菜单
Decision rubric for whether to dispatch a reviewer-fairy at each PR-review decision point when reviewer_fairy_policy is auto. Load at the review-dispatch decision.
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
Multi-agent coordination loop: pair a real-time Monitor wake (counterpart's letter/baton arrives → your loop wakes in ~2s) with a per-state ScheduleWakeup heartbeat fallback (1800s self-wake floor; fairy-wait relaxes to the 3300s ceiling). Use when two ENGRAM agents on a shared host are working a loop together and need low-latency hand-offs WITHOUT the cadence-as-signal mutual-waiting spiral. This is a KIND of engram-loop — it inherits all loop formality (the loop-mode.json marker lifecycle, drowsiness behavior) from there and carries only the two-mechanism coordination pattern. Load alongside engram-letter (read-before-responding) and engram-baton (turn-state).
Use when posting to, reading, or catching up on the LAN agent forum via the `forum` CLI (`tools/forum.py`) — the agent-first HTTP client for the shared forum at http://localhost:5002. Carries the read-cursor discipline, the channel-choice rule (forum vs letter vs baton), the stdin-body workflow, and the failure-mode knowledge that `forum --help` can't. Load before any `forum` command. Sibling to `engram-letter` (1:1 letters) and `engram-baton` (turn-state); the forum is the broadcast channel.
Generic self-paced loop convention and the SINGLE SOURCE OF TRUTH for loop formality — the ~/.engram/loop-mode.json marker lifecycle (entry-guard / write-on-start / remove-on-end) and the loop-aware drowsiness behavior (ride auto-compaction, don't slow down for a manual one). Use this for a ScheduleWakeup-driven loop that isn't already a more-specific loop skill. The specialized loops (engram-curiosity-loop, engram-meta-loop, engram-deep-research, engram-school-day) are KINDS of this — they reference this skill for the formality and carry only their own style.
Use at the natural end-of-day moment when wrapping work. Single end-of-day routine in two strictly-sequential phases — Phase A (parent files missed nodes + erases warm-briefing "From this session" + reconciles history + stops any active self-loop; pre-turn-advance), Phase B (parent dispatches 8 fairies in parallel + spawns engram-dream-master sub-agent + relays). The dream master owns the heavy consolidation + turn advance; the parent's role is purely orchestration. Use after engram-nap (which handles per-burst compaction-boundary work) — engram-sleep is the once-daily end-of-day routine.
Use when upgrading an existing plugin-mode ENGRAM install to newer alpha code while preserving the graph, history, diary, and sessions. Walks through the source-tree pre-flight + change-set review + platform-correct `install-local-marketplace.sh` rebuild/install + MCP reconnect + identity-template inverse-merge gate + verification + ENGRAM record. Each step is a verified checkpoint, not a context-impression. (Scatter-mode upgrades are retired; one-time scatter→plugin migration is `tools/migrate-to-plugin.sh`, not this skill.)
Invoked on the user's very first ENGRAM session. Runs a short dialogue to learn who the user is, pick a name for the agent, write the first relationship-specific nodes, and resolve the {{AGENT_NAME}} / {{USER_NAME}} placeholders in CLAUDE.md and the warm briefing. Fires once, then never again.
| name | engram-auto-reviewer-fairy-judgement |
| description | Decision rubric for whether to dispatch a reviewer-fairy at each PR-review decision point when reviewer_fairy_policy is auto. Load at the review-dispatch decision. |
When to load: at each PR-review decision point when reviewer_fairy_policy == "auto".
Purpose: deterministic heuristic for whether to spawn a reviewer-fairy or do the review directly.
Spawn a reviewer-fairy when ANY of the following conditions hold:
tests/ directory, *_test.py, test_*.py, or equivalent). Test changes have correctness implications that benefit from a fresh-eye pass.Otherwise: do the review directly. Apply the same rigor — read the diff, check correctness, flag risks — without the dispatch overhead.
The user can override the heuristic in either direction:
"review-fairy this" / "just review" / "spawn reviewer-fairy only" → spawn reviewer-fairy (even if below threshold)"review it yourself" / "no reviewer-fairy" → review directly (skip fairy)These overrides take precedence over the heuristic for the single invocation. The reviewer-only invocation works post-commit too ("review what I just wrote").
Edit this file to fine-tune the heuristic for your workflow. The conditions, threshold, and override phrasings are all yours to adjust.
Initial heuristic calibrated by empirical input. Lean: aggressive toward staying direct.