More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Fix Failing Tests Without Skipping or Weakening Them

    1

    Gets a red test suite back to green by fixing the real cause of each failure, never by deleting, skipping or loosening tests without your OK.

    Free

    2 usesSecurity scanned

    Fix Failing Tests Without Skipping or Weakening Them

    Example session with this skill installed

    The tests are failing. Fix them.

    • Read your context and instructions
    • Compiled the fix failing tests

    Test suite: still failing, needs your decision

    Before: the test file couldn't load (0 of 9 tests ran) · After: 1 failed / 9 total
    Command: npm test (vitest run)

    Fixed

    Test(s)CategoryRoot causeFix
    Whole file (Cannot find package '@/shipping')Environment/setupCommit e649fbb ("Tidy vitest config") removed the @ alias from the vitest config. tsconfig.json still maps @/* to src/*.vitest.config.ts:5: put the resolve.alias back and kept the new test.include
    freeShippingEligible › members qualify from exactly $25Code bugThe same commit changed orderTotal >= 25 to > 25. That contradicts the docstring, which says members get free shipping "from $25".src/shipping.ts:38: back to >= 25
    shippingCost › prices any allowed weightFlakyThe test picked a random weight from 0.1 to 50.1 kg, so about 40% of runs used a weight over 30 kg, which the code rejects.test/shipping.test.ts:21: the random weight is replaced with fixed weights 0.1, 1, 2, 2.1, 15, 29.9 and 30 kg, which cover the whole allowed range and its edges. The check (toBeGreaterThan(0)) is unchanged. It passed 5 out of 5 runs on its own.

    Needs your decision

    TestWhy I think the test is wrongProposed change
    shippingCost › charges the international base rateThe test expects 15 and the code returns 18. Commit d8f0192 ("Raise international base rate to $18 (carrier contract renewal)") and the CHANGELOG.md 1.1.0 entry both show the $18 rate was deliberate.test/shipping.test.ts:9: .toBe(15) → .toBe(18)

    Reply

    yes to update the test as shown,

    no if the test is right and the source should change instead (I'll propose that change and ask again before editing anything), or

    leave it to change nothing.

    Unresolved

    TestCategoryWhat's blockingSuggested next step
    none

    Test integrity (checked against git diff)

    No tests were deleted, skipped or loosened, and no expected values were changed. The one test edit was the flaky fix: prices any allowed weight now uses fixed weights instead of a random one, with the same check.

    Files changed (from git diff)

    • vitest.config.ts: put back the @ → ./src path alias
    • src/shipping.ts: members qualify for free shipping at exactly $25 again (>= 25)
    • test/shipping.test.ts: random weight replaced with fixed weights covering the allowed range; same check

    Final check output

     src/shipping.ts       | 2 +-
     test/shipping.test.ts | 5 +++--
     vitest.config.ts      | 2 ++
     3 files changed, 6 insertions(+), 3 deletions(-)
    

    Already modified before this run

    • none

    You: approved


    Test suite: passing

    Before: the test file couldn't load (0 of 9 tests ran) · After: 0 failed / 9 total
    Command: npm test (vitest run)

    Fixed

    Test(s)CategoryRoot causeFix
    Whole file (Cannot find package '@/shipping')Environment/setupCommit e649fbb removed the @ alias from the vitest config. tsconfig.json still maps @/* to src/*.vitest.config.ts:5: put the resolve.alias back and kept test.include
    freeShippingEligible › members qualify from exactly $25Code bugCommit e649fbb changed >= 25 to > 25, which contradicts the docstring ("from $25").src/shipping.ts:38: back to >= 25
    shippingCost › prices any allowed weightFlakyThe random weight (0.1 to 50.1 kg) often went over the 30 kg limit.test/shipping.test.ts:21: fixed weights 0.1, 1, 2, 2.1, 15, 29.9 and 30 kg; same check; passed 5 out of 5 runs on its own
    shippingCost › charges the international base rateOutdated testCommit d8f0192 and CHANGELOG 1.1.0 raised the international base rate to $18.test/shipping.test.ts:9: .toBe(15) → .toBe(18)

    Needs your decision

    none

    Unresolved

    none

    Test integrity (checked against git diff)

    One expected value was changed: charges the international base rate, from 15 to 18, after you approved

    this test change ("approved"). The other test edit is the flaky fix: prices any allowed weight now uses fixed weights instead of a random one, with the same check. No tests were deleted, skipped or loosened.

