New: 98,000+ 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 Failing Test First

by Archive228 in Archive228/loopkit

Before fixing any bug, write a test that reproduces it and watch it fail.

MITAuto-check passedDevelopment

Install Write Failing Test First

skills CLI
$ npx skills add Archive228/loopkit --skill write-failing-test-first -a claude-code

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

GitHub CLI
$ gh skill install Archive228/loopkit write-failing-test-first --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/Archive228/loopkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/write-failing-test-first .claude/skills/write-failing-test-first && 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-failing-test-first
GitHub stars
755
Token cost
~197 tokens
SKILL.md length
101 words
Files
1
Skills in repo
43
Repo updated
First seen
Licence
MIT

At a glance

Before fixing any bug, write a test that reproduces it and watch it fail.

  • Works in 4 steps: Write the smallest test that reproduces… → Run it. Watch it fail for the right… → Now fix the code. → …
  • Tasks that involve Test-driven development
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Debugging

What it does

Write Failing Test First is an agent skill from Archive228/loopkit. Before fixing any bug, write a test that reproduces it and watch it fail. Use for every bug fix.

Its SKILL.md is about 200 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 Development, covering Test-driven development and Debugging. The repository describes itself as: 33 battle-tested skills + minimal .claude harness for any coding agent (Claude Code, Cursor, Codex, Gemini CLI). The licence is MIT.

When your agent uses it

  • Tasks that involve Test-driven development
  • Tasks that involve Debugging

Example prompts

  • “/write-failing-test-first”

Workflow steps

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

  1. Write the smallest test that reproduces the reported behavior.
  2. Run it. Watch it fail for the right reason (read the assertion, not just red).
  3. Now fix the code.
  4. Run the test. It passes. Run the FULL suite — you didn't break anything else.

What it can do on your machine

Read from SKILL.md and the folder at commit 5ae033e. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Write Failing Test First loads about 197 tokens when it runs. Until then it costs about 30 tokens; SKILL.md has 101 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~30
When it runs · the whole SKILL.md, loaded when a task matches
~197

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 Archive228/loopkit at commit 5ae033e, republished under its MIT licence (© Archive228). 101 words, ~197 tokens.

Download SKILL.mdSave it as .claude/skills/write-failing-test-first/SKILL.md (or your agent's skills folder).
name
write-failing-test-first
description
Before fixing any bug, write a test that reproduces it and watch it fail. Use for every bug fix.
when_to_use
fixing a bug, "make X work", a reported defect

Write the Failing Test First

The only proof you fixed a bug is a test that failed before and passes after.

  1. Write the smallest test that reproduces the reported behavior.
  2. Run it. Watch it fail for the right reason (read the assertion, not just red).
  3. Now fix the code.
  4. Run the test. It passes. Run the FULL suite — you didn't break anything else. If you can't write the test easily, the architecture is telling you something (tight coupling). Say so. Never: fix first, test after (you'll write a test that passes regardless). Never: skip the watch-it-fail step.

© Archive228, MIT. 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 skills/write-failing-test-first of Archive228/loopkit.

Open the folder on GitHubat commit 5ae033e

Compare with similar skills

Write Failing Test First 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 Failing Test First compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Write Failing Test First this skillArchive228/loopkit755—~197Automated safety check: PassMIT
Development Workflowrunceel/ReactiveProperty944—~1.4kAutomated safety check: PassMIT
Triage Issuesoftspark/ai-toolkit179—~1.3kAutomated safety check: NotesApache-2.0
TDD Bug Fixgustavscirulis/snapgrid1171 repos~2kAutomated safety check: NotesCustom licence
Compound Engineering DebugEveryInc/compound-engineering-plugin25k—~4.2kAutomated safety check: PassMIT
Foreman DebugVisionForge-OU/foreman443—~1.1kAutomated safety check: PassCustom licence

Similar skills

  • Development Workflow

    runceel/ReactiveProperty

    ReactiveProperty repository development policy. An agent skill from runceel/ReactiveProperty.

    944 GitHub stars~1.4k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

  • Triage Issue

    softspark/ai-toolkit

    Bug triage: explores codebase for root cause, files GitHub issue with TDD fix plan.

    179 GitHub stars~1.3k tokensUpdated yesterday
    DevelopmentAuto-check: notes

  • TDD Bug Fix

    gustavscirulis/snapgrid

    Fix bugs using red-green-refactor — reproduce the bug as a failing test first, then fix it.

