菜单
Answer targeted questions over conversation history with evidence references.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Use when bringing the harness method to a NEW or non-sentropic repo — maps the repo's conventions into a harness profile so the same scope/branch/verify kernel applies anywhere.
Use before any creative/design work (a feature, a package, an evolution) — explores intent and design via the spec-ladder with multi-peer adversarial review BEFORE implementation.
Use on any bug, test failure, or unexpected behaviour BEFORE proposing a fix — runs the generic evidence-first root-cause loop.
Use when you have a spec/decisions and need an executable plan — writes a lot-based BRANCH.md from the template and completes with track for realization state.
Use when completing a feature, a design step, or before merging — runs a ≥2-peer consensus review and reconciles the findings, instead of a single rubber-stamp pass.
Use when adding or evolving tests for a feature/bugfix — applies the sentropic test-pyramid, scoped-test loop, environment isolation, and AI-flaky policy.
基于 SOC 职业分类
| name | history_analyze |
| description | Answer targeted questions over conversation history with evidence references. |
| version | 0.1.0 |
| category | analysis |
| tools | [{"name":"history_analyze","description":"Answer targeted questions over conversation history with evidence references.","inputSchema":{"type":"object","properties":{"question":{"type":"string","description":"Targeted question to answer from chat history."},"from_message_id":{"type":"string","description":"Optional lower bound message id (inclusive)."},"to_message_id":{"type":"string","description":"Optional upper bound message id (inclusive)."},"max_turns":{"type":"integer","minimum":1,"maximum":500,"description":"Optional bound on scanned turns."},"target_tool_call_id":{"type":"string","description":"Optional tool call id to focus on one specific oversized tool result path."},"target_tool_result_message_id":{"type":"string","description":"Optional tool-result message id to focus the analysis scope."},"include_tool_results":{"type":"boolean","description":"Include tool-result messages in analysis scope (default true)."},"include_system_messages":{"type":"boolean","description":"Include system messages in analysis scope (default false)."},"max_words":{"type":"integer","minimum":200,"maximum":6000,"description":"Optional answer bound in words."}},"required":["question"]}}] |
The history_analyze skill answers focused questions over prior conversation
turns with evidence references. Use it when the user asks what was decided,
what remains open, or what a prior tool result or message actually said.
Handlers are intentionally not bound in this package commit. Runtime execution
still routes through the legacy API tool service until BR-19 Lot 5 rebinds
chat-service to SkillsToolRegistry.
