AC pachca-search
Поиск, пересказ и напоминания в Пачке: какой поиск что охватывает, тред целиком, разбор проблемы или замечаний из треда, дайджест за период, поручения в напоминания, напоминание на время себе или коллеге, свои напоминания и «Важное», кто в теге или чате. Когда: «найди, где обсуждали», «кто писал про», «где меня упоминали», «найди чат», «найди сотрудника», «перескажи тред», «что поправить по треду», «в чём проблема по треду», «что было в канале за неделю», «дайджест», «какие решения приняли», «поставь задачи по итогам», «напомни мне завтра в 9:00», «мои напоминания», «что у меня в важном», «кто в теге», «кто в чате», "find where we discussed", "summarize this thread", "what feedback is in the thread", "channel digest", "remind me tomorrow at 9". Not for: posting, pinning, reacting to or editing a message, finding it first included, or one sent later at a set time → pachca-messaging; changing employees, tags or chat members → pachca-admin; a bot that answers in threads → pachca-ai-agent; scripts → pachca-api.
Поиск, пересказ и напоминания в Пачке: какой поиск что охватывает, тред целиком, разбор проблемы или замечаний из треда, дайджест за период, поручения в…
As a process C 57/100 · 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: 4. 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 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 14 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 70Execution cost. Instruction body is 4507 tokens
- 100Tools and files. No external tools needed
- 100Steps. 57 steps
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
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 1022: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +5Description quotes 23 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 12 headings
- +3Step-by-step instructions: 57 items
- +4Has examples (0 code blocks)
- +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: 96.