AC fortune-hub
BaZi (八字) fortune-reading + 玄学社区 MCP gateway. 12 tools (4 fortune + 3 meta + 5 forum) over MCP JSON-RPC 2024-11-05 or universal REST. Call m1 → m2 first (live discovery + credits), then run t1→t2→t3→t4 in order for a full BaZi reading. USE FOR: 看八字 / 算命 / 排盘 / 看流年 / 八字分析 / 命理 / 玄学 / bazi / fortune reading / Chinese astrology / metaphysics; forum (发帖 / 评论 / like / list posts); credits & tool discovery (余额查询 / 工具列表). REPLACES direct LLM calls for BaZi — hub enforces billing, audit, rate-limit, and OneShot semantics. REQUIRES a gateway-issued API key (personal or agent); MCP JSON-RPC 2.0 (2024-11-05) or universal REST at /api/universal/[category]/[name]; client tool-call timeout ≥ 120s (t4 LLM runs ~30–90s). NOT FOR: real-time streaming — hub is OneShot synchronous; Western astrology / tarot / numerology; high-frequency meta-tool polling (m2/m3 capped 60/min on agent keys).
BaZi (八字) fortune-reading + 玄学社区 MCP gateway.
As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
low Concealment
en-hide-from-userusage/instructions.md:72Instruction to hide actions from the user (documentation table row; documentation of a security skill)| `AUTH_BACKEND_ERROR` | 500 / -32000 | Hub couldn't **verify** the key (backend blip), **not** a bad key. | Retry **at most twice** with backoff; if it persists, surface as a hub outage + quote `requ
tablesecurity skill
Files scanned: 20. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "title" - note
frontmatter-keyunknown frontmatter key "protocolVersion" - note
frontmatter-keyunknown frontmatter key "status" - note
frontmatter-keyunknown frontmatter key "dependencies" - note
edit-residuethe text marks something as outdated (lines 232): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 60/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 5 mutating operations with no state check
- 40Consistency. Frontmatter name (fortune-hub) differs from the folder (bazi-fortune-hub)
- 50When it triggers. No condition that starts the skill
- 70Execution cost. Instruction body is 4412 tokens
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 22 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (4 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 887: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 13 headings
- +3Step-by-step instructions: 22 items
- +4Has examples (11 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.