helpers/skills/doc-plan/SKILL.md
Use this skill to produce a STRAT-level documentation plan. Traverses a strategic initiative's child epics and stories to identify what documentation is needed, what type, and at what priority.
npx skillsauth add opendatahub-io/ai-helpers doc-planInstall 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.
Produce a documentation plan for a strategic initiative (STRAT) or epic by analyzing all child tickets for documentation impact.
$ARGUMENTS contains a Jira ticket key, typically a STRAT-level or epic-level ticket (e.g., RHAISTRAT-1401 or RHOAIENG-55000).
Call the MCP tool to resolve the ticket:
mcp__mcp-atlassian__jira_get_issue(issue_key="<KEY>")
Extract:
Resolve all child tickets recursively (up to 3 levels deep):
For each ticket, resolve via MCP and extract:
Cycle detection: maintain a visited set of issue keys during traversal. Before descending into any child ticket, check whether its key is already in the visited set. If so, skip that branch and record that a cycle was detected.
Limits:
For each resolved child ticket, determine:
Does this ticket affect documentation?
What type of documentation is needed?
What priority?
Dependencies?
Group documentation items by:
Identify:
Read ${CLAUDE_SKILL_DIR}/prompts/doc-plan.md for the planning prompt.
Construct the plan combining:
Write the doc plan as markdown to stdout (for the caller to review).
Also write a structured version to workspace/doc-plan.json with the JSON format from the prompt template.
The markdown plan should include:
# Documentation Plan: <STRAT summary>
**STRAT**: <KEY> — <summary>
**Generated**: <timestamp>
**Tickets analyzed**: <count>
## Summary
- **Tickets with doc impact**: N
- **Tickets without doc impact**: N
- **New concepts**: N
- **New procedures**: N
- **New references**: N
- **Updates to existing**: N
- **Release notes**: N
## Critical Priority
| Ticket | Summary | Doc Type | Modules | Dependencies |
|--------|---------|----------|---------|--------------|
| RHOAIENG-55490 | Model serving | new_procedure | proc_configure-model-serving | RHOAIENG-55489 |
## High Priority
...
## Medium Priority
...
## Low Priority
...
## No Documentation Impact
| Ticket | Summary | Reason |
|--------|---------|--------|
| RHOAIENG-55499 | Internal refactoring | No user-visible changes |
## Release Notes
| Ticket | Type | Summary |
|--------|------|---------|
| RHOAIENG-55490 | New feature | Model serving now supports custom runtimes |
Primary: Markdown doc plan (displayed to caller)
Secondary: workspace/doc-plan.json
development
Run hexora static analysis on a Python package repository to detect suspicious code patterns, then triage findings with deterministic rules and AI reasoning to produce a structured risk report section.
development
Inspect recent git history of a Python package repository for suspicious commits touching supply-chain-sensitive files, then triage findings with AI reasoning to produce a structured risk report section.
development
Scan a Python package repository for compiled/binary files using Fromager-style detection and malcontent YARA analysis, then triage findings with deterministic rules and AI reasoning to produce a structured risk report section.
testing
Use this skill to identify non-Red Hat RPM packages installed in container images or on the local machine. For containers, pulls images across multiple architectures and release tags; for local scans, inspects the host directly. Extracts RPM signing metadata and reports packages not signed with the Red Hat GPG key as CSV output. Use when auditing compliance, checking supply-chain provenance, or scanning for third-party RPMs in RHOAI component images.