菜单
Use when a plan exists and needs validation gates added to each step before implementation begins. Produces task files that implement can consume. Triggers include "break down this plan", "add validation to the plan steps", "plan-breakdown", and "gate this plan".
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 | plan-breakdown |
| description | Use when a plan exists and needs validation gates added to each step before implementation begins. Produces task files that implement can consume. Triggers include "break down this plan", "add validation to the plan steps", "plan-breakdown", and "gate this plan". |
A plan describes what to build. This skill adds what's missing: how do you know each step is done?
Invoke when a plan is complex enough that explicit validation at each step matters before handing off to implement. Simple plans don't need it — implement can work from the plan directly.
Invoked as /plan-breakdown <path> where <path> is a plan in .lore/work/plans/. Read the plan and any spec it references.
For each plan step, define:
Split a step only when it bundles genuinely different concerns with different validation needs. Resist over-decomposition — the value is the validation gates, not artificial granularity.
Save the task list. The saved files are the review vehicle.
Save task files to .lore/work/tasks/<plan-name>/NNN-<task-name>.md. Load ${CLAUDE_PLUGIN_ROOT}/shared/frontmatter-schema.md for the frontmatter fields. Set status: pending and include a sequence frontmatter field for ordering.
Each task file body: What, Validation, Why, Files sections.
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 status badge or a diagram a reviewing agent needs at a glance.
Stop here. The user invokes /implement when ready.