    Files changed (from git diff)

    • vitest.config.ts: put back the @ → ./src path alias
    • src/shipping.ts: members qualify for free shipping at exactly $25 again (>= 25)
    • test/shipping.test.ts: fixed weights instead of a random one, same check; international base rate expectation 15 → 18 (approved: test change)

    Final check output

     src/shipping.ts       | 2 +-
     test/shipping.test.ts | 7 ++++---
     vitest.config.ts      | 2 ++
     3 files changed, 7 insertions(+), 4 deletions(-)
    

    Already modified before this run

    • none

    Nothing is committed yet.

    Tip: green tests don't prove they'd catch a regression. The Mutation-Verified Test Generator skill measures that with a mutation score.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    The problem

    Ask an AI agent to "make the tests pass" and it often will, by editing the expected value, wrapping a flaky test in a retry, or adding .skip. The suite turns green and the bug ships. Tests are your specification; silencing them isn't fixing them.

    What this skill does

    It treats every failing test as evidence, and works out why it fails before changing anything. Each failure gets exactly one category:

    CategoryWhat it meansWhat the agent changes
    Code bugThe code is wrong, the test is rightThe source, with the smallest fix
    Outdated testBehaviour changed on purpose (commit, changelog, docs)Nothing until you decide. It shows the evidence and the exact diff, then asks: yes, no or leave it (see below)
    Environment/setupMissing alias, wrong config, moved fixture file, missing dependencyIn-repo config; anything outside the repo is given to you as a command
    FlakyPasses and fails on the same codeRemoves the nondeterminism (time, randomness, ordering, shared state)

    When the evidence is unclear, it assumes the test is right.

    When a test looks outdated, you choose:

    • yes: it updates the test's expected value as shown.
    • no: the test is right, so the source should change instead. It doesn't edit anything yet. It shows the evidence that the source change looked deliberate, the exact source diff, a warning that this reverses an intentional-looking change, and what else depends on the value. Then it asks again: yes to apply that source change, or leave it.
    • leave it: nothing changes; the test is reported as unresolved and the suite stays failing.

    Each edit needs its own "yes" to its own question, and the report says which approval covered which change.

    Hard rules. It never deletes or skips a test, loosens an assertion, changes an expected value, updates snapshots, or adds retries or sleeps, unless you explicitly approve after it explains why the test itself is wrong. It never installs packages without asking, and never opens .env or other secrets.

    Who it's for

    Anyone who's had a suite break after a refactor, merge or dependency bump, and wants it fixed properly. Also teams who want an agent they can point at CI failures without worrying it will quietly hollow out their tests.

    What the agent does, step by step

    1. Runs your project's own test command and groups failures by shared root cause.
    2. Collects evidence for each one: the failure, the code at the trace, recent git history of the test and the source, docs and changelog, isolated and repeated runs.
    3. Assigns a category and fixes environment issues first, then code bugs, then flaky tests. For outdated tests, it asks (yes / no / leave it) and edits nothing for that test until you answer.
    4. Re-runs the full suite (at most three passes through steps 2–4, so it won't thrash).
    5. Reports what was fixed and how, what needs your decision, what's unresolved, and a test integrity line confirming nothing was weakened.

    Example output

    From a real run on a broken TypeScript + Vitest project (the first report, before any answer; verbatim, shortened after the question). The full run, including the report after "approved", is in the example file.

    ## Test suite: still failing, needs your decision
    
    **Before:** the test file couldn't load (0 of 9 tests ran) · **After:** 1 failed / 9 total
    **Command:** `npm test` (`vitest run`)
    
    ### Fixed
    | Test(s) | Category | Root cause | Fix |
    |---|---|---|---|
    | Whole file (`Cannot find package '@/shipping'`) | Environment/setup | Commit `e649fbb` ("Tidy vitest config") removed the `@` alias from the vitest config. `tsconfig.json` still maps `@/*` to `src/*`. | `vitest.config.ts:5`: put the `resolve.alias` back and kept the new `test.include` |
    | `freeShippingEligible › members qualify from exactly $25` | Code bug | The same commit changed `orderTotal >= 25` to `> 25`. That contradicts the docstring, which says members get free shipping "from $25". | `src/shipping.ts:38`: back to `>= 25` |
    | `shippingCost › prices any allowed weight` | Flaky | The test picked a random weight from 0.1 to 50.1 kg, so about 40% of runs used a weight over 30 kg, which the code rejects. | `test/shipping.test.ts:21`: the random weight is replaced with fixed weights 0.1, 1, 2, 2.1, 15, 29.9 and 30 kg, which cover the whole allowed range and its edges. The check (`toBeGreaterThan(0)`) is unchanged. It passed 5 out of 5 runs on its own. |
    
