prompts/squad/skills/prove-it-bugfix/SKILL.md
DevSquad-style bug-fix flow — reproduce, write a failing test, fix, verify. Use this whenever the squad task is "fix bug X" or the Planner flags a step as a bug repro.
npx skillsauth add imabusyman/CodebrewRouter prove-it-bugfixInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
When the task is to fix a bug, the squad proves the bug before the fix, then proves the fix with the same test.
dotnet build --no-incremental -warnaserror
dotnet test --no-build --collect:"XPlat Code Coverage"
| Phase | Owner | Output |
|---|---|---|
| Reproduce | Planner | spec.md §"Current state" with the failing code path cited |
| Red | Tester | <Area>/<Class>Tests.cs with [Fact] that fails against baseline |
| Root cause | Coder | Log entry (MEDIUM): "Failure reason: <compiler | runtime | logic>" |
| Green | Coder | Minimal diff on the bug site |
| Gate | Coder (build) → Tester (test + coverage) | [CHECKPOINT] then [DONE] |
| Verify | Reviewer | Reread diff, confirm fix is minimal, no new CRITICAL/HIGH findings |
#nullable disable or Assert.True(true) in place of real assertions → CRITICAL.Prove-It runs append one reasoning-log entry per phase flip:
## <ts> — tester — HIGH
Decision: captured <bug-name> with assertion on <invariant>
Rationale: test fails against commit <sha> (pre-fix); passes against current HEAD
Evidence: Blaze.LlmGateway.Tests/<Area>/<Class>Tests.cs:<line>
development
Generate a Product Requirements Document from a task description, user intent, or PRD outline. Structure the PRD with sections: Overview, Problem Statement, Goals, Scope, Features, Acceptance Criteria, Metrics. Use this when the Planner or Orchestrator needs to formalize requirements before decomposing into implementation steps.
development
Compose parallel teams of specialized agents for a multi-faceted task. Map subtasks to agent roles, balance workload, and validate team composition. Use this when breaking a task into parallel streams that require different expertise (Coder, Tester, Infra, etc.).
development
Delegate implementation work to specialized subagent instances, each inheriting a task scope and constraints from the parent. Emit structured handoffs, monitor completion signals, aggregate results. Use this in the Orchestrator parallel path when spawning independent Coder/Tester/Infra subagents from a single coordinator.
testing
Maintain the append-only reasoning log and write handoff envelopes for every squad delegation. Use this when the Conductor delegates to a specialist or when a specialist records a non-trivial decision.