← ClaudeAtlas

querylisted

Query Lode's decision replay index for why a project chose a path, what alternatives were rejected, what should be revisited, what impact a decision had, or any natural-language question about project history. Use this skill for "/lode:query", "why did we choose this?", "为什么当时这么选", "有没有被拒绝过的方案", "revisit this decision", "auth 迁移做到哪了", "我们讨论过 rate limiting 吗", or when a coding agent needs cited decision evidence before changing architecture, contracts, prompts, schemas, or product direction.
KKenny0/Lode · ★ 1 · AI & Automation · score 62
Install: claude install-skill KKenny0/Lode
# Decision Replay Query This skill answers targeted project-history questions from Lode's local decision memory. It is a thin wrapper around the deterministic decision replay helper: the script narrows evidence, and the host agent writes the final answer. Use `query` when the current task touches an existing decision, architecture boundary, rejected option, long-running risk, or product tradeoff. Use `recall` for session-start orientation; use `query` for a specific follow-up question. ## Scope - Intra-project by default. - Raw entries remain the source of truth. - `{vault}/raw/decisions/{project-slug}.json` is a derived retrieval index. - The helper may rebuild an in-memory index from raw entries when no saved index exists, but this skill does not write new memory. - Do not use git history, external docs, or model assumptions to fill missing decision evidence. ## Workflow 1. Identify the user's decision question. 2. Pick the mode: | Mode | Use when the user asks | |------|------------------------| | `why` | why a path was chosen, why something works this way | | `alternatives` | what was rejected, abandoned, deferred, or not chosen | | `revisit` | what open questions or deferred choices should be reconsidered | | `impact` | what downstream effects a decision had | | `free` | anything that doesn't fit the other 4 modes — status checks, "did we discuss X?", "what's the history of Y?" | ### Free-Form Mode When the user asks a natural-language question that doesn't