Designing Tests
CloudAI-X/claude-workflow-v2
Designs and implements testing strategies for any codebase. An agent skill from CloudAI-X/claude-workflow-v2.
Guides writing or refactoring tests for the Mistral Vibe CLI agent so they check behavior through stable boundaries, like tool invocation or saved session shape, instead of internal calls.
Install Write Vibe Tests
$ npx skills add mistralai/mistral-vibe --skill write-vibe-tests -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mistralai/mistral-vibe write-vibe-tests --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mistralai/mistral-vibe.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.vibe/skills/write-vibe-tests .claude/skills/write-vibe-tests && rm -rf skills-srcUse ~/.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/
Install the "write-vibe-tests" agent skill from https://github.com/mistralai/mistral-vibe/tree/main/.vibe/skills/write-vibe-tests into .claude/skills/write-vibe-tests/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-vibe-tests", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mistralai/mistral-vibe/tree/main/.vibe/skills/write-vibe-testsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mistralai/mistral-vibe --skill write-vibe-tests -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mistralai/mistral-vibe write-vibe-tests --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mistralai/mistral-vibe.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.vibe/skills/write-vibe-tests .agents/skills/write-vibe-tests && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "write-vibe-tests" agent skill from https://github.com/mistralai/mistral-vibe/tree/main/.vibe/skills/write-vibe-tests into .agents/skills/write-vibe-tests/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-vibe-tests", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mistralai/mistral-vibe --skill write-vibe-tests -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mistralai/mistral-vibe write-vibe-tests --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mistralai/mistral-vibe.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.vibe/skills/write-vibe-tests .cursor/skills/write-vibe-tests && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "write-vibe-tests" agent skill from https://github.com/mistralai/mistral-vibe/tree/main/.vibe/skills/write-vibe-tests into .cursor/skills/write-vibe-tests/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-vibe-tests", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mistralai/mistral-vibe.git --path .vibe/skills/write-vibe-tests--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mistralai/mistral-vibe --skill write-vibe-tests -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mistralai/mistral-vibe write-vibe-tests --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mistralai/mistral-vibe.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.vibe/skills/write-vibe-tests .gemini/skills/write-vibe-tests && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "write-vibe-tests" agent skill from https://github.com/mistralai/mistral-vibe/tree/main/.vibe/skills/write-vibe-tests into .gemini/skills/write-vibe-tests/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-vibe-tests", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mistralai/mistral-vibe write-vibe-testsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mistralai/mistral-vibe --skill write-vibe-tests -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mistralai/mistral-vibe.git skills-src && mkdir -p .github/skills && cp -r skills-src/.vibe/skills/write-vibe-tests .github/skills/write-vibe-tests && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "write-vibe-tests" agent skill from https://github.com/mistralai/mistral-vibe/tree/main/.vibe/skills/write-vibe-tests into .github/skills/write-vibe-tests/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-vibe-tests", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mistralai/mistral-vibe --skill write-vibe-tests -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mistralai/mistral-vibe write-vibe-tests --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mistralai/mistral-vibe.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.vibe/skills/write-vibe-tests .opencode/skills/write-vibe-tests && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "write-vibe-tests" agent skill from https://github.com/mistralai/mistral-vibe/tree/main/.vibe/skills/write-vibe-tests into .opencode/skills/write-vibe-tests/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-vibe-tests", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
write-vibe-tests- GitHub stars
- 5.1k
- Token cost
- ~1.2k tokens
- SKILL.md length
- 535 words
- Files
- 1
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Guides writing or refactoring tests for the Mistral Vibe CLI agent so they check behavior through stable boundaries, like tool invocation or saved session shape, instead of internal calls.
- Works in 5 steps: Find the smallest seam: function… → Add characterization tests through the… → Capture current observable behavior,… → …
- Adding test coverage for a new feature in the Vibe codebase
- SKILL.md covers Core Principle, Vibe Test Boundaries, Prefer Fakes Over Mocks and Legacy Or Refactor Workflow, plus 3 more sections
- Calls uv
What it does
The core principle is that a refactor which changes no observable behavior should not break many tests; if it does, the tests were coupled to implementation details. A table sets the preferred test boundary per area: core services through their public API and persisted state, tools through BaseTool.invoke or run with typed results and permission behavior, LLM orchestration through AgentLoop events and fake backends, config through Pydantic validation and layer merge, sessions through saved JSONL shape and resume behavior, CLI widgets through Textual snapshots, and ACP through its session updates rather than core internals.
