fix(skills): using-synology-ops 0.1.0→0.1.1 — extend skip-rule with non-NAS hosts

Behavioral fire-test of trigger phrases (10 parallel general-purpose subagents,
each phrase as isolated user message, META: skills_invoked= parsed) revealed
one false-positive: «restart-loop in books-pipeline» fired the skill despite
books-pipeline not being a NAS-hosted container — static-pass prediction
confirmed (implicit NAS-context discriminator, LLM keyed on `restart-loop`
without host check).

Tuning: extended skip-rule with non-NAS hosts examples
(`books-pipeline`, `vps-*` etc. — only the 6 listed above are NAS-hosted).
Description 941 chars / 1024 limit. PATCH bump (fix only, no new triggers).
Retest of NEG#3 → PASS (subagent quoted new skip-rule). Final 10/10.

Closes [using-synology-ops-test-trigger]; unblocks [using-synology-ops-review]
(ready, baseline tasks all 🟢, but body still <пусто> stub — separate debt).

dist-hermes/mcp/using-synology-ops/SKILL.md regenerated via build-hermes.py.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-12 19:57:42 +03:00
parent 0505e2e7ab
commit f14b579429
3 changed files with 14 additions and 25 deletions

View File

@@ -1,7 +1,7 @@
---
name: using-synology-ops
version: 0.1.0
description: Use when diagnosing docker containers on the Synology NAS — the `synology-ops` HTTP MCP server (https://opsmcp.kzntsv.site/mcp) exposes 4 read-only tools — `ops.docker.ps`, `ops.docker.logs`, `ops.docker.inspect`, `ops.docker.stats` — all routed through tecnativa `synology-docker-proxy-ro` with `POST=0` (write-ops return 403). Triggers on container names (`modulair-rag`, `modulair-pipeline`, `lightrag-modulair`, `tier1-converter`, `modulair-mcp`, `synology-ops-mcp`), on NAS-domain words ("на NAS", "Synology", "синолоджи", "Portainer-стек", "ops-mcp", "опс мсп", "opsmcp.kzntsv.site"), or on incident phrases ("падает", "restart-loop", "не стартует", "unhealthy", "посмотри логи") when NAS-context. Read-only by design — no per-session grant needed. Skip for non-incident container mentions, explicit "open Portainer GUI" requests, and write-operations (those go to Portainer manually).
version: 0.1.1
description: Use when diagnosing docker containers on the Synology NAS — the `synology-ops` HTTP MCP server (https://opsmcp.kzntsv.site/mcp) exposes 4 read-only tools — `ops.docker.ps`, `ops.docker.logs`, `ops.docker.inspect`, `ops.docker.stats` — all routed through tecnativa `synology-docker-proxy-ro` with `POST=0` (write-ops return 403). Triggers on container names (`modulair-rag`, `modulair-pipeline`, `lightrag-modulair`, `tier1-converter`, `modulair-mcp`, `synology-ops-mcp`), on NAS-domain words ("на NAS", "Synology", "синолоджи", "Portainer-стек", "ops-mcp", "опс мсп", "opsmcp.kzntsv.site"), or on incident phrases ("падает", "restart-loop", "не стартует", "unhealthy", "посмотри логи") when NAS-context. Read-only by design — no per-session grant needed. Skip for non-incident mentions, "open Portainer GUI" requests, write-ops, and incident phrases on non-NAS hosts (`books-pipeline`, `vps-*` etc. — only the 6 listed above are NAS-hosted).
---
# using-synology-ops