菜单
Use when recovering decisions or context from conversation history: session log navigation, transcript delegation.
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 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.
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.
Use when deciding where knowledge goes or reading/writing durable docs: AGENTS.md, .context/, KB, docs/, and work directories.
Anchor work in a work item: artifacts on disk, not in context.
Investigate and engage concurrently: don't block on evidence before surfacing your read.
Use when exploring or changing the codebase: read AGENTS.md first, use .context/CONTEXT.md for detail, keep intent docs succinct.
| name | session-mining |
| type | reference |
| description | Use when recovering decisions or context from conversation history: session log navigation, transcript delegation. |
| model-invocable | true |
Design decisions, rejected alternatives, and discovered constraints often live in conversation instead of code or docs. Compaction makes that context expensive to recover later, so mine it before the next implementation or documentation step starts.
Start from the top-level conversation. $MERIDIAN_CHAT_ID points to the primary session at the root of the chat tree, regardless of how deep in the spawn tree you are. That root context holds the primary's decisions and framing: usually the highest-leverage read.
Use a recent-context read first, then widen or anchor only if needed:
meridian session log "$MERIDIAN_CHAT_ID" --tail 20
Bare meridian session log "$MERIDIAN_CHAT_ID" reads the last 5 interaction
entries from the current segment with safe previews. Navigation is
segment-local by default: --from/--before/--around are ordinals inside
the selected segment, defaulting to the current one. Entry 0 of any segment
is its setup slot (prologue/handoff); reach it with --from 0 --limit 1. Use
--segment previous|current|N to switch segments, --full for the full
selected segment (entry 0 included), --no-truncate for complete content, and
--around N --context M for a deterministic window around a known entry.
Reach for --global only when you need one flat stream across all segments
(every segment's entry 0 included, with unique global ordinals starting at 0).
It conflicts with --segment and requires --from/--before/--around. Prefer
segment-local navigation: it stays stable across compactions.
Search instead of paging when you know what you're looking for:
meridian session search "decision text" "$MERIDIAN_CHAT_ID"
meridian session search "auth" --work <work-id> # scope to a work item
meridian session search "shape" --workspace # current project + workspace
Each hit prints a deterministic Open: command: run it to jump straight to
the entry instead of recomputing windows.
When the question spans long histories or multiple sessions, spawn @session-miner for transcript mining and synthesis. That keeps your context window focused on decisions instead of raw transcript paging.
meridian spawn -a session-miner \
--prompt-file session-mine.md
If you are the @session-miner, mine directly rather than spawning recursively.
When work spans interruptions, reopenings, or multi-day execution, list all related sessions before mining. Reading only the current session misses prior decisions.
meridian work sessions <work_id> --all
Skip mining if the spawning prompt already includes the needed rationale, or if current design/plan artifacts already capture the decisions you need. Skim artifacts first, and mine only the gaps.