Fakes are preferred over mocks: reusable in-memory test doubles live in tests/stubs named Fake*, kept small and behavior-oriented, with mocks reserved for hard process, network, time or third-party boundaries, and assertions like "method X was called with Y" used only when the call itself is the observable contract.
For legacy or hard-to-test code, the workflow finds the smallest seam, such as a constructor dependency or module boundary, adds characterization tests through the nearest public entry point to capture current behavior even if awkward, refactors behind that seam in small steps, then replaces the characterization checks with clearer behavior tests. The stack is pytest with pytest-asyncio, pytest-textual-snapshot and respx, using descriptive test names without docstrings.
When your agent uses it
- Adding test coverage for a new feature in the Vibe codebase
- Replacing brittle mocks with fakes for a port or adapter
- Adding characterization tests before refactoring hard-to-test code
- Deciding where a test boundary should sit for tools, sessions or CLI widgets
Example prompts
- “Write tests for the new session resume logic using a fake backend instead of mocks.”
- “Add characterization tests around this legacy config loader before we refactor it.”
- “Replace the mock-heavy tests in tests/tools/test_search.py with a Fake adapter.”
Requirements
- pytest with pytest-asyncio, pytest-textual-snapshot and respx
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Find the smallest seam: function boundary, constructor dependency, protocol/port, wrapper, composition root, feature flag, or module…
- Add characterization tests through the nearest public entry point.
- Capture current observable behavior, even if awkward.
- Refactor behind the seam in small steps.
- Replace broad characterization checks with clearer behavior/spec tests as the design improves.
What it can do on your machine
Read from SKILL.md and the folder at commit 7cb9189. 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
Shell commands in SKILL.md call:
uv
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.
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
Write Vibe Tests loads about 1.2k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 535 words of instructions outside code blocks.
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); files beside SKILL.md are not scanned.
SKILL.md
The full file from mistralai/mistral-vibe at commit 7cb9189, republished under its Apache-2.0 licence (© mistralai). 535 words, ~1,195 tokens.
Download SKILL.mdSave it as
.claude/skills/write-vibe-tests/SKILL.md (or your agent's skills folder).- name
- write-vibe-tests
- description
- Write or refactor Mistral Vibe tests with proper decoupling. Use when adding behavior coverage, testing ports/adapters, replacing brittle mocks, creating fakes, adding characterization tests before refactors, or changing tests under tests/ for vibe/core, vibe/cli, vibe/acp, tools, config, sessions, skills, hooks, MCP, or setup.
- metadata.display-name
- Write Vibe Tests
- metadata.short-description
- Write decoupled behavior tests for Vibe
- metadata.default-prompt
- Use $write-vibe-tests to add or refactor Mistral Vibe tests around behavior and stable boundaries.
Write Vibe Tests
Use this skill to make Vibe architecture testable, not just well-shaped. Tests should protect observable behavior while allowing internals to move.
Core Principle
Test behavior through stable boundaries. Do not couple tests to private methods, internal call choreography, or temporary structure.
If a refactor changes no observable behavior but breaks many tests, the tests are probably coupled to implementation details.
Vibe Test Boundaries
| Code area | Preferred test boundary |
|---|---|
| Core use cases and services | Public function/class API, typed events, model outputs, persisted state |
| Tools | BaseTool.invoke/run, typed args/results, permission behavior, user-facing errors |
| LLM/backend orchestration | AgentLoop events and fake backend outputs |
| Config | Pydantic model validation, layer merge outputs, migration results |
| Sessions | Saved JSONL/metadata shape, resume/loader behavior, migration behavior |
| CLI widgets | Textual snapshots, posted messages, rendered user-visible state |
| ACP | ACP session updates and protocol-facing content, not core internals |
Prefer Fakes Over Mocks
Prefer in-memory implementations and fake adapters that implement real contracts.
