SKILLEMALL.ai

AF shanghai-service-guide

Help users with Shanghai government service questions using public Shanghai "一网通办" service-guide data. Use when the user asks about 上海办事, 一网通办, 办事指南, 去哪办, 哪个部门, 线上办理, 线下窗口, 个人事项, 法人事项, or wants to identify the right Shanghai department, service item, online/offline path, or next step for a described need.

ClawHub Agent Skills author: 汤杭运 v1.0.0 MIT-0 11 files body ≈ 1 071 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process F 54/100 · Will not run — References files that are not bundled: references/service_items.jsonl

ProcedureInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
A
95/100
safety, quality, tests
Safety 60%
100
Quality 40%
88
Run on models
none yet
Process rating
F
54/100
Will not run
References files that are not bundled: references/service_items.jsonl
Tools and files w 18
0
Inputs and preconditions w 11
0
Consistency w 8
40
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • 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 · 0

✓ No critical or high findings

Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/service_items.jsonl

Process rating: all ten parameters 54/100

Will not run. References files that are not bundled: references/service_items.jsonl
  • 0Tools and files. 1 referenced file(s) missing: references/service_items.jsonl
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Consistency. Frontmatter name (shanghai-service-guide) differs from the folder (tongban)
  • 60Result and completion. Output format stated, no completion criterion
  • 65Failures and branches. 3 branches
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 34 steps
  • 100Execution cost. Instruction body is 1071 tokens
  • 100Running it twice. No mutating operations
  • 100Progress reporting. Reports progress

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
  • +4Description does not say when NOT to use the skill (false activations)
  • +1No license
  • +2Single-language instructions
  • +3Description length 306: enough signal without eating the budget
  • +4Structure: 6 headings
  • +3Step-by-step instructions: 34 items
  • +3Output format is stated explicitly
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)
  • +3All 4 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.

External checks

ClawHub: clean
This skill is a public Shanghai government-service lookup guide with disclosed local references and optional public-data refresh scripts, but users should verify important official-process advice.
LLM: benign (high) · 28 May 2026