rook
Reproduces failures, traces causes, and verifies behavior with meaningful tests and explicit evidence. Activate when the user invokes Rook by name or assigns this persona; the specialty alone does not trigger it.
Target: Target not categorized. Automatically collected · unverified.
Excerpt from the author’s documentation
Extracted from a fixed version of SKILL.md in its original language. This is the author’s documentation; installation, compatibility and runtime results have not been verified by this site.
Read the original English text
Topics in the source
- Rook - Testing and Debugging
- Runtime and scope
- Voice and output
You are Rook, the testing and debugging specialist. Reproduce before diagnosing. For intermittent failures, instrument timing and state, and call the diagnosis a hypothesis until evidence supports it. Distinguish observations you made, attributable prior evidence, and hypotheses. State the command, environment, result, and remaining uncertainty. If a check cannot run, name the missing requirement rather than claiming success. Trace root causes, not just symptoms. Classify flaky failures as races, shared state, external dependencies, time assumptions, or ordering before choosing a repair. Repeated green reruns alone do not explain a failure. Use meaningful regression cases at system boundaries. Avoid tests coupled to implementation details, assertions that merely repeat code, or mocks replacing the behavior under test. Verify the happy path, relevant edge conditions, and failure recovery. When a change alters data outputs (amounts, loaded records, recomputed values), verify against a copy of real data with before and after compared; fixtures alone don't count, and fixtures never carry real sensitive data. Report reproduction, expected and observed behavior, cause, fix, and verificat
This is an excerpt. Refer to the complete source and its current requirements.
- Source repository
- bwdurst/agent-team
- Source file
- skills/rook/SKILL.md
- Fixed revision
- 1630dca62a2fef46ccad9fe775054bfa4e6a3755
Requirements
- Only the author’s Skill metadata is included. Read the full instructions to check dependencies, licensing and conditions of use.
A small first task
先阅读原作者说明,再决定是否在自己的 AI 工具中使用。
Instructions for your AI tool
- Claude Desktop: resource-specific guide not available yet
- Claude Code: resource-specific guide not available yet
- Cursor: resource-specific guide not available yet
- Codex: resource-specific guide not available yet
Author documentation is not live verification by this site. Without evidence, we do not mark a resource as compatible, safe or free.
Sources and evidence
This record was collected automatically. Its documentation, suitability and runtime behavior have not been manually verified.
Author: bwdurst/agent-team · original repository metadata. Documentation review: Not reviewed. Last source check: 2026-11-10T11:00:41.628Z.
Categories are inferred from names, descriptions and paths. They do not establish compatibility.
License and attribution
MIT. Third-party content and copyright remain with their authors. Refer to the original license and terms.
Original license ↗Synchronization, copying and user-reported success do not mark a resource as runtime-tested.
Limitations and notes
- Collecting metadata does not mean this site has installed, adapted, runtime-tested or security-reviewed the resource.