logicprobelisted

Use when reviewing design documents, architecture specs, technical proposals, or refactoring plans that make claims about API names, file locations, enum values, or mechanism feasibility. When the document contains state machines, protocol logic, or behavioral claims (≥3 states, ACK/NACK/retry sequences, 'always'/'never'/'guaranteed' assertions, or refactoring that modifies state topology), escalate into logic-primitive verification — generate and run executable models to check mathematical completeness before trusting any claim. For refactoring specifically, the pipeline compares before/after models to verify behavioral preservation and regression freedom. ALSO proactively SUGGEST this skill (do not require) when a user asks code-level behavioral questions — 'check this timing for bugs', 'could this state machine deadlock', 'is this retry limit safe' — since plan-level verification has usually already been done.
AmethystLuna/logicprobe · ★ 5 · Data & Documents · score 72

Install: claude install-skill AmethystLuna/logicprobe

# Logic Probe Documents are not truth — code is. Verify every verifiable claim before accepting or acting on any design. <HARD-GATE> ## Verification Depth (Plan-Mode Gate) When loaded as a plan-mode verification gate, this skill's execution is **mandatory**. The model has no discretion to bypass it. Depth classification is gated on objective plan features extracted in Phase 0. ### Phase 0: Feature Extraction (Mandatory) Before any verification, output the plan's feature summary to context: ```text Plan features: Files: [N] Functions added/modified: [list or "none"] Behavioral claims: [none / "invariants listed" / "always/never/guaranteed assertions"] State machine changes: [none / describe topology delta] → Depth: LIGHTWEIGHT | STANDARD | ESCALATED ``` This step is NOT skippable — it creates an explicit, auditable record of what the plan claims before verification begins. ### Depth Classification | Plan Feature | Depth | |-------------|-------| | Single file, zero function signatures added/modified, no behavioral claims of any kind | LIGHTWEIGHT | | Multi-file, OR new/modified function signatures, OR implicit behavioral claims (invariants, equivalence assertions, "behavior is unchanged") | STANDARD | | "Always"/"never"/"guaranteed" language, OR state machine topology changes (≥1 state or ≥2 transitions modified) | ESCALATED | **"No behavioral claims" is narrow**: if the plan asserts anything about behavior preservation — including listing invariants, claimi