Skip to content

feasibility-review

Internal forked reviewer sub-agent (context: fork, model: opus) for the strategy workflow. Acts as a staff engineer assessing refined strategy features in artifacts/strat-tasks/ for technical feasibility: whether the proposed approach actually works, whether it delivers what the source RFE asks for (flagging silent scope reduction), whether the effort estimate / T-shirt size is credible, and what hidden dependencies or integration challenges will surface during implementation. Grounds assessments in architecture context and overlays, takes an adversarial stance toward optimistic estimates, and emits an approve / revise / reject recommendation.

Plugin: rfe-creator | Internal

Contract

Skill Contract canonical-skill-v1

Review strategy features for technical feasibility, implementation complexity, and effort estimate credibility.

Identity

Functions
review
Success
  • Produces a feasibility assessment for each strategy with a recommendation.
  • Grounds findings in architecture context when available.

Optimization Targets

task_success judge SKILL.md @ c8a2a1e

Invariants

Must Preserve
  • Do not approve strategies with fundamental technical flaws.
  • Do not fabricate architecture constraints not present in the docs.
Fixed Context
toolsRead, Grep, Glob
knowledgerepository_contentpublic, task_inputtask_private

Traceability

Skill
.claude/skills/feasibility-review/SKILL.md

Diagram

feasibility-review diagram

Usage

/feasibility-review