Multica Test Orchestration logo

Multica Test Orchestration

Community
it235
multica-test-orchestration

Tester T1/T2/T3 orchestration and gatekeeping—sub-skill routing, assembling materials from Issue comments, and BLOCKED interruption list. Integrates acceptance-verifier-squad; the preferred mount for @Tester.

Overview

Publisherit235
Repositorymultica-best-practices
Skill namemultica-test-orchestration
Stars
199
Forks
29
Bundled files
5
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by it235 on GitHub. Read the source before you install it.

Installation

Install the Multica Test Orchestration AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/it235/multica-best-practices/tree/main/templates/en_US/skills/tester/multica-test-orchestration
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/it235/multica-best-practices.git /tmp/multica-best-practices
mkdir -p .claude/skills
cp -r /tmp/multica-best-practices/templates/en_US/skills/tester/multica-test-orchestration .claude/skills/multica-test-orchestration
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Multica Test Orchestration in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Multica Test Orchestration on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Multica Test Orchestration is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Test Orchestration (Acceptance Verifier · Orchestration)

You are accountable for whether the requirement is actually implemented. Testing shifts left and is split into T1 / T2 / T3. T3 must wait for DevOps G2.5 PASS before running automation.

This skill belongs to no single T1/T2/T3 phase—it is the cross-phase orchestration entry: routing, comment assembly, BLOCKED, and T3 merge adjudication. Integrated from acceptance-verifier-squad; method details live in the -t1/-t2/-t3 sub-skills.

Platform Collaboration

Platform skillUsed for
multica-platform-jiraRead all Issue comments before T2/T3 (get-issue / equivalent)
team-knowledge-base (optional)T1 Step 0 (via multica-test-t1-design)
multica-platform-apifoxT1 parallel scenarios + T3 batch run (via t1-design / t3-api-automation)

T1 collection (JIRA / Confluence / Figma) goes through multica-test-t1-design → platform-jira / confluence / figma. Credentials and CLIs are only looked up in the platform skill.

Sub-skill Routing (must Read before acting)

PhaseSkillOutput
Orchestration / gateThis filePhase card, BLOCKED reason
T1 test designmultica-test-t1-designFull Confluence cases + Apifox scenarios + e2e plan
T1 QAmultica-review-testReview Confluence; after 👤 passphrase, XMind/JIRA
Parallel API scenariosmultica-platform-apifoxSupplement scenarios by API contract (AI branch)
T2multica-test-t2-coverageConfluence delta + Apifox + MULTICA §2 e2e into repo
T3 APImultica-test-t3-api-automation → multica-platform-apifoxApifox logs + join overall report
T3 UImultica-test-t3-ui-automationpytest+Playwright 1:1 execution
T3 adjudicationOrchestration merges both sides' evidenceSingle PASS/FAIL/BLOCKED

Copyable agent instructions: references/agent-instructions.md.
Skill cross-reference: references/skill-inventory.md; T3 merge report: references/t3-merge-report.md; automation assets into repo: references/automation-assets-lifecycle.md.

Task Card (stop if missing)

text
stage: T1 | T2 | T3 | parallel-api
issue:                  # Multica and/or Jira Key
ac_source:              # Where the numbered AC- original text lives (Issue/PRD)

T2 / T3 materials: assemble only from this Issue's description + all comments (including attachment names). If you cannot assemble, stop, output the missing list, and wait for a human to complete the comments before continuing. No fabrication; no local mock / URL not present in comments as a substitute.

Assemble from Comments (mandatory)

Before entering T2 / T3 / parallel-api, you must jira_cli.py get-issue --comments (or equivalently read all comments) and fill the task card by recognizing the following:

FieldRecognized if any of these appears in comments
g2_passLeader explicitly writes G2 PASS / G2 convergence gate PASS
g2_sha / changeMerged SHA, frontend/backend commits, changed-files table, or MR/PR link
api_contractApifox/OAS link, or explicit N/A + which interface/link is reused
g25_passLeader/DevOps explicitly G2.5 PASS; only "G2.5 N/A" → automation lacks deploy evidence (unless there is also a deploy_url and Leader authorizes in writing)
page_urlURL of the page under test; if omitted may equal deploy_url (must be stated in comments)
ui_authOnly when running UI: auth_mode=none or "account via Secret variable name". Never use plaintext passwords from comments
apifox_project_id / environment_id / scenario_idsNumeric ID or scenario link; if contract is N/A and this iteration has no API automation → mark all three N/A (not missing)

On conflict: the later Leader comment wins. Branch name only, with no SHA/files table/MR link → change item still counts as missing.