- Put reusable test doubles in
tests/stubs/and name themFake*. - Make fakes small and behavior-oriented.
- Mock only at hard process, network, time, or third-party boundaries when a fake would be more complex than the behavior under test.
- Avoid assertions like "method X was called with Y" unless the call itself is the observable contract.
Legacy Or Refactor Workflow
When code is hard to test:
- Find the smallest seam: function boundary, constructor dependency, protocol/port, wrapper, composition root, feature flag, or module boundary.
- Add characterization tests through the nearest public entry point.
- Capture current observable behavior, even if awkward.
- Refactor behind the seam in small steps.
- Replace broad characterization checks with clearer behavior/spec tests as the design improves.
Prefer "make it testable" refactors first: isolate I/O, extract pure functions, introduce ports/adapters where useful, or move construction out of business logic.
Show full SKILL.md (241 more words)Show less
Test Shape
- Stack:
pytest+pytest-asyncio+pytest-textual-snapshot+respx. - Use descriptive test names; do not add test docstrings. Pytest displays docstrings instead of node IDs when present, which hurts.
- Arrange, act, and assert clearly, but optimize for readability over ceremony.
- Keep tests deterministic, fast, and explicit about failure.
- Use autouse fixtures from
tests/conftest.py(config_dir,tmp_working_directory) for config/home/working-directory isolation. - Mark async tests with
@pytest.mark.asyncio. - Mock outbound HTTP with
respx. - Use the narrowest relevant test first, then broaden when shared contracts are touched.
- Tests are exempt from the
ANNandPLRruff rules (seeper-file-ignores). - Changes to managed shell tools, managed shell backends, shell prompts, or shell dependencies require focused POSIX/common validation and passing Windows shell CI. If Windows shell CI is unavailable, the PR notes must include manual native Windows commands and results.
- After app-server session behavior, backend adapters, or shared contract-fixture changes, run both backend contract commands. A failing Unified frontier is expected before parity; include its complete pytest summary in parity-related PRs.
Avoid
- Testing private methods as the primary coverage for behavior.
- Asserting intermediate internal state when user-visible output, emitted events, files, or return values can be asserted.
- Building mocks that mirror the implementation.
- Adding abstractions only to satisfy a test.
- Writing tests that require a specific internal file split or call order when the domain behavior is unchanged.
Verification
After Python test/code changes, run:
uv run ruff format .
uv run ruff check --fix .Then run the targeted tests:
uv run pytest <test-path-or-node-id>Run uv run pyright when signatures, models, protocols, or shared contracts changed.
© mistralai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .vibe/skills/write-vibe-tests of mistralai/mistral-vibe.
Open the folder on GitHubat commit 7cb9189
Compare with similar skills
Write Vibe Tests 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Write Vibe Tests this skillmistralai/mistral-vibe | 5.1k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| Designing TestsCloudAI-X/claude-workflow-v2 | 1.4k | 1 repos | ~1.5k | Automated safety check: Pass | MIT | |
| Robotics Testingarpitg1304/robotics-agent-skills | 368 | — | ~4.7k | Automated safety check: Pass | Apache-2.0 | |
| Python Testingaffaan-m/ECC | 275k | 6 repos | ~4.7k | Automated safety check: Pass | MIT | |
| Python Testing Patternsjh941213/my-cc-harness | 126 | 17 repos | ~5.4k | Automated safety check: Pass | None | |
| Python Testingaffaan-m/ECC | 275k | — | ~2.7k | Automated safety check: Pass | MIT |
Similar skills
Robotics Testing
arpitg1304/robotics-agent-skills
Testing strategies, patterns, and tools for robotics software.
Python Testing
affaan-m/ECC
Python testing strategies using pytest, TDD methodology, fixtures, mocking, parametrization, and coverage requirements.
Python Testing Patterns
jh941213/my-cc-harness
Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development.
Python Testing
affaan-m/ECC
Python testing best practices using pytest including fixtures, parametrization, mocking, coverage analysis, async testing, and test organization.
Python Testing Strategies
c0x12c/ai-toolkit
Testing patterns for FastAPI with pytest-asyncio, httpx AsyncClient, fixtures, and test data factories.
