comol/ai_rules_1c/1c-platform-help

Claude Code and agent skill by comol/ai_rules_1c

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

External 1C knowledge — platform syntax reference, the platform-capability check before a custom specialized mechanism, БСП / SSL APIs, routed standards, file-format specs, ITS docs — via the docs, SSL and code-check MCP. Use only when such a fact affects the task.

Install

npx vskill@latest install comol/ai_rules_1c/1c-platform-help

SKILL.md

1c-platform-help — platform, БСП, standards, ITS

Conditional knowledge: call when the task depends on versioned platform behaviour, a reusable БСП API or standards compliance; never for prose cleanup. Model memory is not evidence of a platform feature's absence.

Tools and exact arguments

NeedCallArguments
Known type / methoddocinfoname ("ТаблицаЗначений", "Массив.Найти"), optional doc_type, scope, detail_level="compact"
Feature by descriptiondocsearchquery (Russian description of the capability), top_k, `scope="syntax" \"docs" \"all"`
Routed project standardstandardsname="<rule stem>" (anti-patterns, dev-standards-architecture); query= searches the collection; no args = catalogue — never docsearch for a standard
On-disk XML formatformatspecname= / query=
БСП reusable APIssl_searchquery (exact symbol or Russian description), limit=5, detail="compact"; fetch one hit with doc_id, detail="full"
ITS standardits_help → fetch_itsquery → id for every document relied on
Version-specific docssearch_1c_documentationquery, version="v8.3.25"; changes between versions — diff_1c_documentation_versions
Typical-configuration docsconfig_helpquery
Project help articleshelpsearch (code)query, limit, grep

There is no corpus argument on the docs server; scope never reaches standards / formatspec.

Calls

json
{"tool": "docinfo", "args": {"name": "ХранилищеЗначения", "detail_level": "compact"}}
{"tool": "docsearch", "args": {"query": "решение системы линейных уравнений", "scope": "all", "top_k": 5}}
{"tool": "standards", "args": {"name": "locks-and-transactions"}}
{"tool": "ssl_search", "args": {"query": "ОбщегоНазначения.ЗначениеРеквизитаОбъекта", "detail": "compact"}}
{"tool": "its_help", "args": {"query": "длительные операции"}}
{"tool": "fetch_its", "args": {"id": "<id from its_help>"}}

Platform-capability check (hard gate, mcp-policy.md → A.7)

Before a custom implementation in a specialized domain (cryptography, СЛАУ, data analysis, collaboration system / bots, integration bus / queues, full-text search, regex, archives, geo, background work): docsearch by capability, 1–2 reformulations → docinfo for every exact name found → ssl_search where a БСП solution is plausible. Found and usable → build on it, custom code for glue only. Partial fit → CONFUSION. Rejecting a found mechanism needs doc-confirmed incompatibility, stated in the answer.

Reading the answers

outcome: "not_found" on the docs server and not_found on SSL are finished answers, not retries; ambiguous_name on SSL returns candidates — refine by signature. Documents are paged (next_cursor), a first page is not the whole standard. Typed answers map to actions by code — content/rules/mcp-policy.md → C. Server answers → actions.

Details: content/skills/mcp-1c-tools/docs/1C-docs-mcp.md, content/skills/mcp-1c-tools/docs/1c-ssl-mcp.md, content/skills/mcp-1c-tools/docs/1c-code-check-mcp.md → Documentation & knowledge base, content/rules/help-corpus-retrieval.md.

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

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
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/comol/ai_rules_1c/1c-platform-help/badge)](https://verified-skill.com/skills/comol/ai_rules_1c/1c-platform-help)

Something wrong with this skill or its page? Tell us.