菜单
Synthesize observations into a readable network health report. Aggregates patterns and trends from observation cycles.
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
Single-pass network health observation. Checks API liveness, namespace freshness, drift, computes Network Health Score.
Deep investigation of a single construct. Identity-reality drift, maintenance pattern, composition analysis.
Single-pass network health observation. Checks API liveness, namespace freshness, drift, computes Network Health Score.
Autonomous observation loop. Time-boxed cycles with ratcheting health score, commits findings to grimoires.
Single-pass coherence sense of an ARBITRARY estate (a registry/state pair). Resolves the read-command from operator-local estate-config, shells the estate's own doctor read-only, emits exactly the STATUS|SIGNAL|MISMATCH tile. Sense-only — never mutates the estate.
Sense whether the config the OPERATOR owns is consistent across an estate of Loa repos. Loa is mounted per-repo, so every repo carries its own .loa.config.yaml and there is NO global tier — operator-owned config (model routing, which models review code, effort) gets duplicated across N repos and DRIFTS. This eye walks the estate, classifies each config key by TIER (operator vs project), and fires `drift` when an operator-tier key — one that SHOULD be identical everywhere — holds more than one distinct value. Optionally flags dead model pins against a model SoT. Emits the STATUS|SIGNAL|MISMATCH tile + a config-drift ledger. Sense-only — never mutates a config, never gates.
| name | report |
| description | Synthesize observations into a readable network health report. Aggregates patterns and trends from observation cycles. |
| allowed-tools | ["Bash","Read","Grep","Glob","Write","Edit"] |
| user-invocable | true |
Aggregate observations from /observe cycles into a readable network health report. This is the "commit" in the Karpathy Loop — what survived the ratchet, presented for humans.
/report # Generate report from all observations
/report --since 7d # Last 7 days only
/report --since 2026-03-01 # Since specific date
Read grimoires/gecko/observations.jsonl. Parse each line as JSON. Filter by --since if provided.
From the observation series:
Read any files in grimoires/gecko/diagnoses/ that fall within the reporting window. Cross-reference with observations.
Write to grimoires/gecko/reports/network-health-<date>.md:
# Network Health Report — <date>
## Summary
[2-3 sentences: overall network health, primary trend, key concern]
## Health Score
**Current**: 75/100 | **Trend**: +3 over 7 days | **Baseline**: 72
### Sub-Signals
| Signal | Score | Trend | Notes |
|--------|-------|-------|-------|
| API Liveness | 100 | stable | — |
| Version Freshness | 68 | -2 | webgl-particles stale |
| Category Coverage | 88 | stable | infrastructure empty |
| Identity Drift | 70 | +5 | dynamic-auth improved |
| Composition Density | 60 | stable | — |
| Verification Flow | 50 | stable | all UNVERIFIED |
## Constructs by Health
| Construct | Health | Days Since Update | Drift | Category |
|-----------|--------|-------------------|-------|----------|
| observer | HEALTHY | 3 | aligned | development |
| k-hole | HEALTHY | 5 | aligned | straylight |
| ... | ... | ... | ... | ... |
## Anomalies
[Any patterns that surfaced across multiple observation cycles]
## Diagnoses
[Summary of any deep diagnoses performed this period]
## Bazaar Observations
[Gecko-voice: what the numbers don't capture — foot traffic patterns, energy shifts, cultural signals]
Print report summary to stdout. If health is declining, highlight the top 3 contributing factors.
| Path | Description |
|---|---|
grimoires/gecko/reports/network-health-<date>.md | Full network health report |