Stop if missing (output to human)

markdown
## Interrupted: awaiting human to add to Issue comments

Phase: T2 | T3
Issue: {id}

### Already assembled from comments
- {field}: {excerpt source comment summary}

### Missing list (please reply in comments using the right-column format)
| Missing | Please provide |
|--------|--------|
| g2_sha / changed files or MR link | e.g. SHA + file list, or GitLab MR URL |
| api_contract | Apifox/OAS link, or: N/A (reuse xxx) |
| g25_pass | G2.5 PASS or explicitly not passed |
| deploy_url | Reachable environment URL |
| apifox_project_id | Number, or N/A |
| apifox_environment_id | Number or environment name, or N/A |
| apifox_scenario_ids | Scenario ID list, or N/A |

Reply "continue T2" or "continue T3" once completed.

Gates (non-negotiable)

  • Do not pass merely because it compiles, unit tests pass, or the implementer says it's fine.
  • Do not convert BLOCKED into PASS.
  • No T3 automation when G2.5 is not PASS; no local mock as a substitute for the deployed environment.
  • G2.5 N/A: no deploy_url → T3 automation BLOCKED; with deploy_url + Leader written authorization → may run, report notes the downgrade.
  • Manual appendix (only with Leader written authorization): may list manual results, titled "non-automated, does not replace G2.5"; must not therefore pass the whole automation (see t3-merge-report.md).
  • T1 import: requires multica-review-test non-Block, and user/Leader explicit import passphrase.
  • T2 conclusion only allows "evaluation complete / evaluation BLOCKED", never worded as acceptance PASS/FAIL.
  • Interface cases are not imported into JIRA.

T1 Flow

  1. Lock Issue + AC- original text.
  2. multica-test-t1-design — full Confluence t1-cases (no XMind) + parallel Apifox (once contract ready).
  3. multica-review-test — review Confluence.
  4. After 👤 passphrase: XMind → import_to_tracker.py (phase C).
  5. Plan e2e / API manifest path (MULTICA.md §2; lands in T2).

Leader judges the T1 gate (Confluence link + Apifox summary).

T2 (only after G2 PASS)

Assemble comment materials → multica-test-t2-coverage: Confluence delta + Apifox scenarios + Playwright writes MULTICA §2 e2e path + manifest update → commit to deploy branch.

T3 (only after G2.5 PASS + URL)

First assemble g25_pass + deploy_url.

ConditionAction
Confirmed cases + page_url + e2e script in deploy branch (path in MULTICA §2)multica-test-t3-ui-automation
Contract not N/A + manifest or Apifox three IDs completemultica-test-t3-api-automation
Both completeRun both, then merge one AC report
One side's materials missingThat side interrupted; the other may run. If an AC can only be verified by the missing side → whole ticket cannot be PASS

When there is no UI channel, Apifox materials still follow the contract requirement; when there is no API channel, Apifox three IDs marked N/A do not count as missing.

Never use xmind-ui-automation, playwright.git, req-figma-ui-automation as T3 UI prerequisites.

Merge report template: references/t3-merge-report.md. FAIL/ERROR triage: references/t3-failure-triage.md (@Tester responsible; fix case problems yourself, assign product problems to FE/BE). Report corresponds to G3.

Why it works

Orchestration is separated from content skills: Tester only needs to mount this skill to know phase routing and hard gates; sub-skills can evolve independently.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Multica Test Orchestration AI skill do?

Tester T1/T2/T3 orchestration and gatekeeping—sub-skill routing, assembling materials from Issue comments, and BLOCKED interruption list. Integrates acceptance-verifier-squad; the preferred mount for @Tester.

Why use Multica Test Orchestration on TypingMind?

Because you install it once and use it with any model. Multica Test Orchestration is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Multica Test Orchestration in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/it235/multica-best-practices/tree/main/templates/en_US/skills/tester/multica-test-orchestration. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Multica Test Orchestration?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Multica Test Orchestration?

As many as you like. As long as a model supports skills, you can use Multica Test Orchestration with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Multica Test Orchestration AI skill free?

Yes. It is published on GitHub by it235 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