New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Write Tests

by open-thoughts in open-thoughts/OpenThoughts-Agent

Write or revise tests with an emphasis on behavior, regression coverage, pytest style, and avoiding "slop tests." Use when adding tests, fixing failing tests, reviewing test quality, or deciding…

Apache-2.0Auto-check passedTesting & QA

Install Write Tests

skills CLI
$ npx skills add open-thoughts/OpenThoughts-Agent --skill write-tests -a claude-code

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

GitHub CLI
$ gh skill install open-thoughts/OpenThoughts-Agent write-tests --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/open-thoughts/OpenThoughts-Agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/write-tests .claude/skills/write-tests && 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
write-tests
GitHub stars
301
Token cost
~498 tokens
SKILL.md length
244 words
Files
1
Skills in repo
44
Repo updated
First seen
Licence
Apache-2.0

At a glance

Write or revise tests with an emphasis on behavior, regression coverage, pytest style, and avoiding "slop tests." Use when adding tests, fixing failing tests, reviewing test quality, or deciding…

  • Works in 7 steps: Find existing tests for the touched… → Check for repo-specific testing rules… → Name the behavior that should fail if… → …
  • Fixing failing tests
  • SKILL.md covers Workflow and Default Commands
  • Calls uv

What it does

Write Tests is an agent skill from open-thoughts/OpenThoughts-Agent. Write or revise tests with an emphasis on behavior, regression coverage, pytest style, and avoiding "slop tests." Use when adding tests, fixing failing tests, reviewing test quality, or deciding what test would catch a bug.

Its SKILL.md is about 500 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering Test generation, Unit testing and Failing and flaky tests. It works with pytest. The repository describes itself as: Data recipes and robust infrastructure for training AI agents. The licence is Apache-2.0.

When your agent uses it

  • Fixing failing tests
  • Reviewing test quality
  • Deciding what test would catch a bug

Example prompts

  • “slop tests.”
  • “/write-tests”

Workflow steps

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

  1. Find existing tests for the touched behavior before creating a new file.
  2. Check for repo-specific testing rules for commands, markers, fakes, mocks, and
  3. Name the behavior that should fail if the code is wrong.
  4. Write the smallest test that observes that behavior through a public API,
  5. Prefer a regression test before the fix when fixing a bug. Ensure the test
  6. Keep test setup realistic but small. Use fixtures and parameterization to
  7. Run the narrow test first, then the relevant package test command. Before a

What it can do on your machine

Read from SKILL.md and the folder at commit 3bd1917. 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 Tests loads about 498 tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 244 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~498

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 open-thoughts/OpenThoughts-Agent at commit 3bd1917, republished under its Apache-2.0 licence (© open-thoughts). 244 words, ~498 tokens.

Download SKILL.mdSave it as .claude/skills/write-tests/SKILL.md (or your agent's skills folder).
name
write-tests
description
Write or revise tests with an emphasis on behavior, regression coverage, pytest style, and avoiding "slop tests." Use when adding tests, fixing failing tests, reviewing test quality, or deciding what test would catch a bug.
<!-- Vendored from marin-community/marin-style v0.3.0 — do not edit; re-run `marin-style sync`. -->

Write Tests

Use this skill when a change needs tests or when existing tests look too coupled to implementation details.

Read TESTING.md before writing or reviewing non-trivial tests. It is the shared behavior-focused testing policy, also used by commit. Read AGENTS.md for the repo's coding standards. If the repo has package- or module-specific testing docs, read the nearest one for local commands, markers, fakes, mocks, and numerical tolerances before choosing a test style.

Workflow

  1. Find existing tests for the touched behavior before creating a new file.
  2. Check for repo-specific testing rules for commands, markers, fakes, mocks, and numerical tolerances.
  3. Name the behavior that should fail if the code is wrong.
  4. Write the smallest test that observes that behavior through a public API, structured output, persisted state, or real side effect.
  5. Prefer a regression test before the fix when fixing a bug. Ensure the test fails before implementing the bug fix.
  6. Keep test setup realistic but small. Use fixtures and parameterization to remove duplication.
  7. Run the narrow test first, then the relevant package test command. Before a PR, run the repo lint entry point required by AGENTS.md.

