haowjy/meridian-base

knowledge-layers

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

Idioma do texto original: inglês

qi-layer

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

Idioma do texto original: inglês

qi-maintenance

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

Idioma do texto original: inglês

handoff

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

Idioma do texto original: inglês

structured-artifact

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

Idioma do texto original: inglês

work-artifacts

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

Idioma do texto original: inglês

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.

Idioma do texto original: inglês

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.

Idioma do texto original: inglês

explore-and-engage

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

Idioma do texto original: inglês

session-mining

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

Idioma do texto original: inglês

shared-dao

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

Idioma do texto original: inglês

shared-workspace

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

Idioma do texto original: inglês

zoom-out

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

Idioma do texto original: inglês

md-validation

Use when validating markdown links or Mermaid diagrams.

Idioma do texto original: inglês

meridian-privilege-escalation

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

Idioma do texto original: inglês

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.

Idioma do texto original: inglês

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.

Idioma do texto original: inglês

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.

Idioma do texto original: inglês

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.

Idioma do texto original: inglês

intent-modeling

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

Idioma do texto original: inglês

reflect

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

Idioma do texto original: inglês