write-error-divergence
L1 trigger - audits file/database write paths for metadata commits, cache updates, and success returns that diverge when writes fail.
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
L1 trigger - audits file/database write paths for metadata commits, cache updates, and success returns that diverge when writes fail.
审查 `docs/00_设计文档/` 中设计文档的结构、边界、命名、图文一致性和部署事实是否成立。Use when the user asks for review/审查, or after creating or updating architecture, deployment, runtime dependency, or validation design docs.
Reverse engineering assistant powered by Ghidra. Use for binary analysis, decompilation, vulnerability research, auditing compiled code, renaming symbols, annotating disassembly, cross-references, or any RE task - even without explicit mention of Ghidra.
Verify whether an exact T-SQL script is already supported by SqlScriptDOM, then add or update the correct parser tests and baselines. Use when a user asks if syntax already works, or when adding regression coverage for a specific script.
Build and verify real-Postgres Go tests and thin transport smoke for tracking behavior.
Build and verify page-flow and E2E coverage for the tracking browser surface.
Build cross-layer regression coverage that ties browser-visible behavior to backend truth.
Use when working in this repository after receiving recurring coding feedback, adding or reviewing durable lint guardrails from AGENTS.md, updating rules/*.md, or finishing changes that should be checked by harness-lint.
Use when a Jumbo goal needs QA review after implementation. Runs the review protocol, verifies every objective, criterion, and related entity constraint, and approves the goal for codification or rejects it with feedback.
Harden shared test infrastructure, runtime readiness, schema setup, and parallel lane behavior.