From docs-tools
Performs technical accuracy review of documentation drafts (.adoc/.md) for JIRA tickets by dispatching technical-reviewer agent, outputs confidence-rated report (HIGH/MEDIUM/LOW).
npx claudepluginhub redhat-documentation/redhat-docs-agent-tools --plugin docs-toolsThis skill is limited to using the following tools:
Step skill for the docs-orchestrator pipeline. Follows the step skill contract: **parse args → dispatch agent → write output**.
Reviews documentation drafts for style guide compliance using Vale linting and Red Hat/IBM skills. Edits AsciiDoc or MkDocs files in place for JIRA tickets.
Reviews Markdown documents and tech specs via Codex MCP in 5 dimensions: architecture design, performance, security, documentation quality, code consistency. Outputs rating table and merge gate for audits.
Reviews generated/updated documentation (MD files, beads issues, specs, task lists) with multi-LLM parallel analysis for inconsistencies, codebase mismatches, gaps. Interactive synthesis and fixes.
Share bugs, ideas, or general feedback.
Step skill for the docs-orchestrator pipeline. Follows the step skill contract: parse args → dispatch agent → write output.
This skill performs a single review pass. The iteration loop (re-running with fixes between passes) is driven by the orchestrator skill, not this step skill.
$1 — JIRA ticket ID (required)--base-path <path> — Base output path (e.g., .claude/docs/proj-123)<base-path>/writing/
<base-path>/technical-review/review.md
Extract the ticket ID and --base-path from the args string.
Set the paths:
DRAFTS_DIR="${BASE_PATH}/writing"
OUTPUT_DIR="${BASE_PATH}/technical-review"
OUTPUT_FILE="${OUTPUT_DIR}/review.md"
mkdir -p "$OUTPUT_DIR"
Dispatch the technical-reviewer agent with the following prompt.
Agent tool parameters:
subagent_type: technical-reviewerdescription: Technical review of documentation for <TICKET>Prompt:
Perform a technical review of the documentation drafts for ticket
<TICKET>. Source drafts location:<DRAFTS_DIR>/Review all .adoc and .md files. Follow your standard review methodology. Save your review report to:<OUTPUT_FILE>The report must include an
Overall technical confidence: HIGH|MEDIUM|LOWline.
After the agent completes, verify the review report exists at <OUTPUT_FILE>.
The review report must include an Overall technical confidence: HIGH|MEDIUM|LOW line. If this line is missing from the output, the orchestrator will treat it as a step failure.