comol/ai_rules_1c/1c-validate
Claude Code and agent skill by comol/ai_rules_1c
- community
Checking that the SKILL.md file is still in the repository.
Validate changed 1C artifacts — BSL by path (BSL Language Server), logic and performance (1С:Напарник check), style and ITS review, metadata XML against XSD — within the verification-policy budget. Use after every BSL or metadata edit.
Install
npx vskill@latest install comol/ai_rules_1c/1c-validateSKILL.md
1c-validate — the validator chain
Order for touched BSL: syntaxcheck_file → check_1c_code → review_1c_code, at the depth of VERIFICATION_DEPTH and within the budget of content/rules/verification-policy.md → Validator budget (one clean pass on the latest state; after a blocking fix one confirmation at standard, up to two at full; never a run on unchanged content). Pure metadata XML without BSL: verify_xml once. Which gates a change needs — content/rules/verification-gates.md.
Tools and exact arguments
| Gate | Call | Arguments | |
|---|---|---|---|
| 1 Syntax — saved file (default) | syntaxcheck_file | file_path relative to the mounted sources root, optional lines="5, 10-20" — save first; a failed path is retried once, then fall back to text | |
| 1 Syntax — text (fallback) | syntaxcheck | code — only when the file tool is not exposed or the fragment has no file yet; confirm by path once written | |
| 2 Logic & performance | check_1c_code | exactly one of code or files (list of saved paths under the declared workspace roots) | |
| 3 Style & ITS | review_1c_code | same shape as check_1c_code | |
| 5 Metadata XML | verify_xml | xml_content, object_type (Справочник, Документ, Форма, Роль, СКД, Макет) |
syntaxcheck and syntaxcheck_file are one validator for budgeting. Never feed syntax-broken code to the AI validators.
Calls
Reading the answers
- Blocking: any
errorfrom syntax;critical/errorfrom check;errorfrom review; a logic, data-integrity, security, transaction or performance defect named by the validator. Style noise never starts another AI pass. provenance.indexon a syntax answer says what a clean report proves:absent/building/failed= syntax and local rules only;ready= cross-module resolution included. Read it, never wait for it.- A check of a large module may run for minutes; the server retries transport failures itself — do not resend.
- Rewrites from
rewrite_1c_code/modify_1c_codeare drafts and re-enter this chain. - A missing validator is graceful degradation with a
Risk:line, never a silent skip. Typed answers map to actions by code —content/rules/mcp-policy.md → C. Server answers → actions.
Details: content/skills/mcp-1c-tools/docs/1c-syntax-checker-mcp.md, content/skills/mcp-1c-tools/docs/1c-code-check-mcp.md, content/skills/mcp-1c-tools/docs/1c-code-metadata-mcp.md → XSD schemas & validation.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingcontent/skills/1c-validate/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/comol/ai_rules_1c/1c-validate)