AC pachca-oauth
Авторизация от имени сотрудника в Пачке (OAuth 2.0 с PKCE): когда боту нужен собственный токен сотрудника, вкладка OAuth, адреса возврата и набор прав, ссылка на авторизацию, обмен кода на токен, проверка владельца токена, хранение токена каждого сотрудника, повторная авторизация, отзыв доступа, список проверок перед запуском. Когда: «бот от имени сотрудника», «авторизация от имени сотрудника», «OAuth в Пачке», «client_id и client_secret», «redirect URI», «обменять код на токен», «PKCE», «экран согласия моего бота», «кнопка Предоставить доступ», «сотрудник отозвал доступ», «токен сотрудника вернул 401 или 403», "Pachca OAuth", "act on behalf of a user", "authorization code flow", "exchange code for token", "my bot's OAuth consent screen", "per-user token for my bot". Not for: a bot acting as itself, webhooks, showcase, a leaked bot token → pachca-bots; MCP sign-in, a 401/403 from an MCP tool or the CLI → pachca; your own token in a script → pachca-api; revoking access on the All tokens tab → pachca-admin.
Авторизация от имени сотрудника в Пачке (OAuth 2.0 с PKCE): когда боту нужен собственный токен сотрудника, вкладка OAuth, адреса возврата и набор прав, ссылка…
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
The same skill appears in 1 more place: openapi
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: 3. 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 52/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 26 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Execution cost. Instruction body is 4257 tokens
- 100Steps. 65 steps
- 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
- low 10 top-level sections: this looks like several domains in one skill
- 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
- +1No license
- +5Description quotes 16 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 11 headings
- +3Step-by-step instructions: 65 items
- +4Has examples (0 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +2Bilingual instructions (RU + EN)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.