haowjy/meridian-base

knowledge-layers

Use when deciding where knowledge goes or reading/writing durable docs: AGENTS.md, .context/, KB, docs/, and work directories.

原文语言：英语

qi-layer

Use when writing or maintaining AGENTS.md, .context/CONTEXT.md, or CLAUDE.md mirrors: keep intent docs minimal and load-bearing.

原文语言：英语

qi-maintenance

Always load on agents that make durable source changes: keep colocated agent-facing knowledge synchronized with the source.

原文语言：英语

handoff

Produce a transition brief and launch command for the user's next interactive primary.

原文语言：英语

structured-artifact

Load when building a static HTML artifact: single page or multi-page site to make structured information explorable through layout and navigation.

原文语言：英语

work-artifacts

Anchor work in a work item: artifacts on disk, not in context.

原文语言：英语

grill-with-docs

Use when grilling should be grounded primarily in project artifacts. Loads `/grill`, checks project vocabulary and prior decisions first, and spawns bounded explorers when the answer should come from docs.

原文语言：英语

information-hierarchy

Load for large human-facing outputs: reports, docs, multi-section explanations, artifacts. Choose the right form for each beat (prose, diagram, table, mockup) and put the answer first, depth behind it. If the medium allows, use progressive disclosure.

原文语言：英语

explore-and-engage

Investigate and engage concurrently: don't block on evidence before surfacing your read.

原文语言：英语

session-mining

Use when recovering decisions or context from conversation history: session log navigation, transcript delegation.

原文语言：英语

shared-dao

Use when establishing shared vocabulary: resolve terminology early, one name per concept, vocab files as record.

原文语言：英语

shared-workspace

Use when a workspace has changes from other agents: safe orientation, preserving unfamiliar files.

原文语言：英语

zoom-out

Use when orienting in an unfamiliar area: fans out parallel explorers across code, knowledge, and history, then synthesizes one orientation map.

原文语言：英语

md-validation

Use when validating markdown links or Mermaid diagrams.

原文语言：英语

meridian-privilege-escalation

Use when a spawn fails due to sandbox or permission restrictions.

原文语言：英语

llm-writing

Load before writing or revising human-facing text. Choose words deliberately, ground the piece in the reader's context, and remove default LLM phrasing before the final draft.

原文语言：英语

goal-writing

Load when turning intent into an executable goal for an agent, spawn, work item, experiment, or handoff. Use to define outcome, evidence, constraints, anti-goals, stop conditions, and reporting shape before work begins.

原文语言：英语

grill-with-evidence

Use when grilling should be grounded in evidence. Loads `/grill`, then checks the plan, terms, and assumptions against project artifacts first and primary sources when needed.

原文语言：英语

grill

Use in conversation to stress-test a plan or direction. Interviews the human branch by branch, sharpens terminology, challenges assumptions, and asks the next high-leverage question with a recommended answer.

原文语言：英语

intent-modeling

Use before acting on human instructions: separate what they said from what they meant.

原文语言：英语

reflect

User-invoked pause before reporting to check intent vs literal completion, surface adjacent wins, and route knowledge capture.

原文语言：英语