菜单
This skill should be used when the user wants to clean up code without changing behavior. Dispatches cleanup agents, runs tests to verify behavior is preserved, then runs code review. Triggers include "simplify this", "clean up this code", "refactor without changing behavior", "reduce complexity".
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。
基于 SOC 职业分类
Use when checking whether field-guide reference pages still match current code and tests. Reads pages plus fg-evidence anchors, reports or fixes semantic drift, and can use sub-agents for parallel audit batches. Triggers include "resolve drift", "semantic drift", "check accuracy", "verify the reference against code", and "audit the wiki".
Use after ingesting or editing field-guide pages to attach living code/test anchors. Adds or refreshes fg-evidence metadata without trying to prove prose accuracy. Triggers include "update evidence", "wire evidence", "add evidence anchors", and "connect the wiki to code".
Use when extracting knowledge from .lore/ artifacts into the reference wiki. Converts work artifacts (retros, specs, plans, research, notes) into structured wiki pages grouped by knowledge type. Reads Markdown or HTML sources and writes Markdown by default. Triggers include "ingest this", "extract knowledge from", "add this to the wiki", "update the reference from", and "populate the field guide".
Use when setting up field-guide on a project for the first time, or to refresh the scheduled lint job after it expires. Triggers include "init field-guide", "set up field-guide", "refresh field-guide lint schedule", and "bootstrap the wiki".
This skill is used when the project wiki needs a health check. Triggers include 'lint the wiki', 'check wiki health', 'run field-guide lint', 'are there stale wiki pages', 'find orphaned pages', 'check for contradictions in the wiki'.
Use when asking questions about the project wiki, querying accumulated knowledge, searching project decisions or lessons. Triggers include "query the wiki", "what does the wiki say about", "search project knowledge", and natural language questions directed at the field-guide wiki.
| name | simplify |
| description | This skill should be used when the user wants to clean up code without changing behavior. Dispatches cleanup agents, runs tests to verify behavior is preserved, then runs code review. Triggers include "simplify this", "clean up this code", "refactor without changing behavior", "reduce complexity". |
Orchestrate code cleanup through agent delegation. Preserve behavior. Don't change what the code does.
Act as orchestrator. Dispatch work to sub-agents via the Task tool. Do not edit code directly.
Invoked as /simplify with optional arguments:
git status).lore/work/notes/*.md): resume a previous sessionCleanup. Dispatch code-simplifier:code-simplifier via Task tool with the file list. If .lore/lore-agents.md exists, check for additional simplification agents in the Code Quality section and dispatch them too.
Test. Dispatch a testing agent via Task tool. Include which files changed and how to run the test suite. Expect pass/fail and notable findings. If tests fail, diagnose and route back to the cleanup agent for correction. After two failed attempts on the same issue, escalate to the user.
Review. Dispatch a review agent via Task tool. Include which files to review and the requirement that behavior must be preserved. Route findings back to the cleanup agent for correction. After two failed attempts, escalate to the user.
Record what happened in a notes file at .lore/work/notes/simplify-<identifier>.md. Load ${CLAUDE_PLUGIN_ROOT}/shared/frontmatter-schema.md for the frontmatter fields. The body is freeform — capture which files were processed, what was simplified, any failures and how they were resolved.
Write the body in Markdown per the "Body Format" section of ${CLAUDE_PLUGIN_ROOT}/shared/frontmatter-schema.md. Reach for embedded inline HTML only when a visual carries meaning prose can't, such as a color-coded per-file outcome table.
Two conditions require human intervention. Everything else is autonomous.