Default Commands

  • Run the repo's test command over the test directories your change touches (e.g. uv run pytest -m 'not slow').
  • For package-specific commands, use the relevant package testing doc.

For PR preparation, run infra/pre-commit.py --changed-files --fix or infra/pre-commit.py --all-files --fix as appropriate. Do not replace it with uv run pre-commit.

© open-thoughts, 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 .agents/skills/write-tests of open-thoughts/OpenThoughts-Agent.

Open the folder on GitHubat commit 3bd1917

Compare with similar skills

Write 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.

Write Tests compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Write Tests this skillopen-thoughts/OpenThoughts-Agent301—~498Automated safety check: PassApache-2.0
Blue Teamgaasher/Agent-Loop-Skills174—~3.6kAutomated safety check: PassMIT
Maintaining Python TestsPostHog/posthog-foss721—~2.5kAutomated safety check: PassMIT
Adk Verify Snippetsgoogle/adk-python22k—~1.4kAutomated safety check: PassApache-2.0
Hermetic Python Unit TestsdimensionalOS/dimos4.6k—~1.4kAutomated safety check: PassCustom licence
ONNX Runtime Test Runnermicrosoft/onnxruntime22k—~1.8kAutomated safety check: PassMIT

Similar skills

  • Blue Team

    gaasher/Agent-Loop-Skills

    A skill your agent uses when the user has concrete failing cases in code or a guardrail/classifier/filter/prompt/API they own — a red-team failure catalogue OR a CI/CD test-failure report (failing…

    174 GitHub stars~3.6k tokensUpdated 3 mo ago
    Testing & QAAuto-check passed

  • Maintaining Python Tests

    PostHog/posthog-foss

    Official

    Maintains existing pytest and Django test suites without weakening correctness.

    721 GitHub stars~2.5k tokensUpdated today
    Testing & QAAuto-check passed

  • Adk Verify Snippets

    google/adk-python

    Official

    Checks that every Python code block in a Markdown file actually compiles and runs, by extracting each block to a temporary file, executing it in an isolated subprocess, and writing a pass/fail…

    22k GitHub stars~1.4k tokensUpdated today
    Testing & QAAuto-check passed

  • Hermetic Python Unit Tests

    dimensionalOS/dimos

    Rules for writing, fixing and reviewing pytest unit tests that are hermetic: behavior-focused, deterministic, isolated and cheap to run.

    4.6k GitHub stars~1.4k tokensUpdated today
    Testing & QAAuto-check passed

  • ONNX Runtime Test Runner

    microsoft/onnxruntime

    Official

    Runs and debugs ONNX Runtime tests: Google Test executables for C++ and unittest or pytest for Python, with filters and build-directory guidance.

    22k GitHub stars~1.8k tokensUpdated today
    Testing & QAAuto-check passed

  • Designing Tests

    CloudAI-X/claude-workflow-v2

    Designs and implements testing strategies for any codebase. An agent skill from CloudAI-X/claude-workflow-v2.

    1.4k GitHub starsUsed in 1 repo~1.5k tokens
    Testing & QAAuto-check passed

More from open-thoughts/OpenThoughts-Agent

All 44 skills in this repo

  • Analyze Dataset Token Length

    open-thoughts/OpenThoughts-Agent

    Analyze the token length of an OT-Agent conversation-format (ShareGPT-style) dataset — the per-trace distribution (median/p90/max) and/or counts under a token threshold + a metadata predicate (e.g.