    117 GitHub starsUsed in 1 repo~2k tokens
    DevelopmentAuto-check: notes

  • Compound Engineering Debug

    EveryInc/compound-engineering-plugin

    Finds the root cause of failing or slow behavior with a hypothesis-driven loop, then fixes it test-first if you choose, or hands back a diagnosis only.

    25k GitHub stars~4.2k tokensUpdated 2 days ago
    DevelopmentAuto-check passed

  • Foreman Debug

    VisionForge-OU/foreman

    Headless root-cause debugging loop for a Foreman worker whose tests, build, or acceptance check are failing — especially on a retry.

    443 GitHub stars~1.1k tokensUpdated 3 mo ago
    Testing & QAAuto-check passed

  • Fix Bug

    tddworks/ClaudeBar

    Guide for fixing bugs in ClaudeBar following Chicago School TDD and rich domain design.

    1.5k GitHub stars~2.2k tokensUpdated today
    Testing & QAAuto-check passed

More from Archive228/loopkit

All 43 skills in this repo

  • Hitl Escalate

    Archive228/loopkit

    Escalate blocked runs to a human via configured channel or fallback to BLOCKED.md and exit the loop.

    755 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed

  • Structured Output

    Archive228/loopkit

    Get JSON out of the model reliably. An agent skill from Archive228/loopkit.

    755 GitHub stars~830 tokensUpdated 2 mo ago
    Auto-check passed

  • Using Loopkit

    Archive228/loopkit

    A skill your agent uses when starting any conversation in a loopkit-enabled project - establishes how to find and use loopkit's 49 skills, requiring skill invocation before ANY response including…

    755 GitHub stars~1.4k tokensUpdated 2 mo ago
    Auto-check passed

  • Active Memory Reminder

    Archive228/loopkit

    Before compaction Loopkit extracts decisions into claude-decisions.json (machine-readable).

    755 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed

  • Eval Harness

    Archive228/loopkit

    Build a repeatable eval loop that grades agent output with an LLM judge, so prompt/skill changes get scored against a baseline instead of eyeballed.

    755 GitHub stars~876 tokensUpdated 2 mo ago
    Auto-check passed

  • Feature List JSON

    Archive228/loopkit

    Enumerate every end-to-end feature as strict JSON entries with passes:false, editable-passes-only discipline, and priority order.

    755 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Write Failing Test First

What does Write Failing Test First do?

Before fixing any bug, write a test that reproduces it and watch it fail. Write Failing Test First is an agent skill from Archive228/loopkit. Before fixing any bug, write a test that reproduces it and watch it fail.

When should I use Write Failing Test First?

Write Failing Test First fits situations like: tasks that involve Test-driven development; tasks that involve Debugging.

How do I install Write Failing Test First in Claude Code?

Run `npx skills add Archive228/loopkit --skill write-failing-test-first -a claude-code`. Or copy the skill folder (skills/write-failing-test-first in Archive228/loopkit) into .claude/skills/write-failing-test-first in your project. Claude Code loads it when a task matches its description.

How do I install Write Failing Test First in Codex?

Run `npx skills add Archive228/loopkit --skill write-failing-test-first -a codex`. Or copy the skill folder (skills/write-failing-test-first in Archive228/loopkit) into .agents/skills/write-failing-test-first in your project. Codex loads it when a task matches its description.

Can I use Write Failing Test First 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 Archive228/loopkit --skill write-failing-test-first -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-failing-test-first, .gemini/skills/write-failing-test-first, .github/skills/write-failing-test-first and .opencode/skills/write-failing-test-first in your project.

What does Write Failing Test First need to run?

SKILL.md names no scripts, command-line tools or credentials: Write Failing Test First is instructions for the agent only.

Does Write Failing Test First 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 Write Failing Test First 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 Failing Test First use?

Write Failing Test First is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Write Failing Test First use?

About 197 tokens (SKILL.md is roughly 788 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 Failing Test First?

Skills that share tags, products or a category with Write Failing Test First: Development Workflow (runceel/ReactiveProperty, 944 stars), Triage Issue (softspark/ai-toolkit, 179 stars), TDD Bug Fix (gustavscirulis/snapgrid, 117 stars) and Compound Engineering Debug (EveryInc/compound-engineering-plugin, 25k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Write Failing Test First?

Archive228 (a GitHub user) maintains it in Archive228/loopkit, which has 755 GitHub stars. The repository holds 43 skills in this directory. The repository was last updated on July 14, 2026.

Source: Archive228/loopkit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.