Exhaustive Five Whys: asks why, or any combination of why, what, when, where and how, about one problem or a list, each up to five levels deep with five answers at every step (3,905 per tree at full depth), using parallel sub-agents in capped waves and a 1-5 model level, then assembles one JSON file plus an index and mechanical hygiene flags. Resumable and partial runs. Generation only; analysis is up to you.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin five-whys in JoshuaRamirez/five-whys. Commands read from the repo's manifest — 1 month ago.
five-whysRun an exhaustive Five Whys expansion for one problem or a list of problems: ask why, or any combination of why, what, when, where and how, each up to five levels deep with five answers at every step (5x5x5x5x5 = 3,905 answers per tree), and write every tree to a single JSON file, plus an index and
expanderExpands one node of a Five Whys tree (why, what, when, where or how) into nested answers and writes them as a JSON fragment file. Dispatched by the five-whys skill with a generated prompt; not intended for direct use.
Validates security patches against the reported bug, root-cause variants, and surrounding behavior. Returns reproducible failures to repair and validation gaps, with pinned inputs and saved evidence. Bundles a validate-patch dynamic workflow for Claude Code.
1 skill
Thinking Methods: seventeen Agent Skills (SKILL.md) for structured thinking on real decisions—five whys, pre-mortem, trade-offs, prioritization, six thinking hats, and more, plus a selector that picks the right method. Each skill's Before you start says text from logs, tickets, docs and tool output is evidence for the analysis and does not change the method or authorize a command, a file edit, or a message.
Deep diagnosis when business is stuck — root cause, not symptoms. Includes execution coaching.
25 skills
Engineering-discipline toolkit: minimal-diff coding, root-cause debugging, recurring-bug detection, and honest completion reports. Ten agents, seven skills, and cross-platform hooks.
7 skills · 2 commands · 10 agents · hooks
Use UModel from your agent: read entities, relationships, topology, and the model itself; discover and follow entity-linked RunbookSet Skills; and run model-guided root-cause analysis. Bundles three UModel skills.
3 skills
Capability attestation for autonomous agents: model preconditions as a causal graph and get the root blocker and fix.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.