Investigate unclear failures, intermittent behavior, and performance regressions before changing code. Separate symptoms from assumptions, trace how failures arise, and rank possible causes by evidence and ease of testing, then report the cause and supporting proof.
Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.
Investigate failures with unclear causes by gathering evidence before changing code. The skill separates observed symptoms from inferred causes, then traces inputs, state changes, boundaries of responsibility, and failure output. Possible explanations are ranked by the strength of their evidence and how easily they can be disproved with little effort. Product code remains unedited until a credible mechanism explains the evidence.
Use it for failures with unknown triggering conditions, problems that happen only occasionally, or processing that has become slower than before. It also helps when several causes seem possible and you want to organize the evidence before moving ahead with a fix based on an assumption. The investigation compares hypotheses in an order guided by evidence and the effort needed to test them.
Investigation stops when enough evidence identifies the cause or a specific obstacle blocking further investigation. The report states the cause and supporting evidence. A fix is implemented only when the request authorizes it.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.
The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 20, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
Gather evidence before changing product code.
Report cause and proof. Make no fix unless task authorizes implementation.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Delegate code lookup, small edits, and diff reviews to three specialized subagents. Their compact, structured results help conserve the main agent's context, with guidance on when to delegate and when to keep work in the main conversation.
Make agent replies shorter and easier to scan by putting answers first and removing filler. Preserves technical details, exact commands, numbers, and essential conditions while keeping the user's chosen language.
Create short commit messages using Conventional Commits, a format that labels the type of change. Emphasize intent, keep the subject concise, and include explanatory text when breaking changes, security fixes, data migrations, or reversions require context.
Compress memory files and task lists into shorter wording to reduce input tokens. Keeps code and document structure intact, saves a readable backup separately, and sends the text to the configured model provider.
Find LLM workflows in a codebase and label them by the job they perform, so Caveman Cloud can separate spending by workflow. Present a labeling proposal for approval, apply focused code changes, and check an affected execution path.
Review Caveman Cloud spending, latency, errors, and potential improvements using current reports and traces, or individual execution records. Produce findings tied to time windows and trace IDs, while keeping measured costs, estimated opportunities, and verified savings separate.