Borrowing it
Nothing to install: this file belongs to Smart-AI-Memory/attune-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Smart-AI-Memory/attune-ai/main/.agents/skills/fix-test/SKILL.mdgit clone --depth 1 https://github.com/Smart-AI-Memory/attune-aiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/smart-ai-memory/attune-ai/fix-test)<a href="https://agentmods.dev/skills/smart-ai-memory/attune-ai/fix-test"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/fix-test/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/smart-ai-memory/attune-ai/fix-test"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/fix-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00047 | $0.00574 |
| Opus 5.5 | $0.00019 | $0.00230 |
| Sonnet 5.5 | $0.00009 | $0.00115 |
| Haiku 4.5 | $0.00005 | $0.00057 |
Grade A, and why
fix-test scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix Test
IMPORTANT: Start your response with a context preamble.
Call help_lookup(topic="fix-test", mode="preamble") and
display the returned preamble text as a blockquote. Then
tell the user they can say "tell me more" for a step-by-step
guide, or answer the scoping questions below to proceed.
If the MCP call fails, fall back to:
Fix Test — Diagnoses failing tests, classifies the root cause, and applies targeted fixes automatically.
Scoping
Before running, ask:
- Target: "Which test is failing? A specific file, test name, or should I find failures automatically?"
- Context: "Did this start failing after a recent change, or has it been broken?"
Execution
Step 1: Identify Failures
Run the failing test(s) to capture the error:
uv run pytest <target> -v --tb=short 2>&1 | tail -40
Step 2: Diagnose Root Cause
Common failure patterns:
| Pattern | Root Cause | Fix |
|---|---|---|
ModuleNotFoundError |
Import path changed | Update import |
AttributeError: mock |
Mock target wrong | Match import path |
AssertionError |
Expected value drift | Update assertion |
TypeError: __init__ |
Constructor changed | Update call site |
FileNotFoundError |
Fixture path wrong | Use tmp_path |
Step 3: Apply Fix and Re-run
Apply the fix, then re-run the test. If it still fails, diagnose again with the new error. Repeat up to 3 times.
uv run pytest <target> -v --tb=short
Step 4: Report
After fixing (or exhausting 3 attempts), report:
## Fix Test Results
**Tests Fixed:** X/Y | **Attempts Used:** Z/3
### Fixed
| Test | Root Cause | Fix Applied |
|------|------------|-------------|
### Still Failing (if any)
| Test | Error | Attempts | Notes |
|------|-------|----------|-------|
Follow-Up
After presenting results, offer:
- "Want me to generate missing tests for the fixed module?"
- "Should I check for similar failures elsewhere?"
- "Want a deeper look at the root cause?"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 84 lines · 47 tokens per session scan A f0608ccfc642
fix-test is a skill published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 574 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
module-regression
Govern cross-module regression in large repositories with a REGRESSION.md ledger that records each module's downstream consumers and executable acceptance command. After a change, run the changed module and every affected downstream command, and use observed exit codes as regression evidence under the project's…
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
fix-failing-tests
Diagnose a failing test in the googleapis/mcp-toolbox repo and land a fix by reasoning from the actual error: read the failure, reproduce it, shrink it until the cause is forced into the open, then fix the cause. Use this whenever a test or CI job is red, a build breaks after a change, many packages fail at once, or a…
credit-note-fixer
Fix the tiny credit-note formatting bug and rerun the exact targeted test command.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…