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 del texto original: inglés

qi-layer

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

Idioma del texto original: inglés

qi-maintenance

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

Idioma del texto original: inglés

handoff

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

Idioma del texto original: inglés

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 del texto original: inglés

work-artifacts

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

Idioma del texto original: inglés

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 del texto original: inglés

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 del texto original: inglés

explore-and-engage

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

Idioma del texto original: inglés

session-mining

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

Idioma del texto original: inglés

shared-dao

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

Idioma del texto original: inglés

shared-workspace

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

Idioma del texto original: inglés

zoom-out

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

Idioma del texto original: inglés

md-validation

Use when validating markdown links or Mermaid diagrams.

Idioma del texto original: inglés

meridian-privilege-escalation

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

Idioma del texto original: inglés

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 del texto original: inglés

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 del texto original: inglés

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 del texto original: inglés

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 del texto original: inglés

intent-modeling

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

Idioma del texto original: inglés

reflect

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

Idioma del texto original: inglés