BC pachca-admin
Администрирование пространства Пачки: сотрудники (пригласить, сменить роль, приостановить, удалить), теги и участники чатов, доступ к API и «Все токены», журнал аудита, экспорт, DLP, безопасный контур и шифрование, и что требует владельца, администратора или «Корпорации». Load before a tool call that changes an employee: delete only after a yes to your question. Когда: «пригласи сотрудника», «уволь / удали сотрудника», «сделай администратором», «добавь в тег», «добавь / удали участника чата», «кто в закрытом канале, где я не состою», «доступ к API ограничен», «отзови доступ сотрудника к API», «журнал аудита», «выгрузи переписку», «правило DLP», "invite an employee", "offboard a user", "change role", "add or remove chat members", "let employees create tokens", "export messages". Not for: a missing tool or a general 401/403 → pachca; who is in a tag or chat → pachca-search; writing messages → pachca-messaging; a bot's own token → pachca-bots; an app acting for employees → pachca-oauth; scripts → pachca-api.
Администрирование пространства Пачки: сотрудники (пригласить, сменить роль, приостановить, удалить), теги и участники чатов, доступ к API и «Все токены»…
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
The same skill appears in 1 more place: openapi
How to improve
- 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 · 0
✓ No critical or high findings
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5118 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 57/100
- 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
- 50When it triggers. No condition that starts the skill
- 70Execution cost. Instruction body is 5118 tokens
- 100Tools and files. No external tools needed
- 100Steps. 44 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- high The skill tells the model to perform an irreversible action with no human approval
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
- +3Description length 1020: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +5Description quotes 19 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 8 headings
- +3Step-by-step instructions: 44 items
- +4Reference files are cited in the instructions (3 of 3)
- +2Bilingual instructions (RU + EN)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.