cskwork/supergoal-skill / skills/supergoal
supergoal
UnverifiedRoute objective-driven development, verification, planning, "teach/explain", codebase learning, and skill evaluation through the Supergoal workflow. Use when Supergoal is requested or an autonomous delivery workflow is needed.
templates/harness-eval-cases/revfactory-case-003-refactoring.yaml
View on GitHubid: revfactory-case-003
upstream_id: case-003
title: "Spaghetti-code refactoring"
difficulty: medium
category: refactoring
source: "RevFactory claude-code-harness"
source_url: "https://github.com/revfactory/claude-code-harness/blob/main/experiments/cases/case-003-refactoring.yaml"
runnable_fixture: "templates/harness-eval-cases/fixtures/revfactory-case-003-refactoring/"
origin_experiment: "2026-06-07 medium-hard skill-vs-baseline (SG_EVAL_CASE=003); raw dir removed 2026-07-06, runner: templates/harness-eval-cases/run-local-eval.mjs"
runtime_adapter: portable
repo_snapshot: "<git sha or immutable snapshot id>"
task: |-
Refactor the RevFactory case-003 spaghetti-code task from the upstream
case file without changing observable behavior.
acceptance:
- "Behavior stays compatible with the original implementation."
- "Responsibilities are separated into cohesive units."
- "Tests or characterization checks protect the refactor."
machine_checks:
- "characterization tests"
- "unit tests"
- "lint/typecheck/build where available"
hidden_checks:
- "edge-case behavior from original implementation"
- "no broad unrelated rewrites"
- "same public API shape"
bug_catch_matrix:
planted_or_hidden_bugs:
- "Refactor changes behavior while improving structure."
- "Shared state or parsing edge case gets lost."
expected_false_green_risk: "Agent claims cleaner code without proving behavior preservation."
extra_bug_discovery: "Record any latent behavior bug revealed by characterization tests."
regression_protection:
high_risk_fixed_red: "behavior preservation"
permanent_test_required: true
exception_allowed_only_with_reason: true
rubric:
quality_score:
method: "RevFactory-style 100-point score; 10 dimensions, each 0-10."
dimensions:
- feature_completeness
- test_coverage
- code_quality
- error_handling
- efficiency
- correctness
- architecture
- extensibility
- documentation
- dev_environment
anchors:
- "No meaningful tests cap test_coverage at 3."
- "Missing requested behavior caps feature_completeness at 7."
- "Failed machine or hidden checks cap correctness at 6."
cost_fields:
- wall_clock_minutes
- model
- reasoning_effort
- tool_calls
- token_estimate
persist_path: "docs/changelog/<YYYY-MM>/<DD-harness-eval>/cases/revfactory-case-003-refactoring.yaml"
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |