AF eia-process-intel
Investigation workflow that turns Chinese EIA filings (环评报告/环评公示) into investment due-diligence intelligence: structured extraction (product scheme, per-step process flow, equipment list, material balance), adversarial field-credibility grading, physics-based cross-validation (low-risk fields as trust anchors to back-calculate capacity/yield/emissions), process-to-equipment mapping inference, and an append-only triple ledger with provenance. Use when: (1) analyzing a company EIA filing or 受理公示, (2) verifying capacity claims / 产能真实性核验, (3) inferring equipment selection from a 设备清单, (4) back-calculating yield from 物料平衡 / material balance, (5) auditing EIA numbers for gaming patterns (批小建大), (6) building a process/equipment fact ledger across deals. Triggers: 环评, EIA report, material balance, equipment list, capacity verification, yield back-calculation, regulatory gaming audit.
Investigation workflow that turns Chinese EIA filings (环评报告/环评公示) into investment due-diligence intelligence: structured extraction (product scheme, per-step…
As a process F 36/100 · Will not run — References files that are not bundled: references/mappings/<track>.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/mappings/<track>.md - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "summary" - note
frontmatter-keyunknown frontmatter key "agent_created"
Process rating: all ten parameters 36/100
- 0Tools and files. 1 referenced file(s) missing: references/mappings/<track>.md
- 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
- 30Running it twice. 6 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 70Execution cost. Instruction body is 4154 tokens
- 85Steps. 54 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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 888: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Structure: 20 headings
- +3Step-by-step instructions: 54 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.