    ### Needs your decision
    | Test | Why I think the test is wrong | Proposed change |
    |---|---|---|
    | `shippingCost › charges the international base rate` | The test expects 15 and the code returns 18. Commit `d8f0192` ("Raise international base rate to $18 (carrier contract renewal)") and the `CHANGELOG.md` 1.1.0 entry both show the $18 rate was deliberate. | `test/shipping.test.ts:9`: `.toBe(15)` → `.toBe(18)` |
    
    Reply **yes** to update the test as shown, **no** if the test is right and the source should change instead (I'll propose that change and ask again before editing anything), or **leave it** to change nothing.
    

    Supported

    TestedJest, Vitest and pytest projects (code bugs, outdated tests, setup problems, flaky tests, a missing dependency)
    Also worksAny test runner the project uses (node:test, Mocha, unittest, Go and others). The workflow is framework-independent
    Tested agentsClaude Code. Built on the open SKILL.md standard, so it should also work in other agents that support SKILL.md skills.
    ModelsWorks best with strong tool-calling models. Smaller or "lite" models may skip steps or follow the rules less reliably. In testing with a full-size Claude model and the small Claude Haiku, no test was weakened, outdated tests were always left for your decision, and approval was never claimed without a real "yes". With a very small "lite" model, the approval rule was not reliably followed, so use a strong model and review the final git diff it reports.
    RequirementsNone. No scripts, instructions only

    Limitations (honest)

    • It fixes failing tests; it doesn't write new tests or improve coverage.
    • It won't change an expected value on its own, so a suite with outdated tests ends "still failing, needs your decision" until you answer. That's deliberate.
    • Answering no doesn't revert your source in one step. It proposes the source change and asks again, so fixing a test the "no" way takes two answers.
    • Fixes outside the repo (installing packages, runtime versions, services, CI secrets) are handed to you as exact commands rather than done automatically.
    • If it can't run your test command at all, it says so and reports what it could determine, rather than guessing results.

    Tags

    failing-tests, debugging, flaky-tests, ci, jest, vitest, pytest, test-maintenance

    Fixes failing tests; it doesn't write new tests or improve coverage. Changing an expected value, or skipping, deleting or loosening a test, always needs your explicit approval, so a suite with outdated tests ends "needs your decision" until you answer. It doesn't install packages or change anything outside the repo (runtime versions, services, CI secrets); it gives you the exact commands instead. Not designed for lint errors or standalone build/type-check failures. Tested with Jest, Vitest and pytest; works best with strong tool-calling models.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    2 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 29 days ago

    • Free with an Agensi account

    Requires

    Git
    Project test runner
    Python
    vitest
    Node.js
    jest
    mocha

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    Works only inside the current project/repository. Edits source, test and config files to fix failures. Never changes an expected value, skips, deletes or loosens a test without the user's explicit approval. Runs the project's own test command and read-only git commands (status, diff, log). No network calls, no package installs (it suggests the command instead), never opens .env or other secrets.

    Listed29 days ago

    What's inside

    Frequently Asked Questions

    It works out why each test fails before changing anything, and assumes the test is right when the evidence is unclear. It never deletes, skips or loosens a test, changes an expected value or updates snapshots without your explicit “yes”. Before reporting, it checks every change against git diff and lists the actual changes.

    Tested with Jest, Vitest and pytest. The workflow doesn’t depend on a specific framework, so other runners (node:test, Mocha, unittest, Go and others) should work but weren’t tested. It needs a git repository, since the final check uses git diff.

    Yes. It confirms flakiness by re-running the test, then removes the cause of nondeterminism in the test, such as random inputs, time or ordering, by replacing it with fixed values while keeping the same assertion. A narrower random range doesn’t count as a fix.

    No scripts and no installs. You need git and your project’s existing test runner. Install the skill through Agensi into any agent that supports SKILL.md skills; it was tested in Claude Code.

    It fixes setup problems that stop tests from loading, such as a missing path alias, broken test config or a moved fixture file. It isn’t designed for lint errors or standalone build or type-check failures.

    The skill is free. You get the instructions your agent follows (SKILL.md) and a triage reference for classifying failures. It runs inside your own agent; nothing extra is installed.

    New in Testing & Debugging