Agent skill

1c QA Testing

by comol in comol/ai_rules_1c

UI checks in the 1C thin client through QA MCP (1c-qa, qa / ui): session, observe → act → assert, platform behaviour, unknown outcomes, journal and verdicts.

No licenceAuto-check passedTesting & QA

Install 1c QA Testing

skills CLI
$ npx skills add comol/ai_rules_1c --skill 1c-qa-testing -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install comol/ai_rules_1c 1c-qa-testing --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/comol/ai_rules_1c.git skills-src && mkdir -p .claude/skills && cp -r skills-src/content/skills/1c-qa-testing .claude/skills/1c-qa-testing && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
1c-qa-testing
GitHub stars
480
Token cost
~2.4k tokens
SKILL.md length
1,284 words
Files
5 (incl. scripts)
Skills in repo
26
Repo updated
First seen
Licence
None found

At a glance

UI checks in the 1C thin client through QA MCP (1c-qa, qa / ui): session, observe → act → assert, platform behaviour, unknown outcomes, journal and verdicts.

  • Works in 4 steps: qa_status — the executor decides who… → Start or find the test client… → qa_status again: executor, link, target.… → …
  • Tasks that involve QA and bug reports
  • SKILL.md covers When this route applies, Other MCP servers in a check, Session and Observe → act → read the…, plus 6 more sections
  • Runs PowerShell scripts from its folder

What it does

1c QA Testing is an agent skill from comol/ai_rules_1c. UI checks in the 1C thin client through QA MCP (1c-qa, qa / ui): session, observe → act → assert, platform behaviour, unknown outcomes, journal and verdicts. Main UI route when connected and TOOLQA allows it; the web client is the fallback.

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts (for example `docs/context-sources.md`, `docs/interaction-recipes.md` and `docs/platform-behaviour.md`).

It sits in Testing & QA, covering QA and bug reports and MCP servers. It works with Model Context Protocol. The repository describes itself as: Rules\skills\subagens for vibecoding in 1C(bsl).

When your agent uses it

  • Tasks that involve QA and bug reports
  • Tasks that involve MCP servers

Example prompts

  • “/1c-qa-testing”

Requirements

  • PowerShell

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. qa_status — the executor decides who starts 1C
  2. Start or find the test client (qa-testclient.md), then qa_start(connection=""); port= overrides the port of MCP_QA_TESTCLIENT. No Windows…
  3. qa_status again: executor, link, target. A test client is already connected to another manager answer means another agent owns the client…
  4. At the end: qa_stop. In native it only disconnects; the client is closed by the tool that started it (qa-testclient.md). A new MCP session…

What it can do on your machine

Read from SKILL.md and the folder at commit 709ecac. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (PowerShell), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

1c QA Testing loads about 2.4k tokens when it runs. Until then it costs about 66 tokens; SKILL.md has 1,284 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~66
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,284 words (~2,377 tokens).

“QA MCP (connection 1c-qa) is the 1C test manager: it connects to a 1C test client (/TestClient) and drives its forms through the platform testing model — windows, fields, tables, commands, messages. It reads structured state, not pixels, so it…”

— opening of SKILL.md by comol
name
1c-qa-testing
argument-hint
<feature or scenario to check>

Read the full SKILL.md on GitHub

Files

SKILL.md and 4 other files (scripts) in content/skills/1c-qa-testing of comol/ai_rules_1c.

  • SKILL.md
  • docs/context-sources.md
  • docs/interaction-recipes.md
  • docs/platform-behaviour.md
  • scripts/qa-testclient.ps1

Open the folder on GitHubat commit 709ecac

Compare with similar skills

1c QA Testing next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

1c QA Testing compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
1c QA Testing this skillcomol/ai_rules_1c480—~2.4kAutomated safety check: PassNone
Testing Scope MCPdaydreamlive/scope452—~1.2kAutomated safety check: PassCustom licence
Agentacct Workflowmikehasa/agentacct765—~1.6kAutomated safety check: PassMIT
Glance TestDebugBase/glance156—~827Automated safety check: PassMIT
Windows QA EngineerCodeAlive-AI/ai-driven-development155—~1.4kAutomated safety check: PassMIT
MCP Smoke TestSepineTam/mcp-for-stata263—~1.4kAutomated safety check: PassAGPL-3.0

Similar skills

  • Testing Scope MCP

    daydreamlive/scope

    Test Daydream Scope through its stdio MCP server, including disconnected startup, connecttoscope, direct Python stdio client fallback, and lightweight smoke tests.

    452 GitHub stars~1.2k tokensUpdated 2 mo ago
    Testing & QAAuto-check passed
  • Agentacct Workflow

    mikehasa/agentacct

    A skill your agent uses when working in a repo with agentacct MCP configured, or when asked to track coding-agent work, smoke-test agentacct integrations, or report objective AI-agent task evidence.

