BC osint-investigation
Follow the money via public records and sanctions data.
Follow the money via public records and sanctions data.
As a process C 60/100 · Has gaps — weak spots: result and completion, 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: 29. 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 60/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 60Consistency. The Hermes dialect needs category and tags
- 100Steps. 25 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 2791 tokens
- 100Running it twice. No mutating operations
- 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
- +3Description length 55: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -32 of 16 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 12 headings
- +3Step-by-step instructions: 25 items
- +4Has examples (7 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.
In the sandbox The scripts kept to themselves
The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.
Запущено 12 скриптов, ещё 4 не поместились в лимит; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.
Из них 10 не дошли до работы, и об их поведении мы ничего не узнали.
scripts/_http.py | ничего за пределами своей папки |
scripts/_normalize.py | ничего за пределами своей папки |
scripts/build_findings.py | не запустился: build_findings.py: error: the following arguments are required: --cross-links |
scripts/entity_resolution.py | не запустился: entity_resolution.py: error: the following arguments are required: --left, --left-name-col, --right, --right-name-col, --out |
scripts/fetch_courtlistener.py | не запустился: fetch_courtlistener.py: error: the following arguments are required: --query, --out |
scripts/fetch_gdelt.py | не запустился: fetch_gdelt.py: error: the following arguments are required: --query, --out |
scripts/fetch_icij_offshore.py | не запустился: fetch_icij_offshore.py: error: the following arguments are required: --out |
scripts/fetch_nyc_acris.py | не запустился: fetch_nyc_acris.py: error: the following arguments are required: --out |
scripts/fetch_ofac_sdn.py | не запустился: fetch_ofac_sdn.py: error: the following arguments are required: --out |
scripts/fetch_opencorporates.py | не запустился: fetch_opencorporates.py: error: the following arguments are required: --query, --out |
scripts/fetch_sec_edgar.py | не запустился: fetch_sec_edgar.py: error: the following arguments are required: --out |
scripts/fetch_senate_ld.py | не запустился: fetch_senate_ld.py: error: the following arguments are required: --out |
18 Oct 2026