More from mistralai/mistral-vibe
All 14 skills in this repo- Official
Mistral Vibe Plugin Creator
mistralai/mistral-vibe
Shows how to build a Vibe plugin package in the Agent Plugins 1.0 format, with a plugin.json manifest and optional skills, MCP servers, hooks and other components.
- Official
Create Vibe Feature
mistralai/mistral-vibe
Guides feature work in the Mistral Vibe Python CLI so each change lands in the right module and matches the project's architecture decision records.
- Official
Feature Analytics Instrumentation Planner
mistralai/mistral-vibe
Plans which analytics events and properties a new feature needs, checks them against the existing event registry, and verifies them per environment.
- Official
Vibe Worktree Manager
mistralai/mistral-vibe
Creates, reuses and cleans up git worktrees under a shared vibe home directory, with per-repo buckets, claim records and dirty-state checks before removal.
- Official
Write Vibe ADR
mistralai/mistral-vibe
Creates or updates concise Architecture Decision Records for the Mistral Vibe CLI and registers each one in the AGENTS.md decisions table.
- Official
Mistral Vibe CLI Reference
mistralai/mistral-vibe
Reference for Mistral Vibe, the CLI agent it runs inside: config files, env vars, agents, skills, tools, hooks and MCP servers, so the agent can explain and troubleshoot its own setup.
Related
Works with
Categories
Questions about Write Vibe Tests
What does Write Vibe Tests do?
Guides writing or refactoring tests for the Mistral Vibe CLI agent so they check behavior through stable boundaries, like tool invocation or saved session shape, instead of internal calls. The core principle is that a refactor which changes no observable behavior should not break many tests; if it does, the tests were coupled to implementation details.invoke or run with typed results and permission behavior, LLM orchestration through AgentLoop events and fake backends, config through Pydantic validation and layer merge, sessions through saved JSONL shape and resume behavior, CLI widgets through Textual snapshots, and ACP through its session updates rather than core internals.
When should I use Write Vibe Tests?
Write Vibe Tests fits situations like: adding test coverage for a new feature in the Vibe codebase; replacing brittle mocks with fakes for a port or adapter; adding characterization tests before refactoring hard-to-test code; deciding where a test boundary should sit for tools, sessions or CLI widgets.
How do I install Write Vibe Tests in Claude Code?
Run `npx skills add mistralai/mistral-vibe --skill write-vibe-tests -a claude-code`. Or copy the skill folder (.vibe/skills/write-vibe-tests in mistralai/mistral-vibe) into .claude/skills/write-vibe-tests in your project. Claude Code loads it when a task matches its description.
How do I install Write Vibe Tests in Codex?
Run `npx skills add mistralai/mistral-vibe --skill write-vibe-tests -a codex`. Or copy the skill folder (.vibe/skills/write-vibe-tests in mistralai/mistral-vibe) into .agents/skills/write-vibe-tests in your project. Codex loads it when a task matches its description.
Can I use Write Vibe Tests 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 mistralai/mistral-vibe --skill write-vibe-tests -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/write-vibe-tests, .gemini/skills/write-vibe-tests, .github/skills/write-vibe-tests and .opencode/skills/write-vibe-tests in your project.
What does Write Vibe Tests need to run?
Going by SKILL.md and its folder, Write Vibe Tests needs the command-line tools its instructions call (uv). Our summary lists: pytest with pytest-asyncio, pytest-textual-snapshot and respx.
Does Write Vibe Tests access the network?
SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Write Vibe Tests 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. Review the folder before installing.
What licence does Write Vibe Tests use?
Write Vibe Tests is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Write Vibe Tests use?
About 1.2k tokens (SKILL.md is roughly 4.8k 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 Write Vibe Tests?
Skills that share tags, products or a category with Write Vibe Tests: Designing Tests (CloudAI-X/claude-workflow-v2, 1.4k stars), Robotics Testing (arpitg1304/robotics-agent-skills, 368 stars), Python Testing (affaan-m/ECC, 275k stars) and Python Testing Patterns (jh941213/my-cc-harness, 126 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Write Vibe Tests?
mistralai (a GitHub organization, an official publisher) maintains it in mistralai/mistral-vibe, which has 5,073 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 7, 2026.
Source: mistralai/mistral-vibe on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.