jabrena/022-root-cause-analysis
Use when a framed problem needs root-cause investigation rather than a symptom-level fix, applying Five Whys, Fishbone (Ishikawa), Current Reality Tree, and constraint identification. This should trigger when an issue's Root Cause Analysis point of view needs evaluation, or when a maintainer directly asks to find the root cause of a problem before proposing a fix. Part of Plinth Toolkit
npx skills add https://github.com/jabrena/plinth --skill 022-root-cause-analysis
Guide the identification of root causes, not symptoms, for a framed problem, using Five Whys, Fishbone (Ishikawa), Current Reality Tree, and constraint identification. This is an interactive SKILL.
What is covered in this Skill?
023-assumption-analysis and the remaining Functional Specification lensesDistinguish root causes from symptoms before recommending a fix. When this technique is orchestrated by another workflow, the orchestrator owns clarifying-question sequencing; when applied standalone, ask directly.
references/022-root-cause-analysis.md before applying Root Cause Analysis guidanceRead references/022-root-cause-analysis.md, then identify the symptom(s) evidenced by the problem frame.
Chain "why" questions from the symptom toward an evidenced root cause, stopping when further "why" steps would require guessing.
Organize candidate causes into categories when more than one causal dimension (people, process, technology, environment) is plausible.
Connect multiple symptoms to a small number of shared core problems through cause-effect relationships when the symptoms appear related.
Name the constraint limiting the current state, distinct from the most visible or most recently reported cause.
Report findings using Five Whys, Fishbone, Current Reality Tree, and the identified constraint, and flag any finding left open pending a clarifying answer.
For detailed guidance, examples, and constraints, see references/022-root-cause-analysis.md.
Take jabrena/022-root-cause-analysis from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.