    765 GitHub stars~1.6k tokensUpdated 4 days ago
    Testing & QAAuto-check passed
  • Glance Test

    DebugBase/glance

    Run E2E browser tests on any web application using Glance MCP.

    156 GitHub stars~827 tokensUpdated 5 mo ago
    Testing & QAAuto-check passed
  • Windows QA Engineer

    CodeAlive-AI/ai-driven-development

    A skill your agent uses when testing Windows 11 desktop apps (WinForms/WPF/UWP) via UFO UIA/Win32 automation MCP.

    155 GitHub stars~1.4k tokensUpdated yesterday
    Testing & QAAuto-check passed
  • MCP Smoke Test

    SepineTam/mcp-for-stata

    Run a local smoke test for the Stata-MCP server. An agent skill from SepineTam/mcp-for-stata.

    263 GitHub stars~1.4k tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Live Linear Smoke

    tacticlaunch/mcp-linear

    Run safe live smoke tests for mcp-linear against a real Linear workspace.

    147 GitHub stars~251 tokensUpdated 3 days ago
    Testing & QAAuto-check passed

More from comol/ai_rules_1c

All 26 skills in this repo
  • Img Grid Analysis

    comol/ai_rules_1c

    Overlay a numbered grid on an image to determine column proportions for layout generation.

    480 GitHub stars~619 tokensUpdated yesterday
    Auto-check passed
  • Md To DOCX

    comol/ai_rules_1c

    Convert a Markdown file to DOCX (Word). An agent skill from comol/ai_rules_1c.

    480 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Transcribe

    comol/ai_rules_1c

    Transcribe video and audio files via Gemini API. An agent skill from comol/ai_rules_1c.

    480 GitHub stars~960 tokensUpdated yesterday
    Auto-check: notes
  • 1c Code Search

    comol/ai_rules_1c

    Find BSL code in a 1C project — routines by name, code by behaviour or exact literal, module layout, members of a context — through the graph and code-metadata MCP servers before any Grep.

    480 GitHub stars~1k tokensUpdated yesterday
    Auto-check passed
  • 1c Repository Manage

    comol/ai_rules_1c

    1C configuration repository (хранилище) — status, history, diff, lock, update, commit, unlock, dump; lock before edit, commit after verify.

    480 GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed
  • 1c Templates Memory

    comol/ai_rules_1c

    Search reusable 1C code templates with the task text and adapt a fitting result.

    480 GitHub stars~575 tokensUpdated yesterday
    Auto-check passed

Questions about 1c QA Testing

What does 1c QA Testing do?

UI checks in the 1C thin client through QA MCP (1c-qa, qa / ui): session, observe → act → assert, platform behaviour, unknown outcomes, journal and verdicts. 1c QA Testing is an agent skill from comol/ai_rules_1c. UI checks in the 1C thin client through QA MCP (1c-qa, qa / ui): session, observe → act → assert, platform behaviour, unknown outcomes, journal and verdicts.

When should I use 1c QA Testing?

1c QA Testing fits situations like: tasks that involve QA and bug reports; tasks that involve MCP servers.

How do I install 1c QA Testing in Claude Code?

Run `npx skills add comol/ai_rules_1c --skill 1c-qa-testing -a claude-code`. Or copy the skill folder (content/skills/1c-qa-testing in comol/ai_rules_1c) into .claude/skills/1c-qa-testing in your project. Claude Code loads it when a task matches its description.

How do I install 1c QA Testing in Codex?

Run `npx skills add comol/ai_rules_1c --skill 1c-qa-testing -a codex`. Or copy the skill folder (content/skills/1c-qa-testing in comol/ai_rules_1c) into .agents/skills/1c-qa-testing in your project. Codex loads it when a task matches its description.

Can I use 1c QA Testing in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add comol/ai_rules_1c --skill 1c-qa-testing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/1c-qa-testing, .gemini/skills/1c-qa-testing, .github/skills/1c-qa-testing and .opencode/skills/1c-qa-testing in your project.

What does 1c QA Testing need to run?

Going by SKILL.md and its folder, 1c QA Testing needs PowerShell for the scripts in its folder. Our summary lists: PowerShell.

Does 1c QA Testing access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is 1c QA Testing safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does 1c QA Testing use?

No licence was found for 1c QA Testing or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does 1c QA Testing use?

About 2.4k tokens (SKILL.md is roughly 9.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to 1c QA Testing?

Skills that share tags, products or a category with 1c QA Testing: Testing Scope MCP (daydreamlive/scope, 452 stars), Agentacct Workflow (mikehasa/agentacct, 765 stars), Glance Test (DebugBase/glance, 156 stars) and Windows QA Engineer (CodeAlive-AI/ai-driven-development, 155 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains 1c QA Testing?

comol (a GitHub user) maintains it in comol/ai_rules_1c, which has 480 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on October 6, 2026.

Source: comol/ai_rules_1c on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.