Skills momentic-result-classification
📦

momentic-result-classification

Content revision r1 Safe ⚙️ External commands🌐 Network access

Classify Momentic Test Run Failures

Test failures can hide their true cause behind later errors or retries. This skill investigates Momentic run evidence and produces a precise classification.

Supports: Claude Codex Code(CC)
🥉 78 Bronze

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "momentic-result-classification" from https://skillstore.io/skills/momentic-ai-momentic-result-classification.md and its manifest at https://skillstore.io/api/skills/momentic-ai-momentic-result-classification/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/momentic-ai-momentic-result-classification.md Signed manifest GET /api/skills/momentic-ai-momentic-result-classification/manifest Signed lockfile GET /api/skills/momentic-ai-momentic-result-classification/lockfile

Test it

Using "momentic-result-classification". Classify a run where a row action succeeded, but the expected editor never opened.

Expected outcome:

Reasoning: The row action was the earliest divergence. The screenshot stayed on the parent page, so the later title assertion checked unrelated text. Category: BUG. Recoverable: NON_RECOVERABLE. Confidence: high.

Using "momentic-result-classification". Review a run where a broad text assertion passed before typing occurred in the wrong field.

Expected outcome:

Reasoning: The assertion did not prove the intended page state. A more specific assertion and target can prevent recurrence. Category: TEST_AUTHORSHIP. Recoverable: RECOVERABLE. Confidence: high.

Using "momentic-result-classification". Explain a run that failed because a required upload file was unavailable.

Expected outcome:

Reasoning: The required file was missing before the picker action, and the test cannot create it. Category: TEST_SETUP. Recoverable: NON_RECOVERABLE. Confidence: high.

Security Audit

Safe
v1 • 8/22/2026 Open versioned report

All 58 static findings are false positives caused by Markdown backticks, code fences, ordinary test-analysis prose, and a documented Momentic run-link template. The skill uses expected Momentic MCP tools, and no command execution, system reconnaissance, prompt injection, or unauthorized network behavior is present.

1
Files scanned
233
Lines analyzed
0
Review items
0
False positives ignored

Risk Factors

⚙️ External commands (44)
SKILL.md:21 SKILL.md:23 SKILL.md:25 SKILL.md:27 SKILL.md:29 SKILL.md:35 SKILL.md:51 SKILL.md:66 SKILL.md:68-74 SKILL.md:74-78 SKILL.md:78-92 SKILL.md:92-94 SKILL.md:94 SKILL.md:110 SKILL.md:114 SKILL.md:126-137 SKILL.md:137 SKILL.md:141 SKILL.md:142-143 SKILL.md:143-149 SKILL.md:149 SKILL.md:161 SKILL.md:169-171 SKILL.md:171-175 SKILL.md:175-177 SKILL.md:177 SKILL.md:178 SKILL.md:189-191 SKILL.md:191-193 SKILL.md:193-200 SKILL.md:200 SKILL.md:201-204 SKILL.md:204-209 SKILL.md:209-213 SKILL.md:213-214 SKILL.md:214-215 SKILL.md:215-221 SKILL.md:221-222 SKILL.md:222-223 SKILL.md:223-224 SKILL.md:224 SKILL.md:226-228 SKILL.md:228-230 SKILL.md:230-232
🌐 Network access (1)
SKILL.md:201
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
Audited by: codex
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/momentic-ai-momentic-result-classification/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/momentic-ai-momentic-result-classification/security.svg)](https://skillstore.io/skills/momentic-ai-momentic-result-classification?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/momentic-ai-momentic-result-classification?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/momentic-ai-momentic-result-classification/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/momentic-ai-momentic-result-classification.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

momentic-ai. (2026). momentic-result-classification security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/momentic-ai-momentic-result-classification/audits/1

BibTeX citation

@techreport{momentic-ai-momentic-ai-momentic-result-classification-2026, author = {momentic-ai}, title = {momentic-result-classification security audit report (audit version 1)}, institution = {Skillstore}, year = {2026}, number = {1}, url = {https://skillstore.io/skills/momentic-ai-momentic-result-classification/audits/1}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "momentic-result-classification security audit report (audit version 1)" version: "unspecified" type: report authors: - name: "momentic-ai" date-released: "2026-08-22" url: "https://skillstore.io/skills/momentic-ai-momentic-result-classification/audits/1" identifiers: - type: other value: "skillstore:momentic-ai-momentic-result-classification:audit:1" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium
55
Architecture
85
Maintainability
87
Content
65
Community
91
Spec Compliance

What You Can Build

Triage a failed test run

Find the earliest divergence and classify the failure using direct run evidence.

Investigate intermittent failures

Compare attempts and past runs to distinguish consistent defects from temporary conditions.

Review release test failures

Summarize root causes, recoverability, and confidence for failed end-to-end checks.

Try These Prompts

Classify one failed run 
Investigate Momentic run [run ID]. Identify the earliest divergence, classify the failure, determine recoverability, and explain the evidence.
Explain a failure 
Explain why Momentic run [run ID] failed. Trace backward from the final error and cite the screenshots, URLs, or step results that prove the cause.
Compare with previous runs 
Compare Momentic run [current run ID] with relevant earlier runs on the same branch. Determine what changed and provide the formal classification.
Analyze retries and recovery 
Analyze every attempt and recovered child step in Momentic run [run ID]. Identify hidden partial failures, broken postconditions, category, recoverability, and confidence.

Best Practices

  • Inspect the current run before using historical results.
  • Verify causal claims with screenshots, step results, URLs, DOM data, or traces.
  • Match past runs by branch and test version whenever possible.

Avoid

  • Do not classify only from the final failing assertion.
  • Do not label a single failure as flaky without comparable evidence.
  • Do not infer overlays, page states, or application changes without direct evidence.

Frequently Asked Questions

What data does this skill need?
It needs a Momentic run identifier or supplied run details, plus access to relevant Momentic MCP tools.
Can it compare previous runs?
Yes. It can inspect relevant earlier runs, attempts, screenshots, and matching step results.
Does it automatically save the classification?
It can submit the final classification through Momentic after the investigation is complete.
Can it identify flaky tests?
It can identify intermittent behavior only when comparable runs show the same test and application behavior.
What categories can it return?
It uses the categories defined by Momentic, including application changes, bugs, test authorship, setup, infrastructure, Momentic issues, and other.
Can it fix the failed test?
No. It can explain whether a test update may recover the failure, but it does not edit tests or application code.

Developer Details

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/momentic-ai/skills/tree/88379b4443b88b1f6c5a0b52b476030bc95d341e/skills/momentic-result-classification

Ref

a740049399b99f93094598d14138485f301898d6

Maintenance freshness

8/22/2026

Usage

1 downloads · 0 views

File structure

📄 SKILL.md