It keeps the useful measured-research loop, but it now runs as a native-hook stateful workflow instead of a direct CLI or tmux launch surface.
omx autoresearch command surface (hard-deprecated)mission-validator-scriptprompt-architect-artifact.omk/state/.../autoresearch-state.json including:
validation_modecompletion_artifact_pathmission_validator_command or validator_promptoutput_artifact_path$deep-interview --autoresearch for intake and $autoresearch for execution.mission-validator-scriptThe completion artifact must exist and record a passing validator result, for example:
{
"status": "passed",
"passed": true,
"summary": "metric improved beyond baseline"
}
prompt-architect-artifactThe completion artifact must include both an architect approval verdict and an output artifact path, for example:
{
"validator_prompt": "Review the research output against the mission.",
"architect_review": { "verdict": "approved" },
"output_artifact_path": ".omk/specs/autoresearch-demo/report.md"
}
$deep-interview --autoresearch to clarify mission + evaluator..omk/specs/autoresearch-{slug}/mission.md, sandbox.md, and result.json.$autoresearch with the chosen validation mode stored in mode state.omx autoresearch is hard-deprecated.data-ai
Kimi-native team worker protocol (ACK, mailbox, task lifecycle)
documentation
Persistent markdown project wiki stored under .omk/wiki with keyword search and lifecycle capture
development
URL-driven website cloning with visual + functional verification
testing
Structured visual QA verdict for screenshot-to-reference comparisons