BD ai-office-pro
Operational chief-of-staff for Russian CEOs: OKR, weekly review, decision log, briefing, delegation and strategic priorities. Dogfooded inside RAAI.
As a process D 45/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.
Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Obfuscation
uni-mixed-script-wordproof/openclaw-proof.md:39Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (1 occurrence)- ❌ Режим 2 (OKR) — был тест провален из-за Telegram parse-error, в v4 исправлено --- ## Вывод **OpenClaw видит коробку как `ready`. Первый boevой вызов (брифин…
-
medium Obfuscation
uni-mixed-script-wordSKILL.md:323Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (1 occurrence)Воронка: Лидов (каtering): 7 | КП отправлено: 3 | Оплат: 1 ━━━ 2. КРИТИЧЕСКИЕ РЕШЕНИЯ НА СЕГОДНЯ ━━━ РЕШЕНИЕ 1: Договор аренды точки на Тверской — истекает 30.0…
Files scanned: 31. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 14220 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "price" - note
frontmatter-keyunknown frontmatter key "price_currency"
Process rating: all ten parameters 45/100
- 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
- 40Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (ai-office-pro) differs from the folder (raai-ai-office-pro)
- 40Execution cost. Instruction body is 14220 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 30 steps
- 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)
- +4Structure: 1 headings, hard to scan
- +3Output format is not stated: the model decides each time
- -5Long text without headings
- +3Description length 148: enough signal without eating the budget
- +3Step-by-step instructions: 30 items
- +4Has examples (24 code blocks)
- +4Reference files are cited in the instructions (1 of 5)
- +1License stated
- +2Bilingual instructions (RU + EN)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.