    301 GitHub stars~1.5k tokensUpdated 9 days ago
    Auto-check passed

  • Analyze Id Eval Ranking

    open-thoughts/OpenThoughts-Agent

    Given a list of models (HF name stubs) that have valid agentic ID eval scores in Supabase, build a ranking table: raw per-benchmark accuracy on the 3 ID benchmarks (SWE-Bench-100…

    301 GitHub stars~3.1k tokensUpdated 9 days ago
    Auto-check passed

  • Analyze Job History Iris

    open-thoughts/OpenThoughts-Agent

    Run the Iris harbor job-history analyzer (scripts/iris/analyzeirisharborjob.py) on a datagen/eval job and read its JSON sidecar for trustworthy throughput / preemption / productive-trial stats.

    301 GitHub stars~2.9k tokensUpdated 9 days ago
    Auto-check passed

  • Analyze Rl Behavior

    open-thoughts/OpenThoughts-Agent

    Run the full RL behavioral-analysis pipeline (scripts/analysis/analyzerlbehavior.py) on a trained RL model to understand WHAT changed vs its pre-RL baseline, WHY, whether it PERSISTS, and its EVAL…

    301 GitHub stars~4.2k tokensUpdated 9 days ago
    Auto-check passed

  • Analyze Training Run Iris

    open-thoughts/OpenThoughts-Agent

    Detailed health check for a Levanter/executor TRAINING run on the marin Iris cluster (e.g.

    301 GitHub stars~2k tokensUpdated 9 days ago
    Auto-check passed

  • Code Create Staged Plan

    open-thoughts/OpenThoughts-Agent

    DESIGN a non-trivial codebase change (Harbor / MarinSkyRL / vLLM / OT-Agent / LLaMA-Factory) as a dependency-ordered STAGED PLAN before writing code — a feature port, a multi-step fix with parity…

    301 GitHub stars~1.5k tokensUpdated 9 days ago
    Auto-check passed

Works with

Categories

Questions about Write Tests

What does Write Tests do?

Write or revise tests with an emphasis on behavior, regression coverage, pytest style, and avoiding "slop tests." Use when adding tests, fixing failing tests, reviewing test quality, or deciding…. Write Tests is an agent skill from open-thoughts/OpenThoughts-Agent." Use when adding tests, fixing failing tests, reviewing test quality, or deciding what test would catch a bug.

When should I use Write Tests?

Write Tests fits situations like: fixing failing tests; reviewing test quality; deciding what test would catch a bug.

How do I install Write Tests in Claude Code?

Run `npx skills add open-thoughts/OpenThoughts-Agent --skill write-tests -a claude-code`. Or copy the skill folder (.agents/skills/write-tests in open-thoughts/OpenThoughts-Agent) into .claude/skills/write-tests in your project. Claude Code loads it when a task matches its description.

How do I install Write Tests in Codex?

Run `npx skills add open-thoughts/OpenThoughts-Agent --skill write-tests -a codex`. Or copy the skill folder (.agents/skills/write-tests in open-thoughts/OpenThoughts-Agent) into .agents/skills/write-tests in your project. Codex loads it when a task matches its description.

Can I use Write 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 open-thoughts/OpenThoughts-Agent --skill write-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-tests, .gemini/skills/write-tests, .github/skills/write-tests and .opencode/skills/write-tests in your project.

What does Write Tests need to run?

Going by SKILL.md and its folder, Write Tests needs the command-line tools its instructions call (uv).

Does Write 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 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 Tests use?

Write 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 Tests use?

About 498 tokens (SKILL.md is roughly 2k 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 Tests?

Skills that share tags, products or a category with Write Tests: Blue Team (gaasher/Agent-Loop-Skills, 174 stars), Maintaining Python Tests (PostHog/posthog-foss, 721 stars), Adk Verify Snippets (google/adk-python, 22k stars) and Hermetic Python Unit Tests (dimensionalOS/dimos, 4.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Write Tests?

open-thoughts (a GitHub organization) maintains it in open-thoughts/OpenThoughts-Agent, which has 301 GitHub stars. The repository holds 44 skills in this directory. The repository was last updated on September 28, 2026.

Source: open-thoughts/OpenThoughts-Agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.