Evidence-first pull request review with independent critique, selective challenger review, and human handoff.
89
92%
Does it follow best practices?
Impact
89%
1.36xAverage score across 43 eval scenarios
Risky
Do not use without reviewing
Independent review is more valuable than same-context self-review. The tile must enforce separation between authoring and reviewing.
Run reviewer skills in a separate agent session that receives only the evidence pack and raw diff. The reviewing agent does not receive the authoring prompt, the authoring agent's reasoning, or the authoring session's tool call history. Report context_isolation: true.
Because Tessl skills within a tile share the same context window, structural isolation requires a separate agent session. If a separate session is not available or not supported by the runtime, fall back to soft isolation:
context_isolation: falseThe tile should attempt structural isolation first and degrade to soft isolation automatically.
reviewer_mode: fresh_eyes | challengerreviewer_model_family: stringcontext_isolation: true | falseauthoring_model_family: string | unknownevals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10
scenario-11
scenario-12
scenario-13
scenario-14
scenario-15
scenario-16
scenario-17
scenario-18
scenario-19
scenario-20
scenario-21
scenario-22
scenario-23
scenario-24
scenario-25
scenario-26
scenario-27
scenario-28
scenario-29
scenario-30
scenario-31
scenario-32
scenario-33
scenario-34
scenario-35
scenario-36
scenario-37
scenario-38
scenario-39
scenario-40
scenario-41
scenario-42
scenario-43
rules
skills
challenger-review
finding-synthesizer
fresh-eyes-review
human-review-handoff
pr-evidence-builder
review-retrospective