AD iaiops-pharma
Pharmaceutical-manufacturing edition of iaiops — GMP drug/biologics plants as a distinct vertical from generic buildings and municipal water. BACnet/IP BMS+EMS (cleanroom pressure cascade, temperature/RH), Modbus (PW/WFI skids, stills, EDI, analysers), HART-IP (conductivity / TOC / level transmitters), OPC-UA (DCS, bioreactors, plant SCADA), plus the cross-protocol brain. Three signature checks: cleanroom_pressure_cascade (EU GMP Annex 1 cascade, door by door), cleanroom_particle_check and pharma_water_check (USP <645> stage-1 procedure). Use when the task mentions pharma, 制药, 药厂, GMP, cleanroom / 洁净室 / 洁净区, Annex 1, 压差梯度, pressure cascade, grade A/B/C/D, 尘埃粒子 / particle count, EMS / 环境监测, PW / WFI / 纯化水 / 注射用水, TOC, 电导率, conductivity, bioreactor / 生物反应器, 冻干机 / lyophilizer, 灌装线 / filling line, CSV, IQ/OQ, Annex 11, Part 11, or 数据完整性 / ALCOA. Read-first; this edition's tool surface is read-only.
Pharmaceutical-manufacturing edition of iaiops — GMP drug/biologics plants as a distinct vertical from generic buildings and municipal water.
As a process D 48/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 48/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 46 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2335 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)
- +3Description length 907: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 11 headings
- +3Step-by-step instructions: 46 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.