SKILLEMALL.ai
GitHub ↗ RU Sign in

CB composing-1c-queries

Compose correct and optimized 1C:Enterprise query language queries. Covers ВЫБРАТЬ/ИЗ/ГДЕ structure, table naming (catalogs, documents, registers, virtual tables), field selection, joins, grouping, totals, temporary tables, and parameter usage. Includes accounting register virtual tables (Остатки, Обороты, ОстаткиИОбороты, ОборотыДтКт, ДвиженияССубконто) with Счет, Субконто, and correspondence parameters. Use when the agent needs to compose a 1C query for execute_query, or when the user asks to query, filter, aggregate, or analyze data from a 1C database. Triggered by requests involving 1C data retrieval, report building, or query debugging.

Desko77/claude-code-skills-1c Agent Skills author: Desko77 MIT 5 files body ≈ 6 428 tokens Open the sourcegithub.com↗ analyzed 6 d ago

Compose correct and optimized 1C:Enterprise query language queries.

As a process B 66/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice

GeneratorData and analyticsSoftware developmentFinancetype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
86/100
safety, quality, tests
Safety 60%
90
Quality 40%
80
Run on models
none yet
Process rating
B
66/100
Nearly there
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Obfuscation medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

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.

For the author

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

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • 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-word references/functions-and-expressions.md:154
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (3 occurrences)
    | `ЕСТЬNULL(<expr>, <default>)` | Returns `<default>` if `<expr>` is NULL (like SQL COALESCE for two args) |
  • medium Obfuscation uni-mixed-script-word SKILL.md:365
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (1 occurrence)
    - Use `ЕСТЬNULL(field, default)` for fields that may be NULL (e.g., from LEFT JOIN)

Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 6428 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 66/100

  • 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. 5 mutating operations with no state check
  • 70Execution cost. Instruction body is 6428 tokens
  • 85Steps. 48 steps, 3 vague phrases
  • 100Tools and files. No external tools needed
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 2 branches, has a failure section
  • 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 14 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (33 tags): a typed call is more reliable
  • medium 3 test cases, all positive: not one "should refuse" or "should ask first"

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)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +3Description length 649: enough signal without eating the budget
  • +4Structure: 27 headings
  • +3Step-by-step instructions: 48 items
  • +4Has examples (27 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: 80.