Back to prompt library
Prompt libraryChat Prompt

CI Failure Triage Chat

Triage a CI failure by separating changed-file failures, environment failures, flaky tests, and next command.

CITestingEngineering
Preview

Chat Prompt

Recommended model

GPT-5.3 Codex

Output format

CI failure triage

Preview

Chat Prompt

chat thread

prompts:check passes, but i18n:check fails after generated message files changed in the working tree.

Changed-file failure: inspect locale JSON shape first. Environment failure: not likely if prompts:check passed. Flaky test: unlikely for deterministic i18n:check. Next command: run i18n:generate, then i18n:check again. Do not do: revert generated files without understanding the source mismatch.

Output

Changed-file failure / environment failure / flaky test / next command / do-not-do note

Triage a CI failure by separating changed-file failures, environment failures, flaky tests, and next command.

Full prompt

CI Failure Triage Chat

Triage a CI failure by separating changed-file failures, environment failures, flaky tests, and next command.

Recommended model: GPT-5.3 CodexOutput format: CI failure triage
Full prompt
Chat Prompt
You are an engineer triaging CI output after a content or code change. Turn the provided notes into a practical review that a team can act on. Return the answer with: Changed-file failure, environment failure, flaky test, next command, do-not-do note. Ground every claim in the provided notes. Mark missing facts instead of inventing them.

Usage notes

Paste the real notes, constraints, and source material. Keep private data out unless it is necessary for the review.

Prompt FAQ

Before you use this prompt

Quick checks for inputs, model fit, and how to adapt the template without weakening the result.

When should I use CI Failure Triage Chat?

Triage a CI failure by separating changed-file failures, environment failures, flaky tests, and next command. Use it when you already have notes, constraints, or a rough draft and need a structured next step a team can review.

What should I include before running it?

Include the source material, audience, constraints, key facts, and boundaries the answer must not invent. The output is organized as Changed-file failure / environment failure / flaky test / next command / do-not-do note.

Thread preview

prompts:check passes, but i18n:check fails after generated message files changed in the working tree.
Changed-file failure: inspect locale JSON shape first. Environment failure: not likely if prompts:check passed. Flaky test: unlikely for deterministic i18n:check. Next command: run i18n:generate, then i18n:check again. Do not do: revert generated files without understanding the source mismatch.

Output

Changed-file failure / environment failure / flaky test / next command / do-not-do note

More prompts in this mode

chat thread

We want to build an AI assistant for small ecommerce teams that turns product photos into campaign assets.

Problem hypothesis: small ecommerce teams lose time turning raw product photos into channel-ready campaign assets. Riskiest assumptions: photo quality is high enough, teams trust AI asset variation, and review time is the real bottleneck. Research questions: who owns campaign asset creation, where revisions stall, and what quality bar blocks publishing. Validation plan: interview 5 operators, test 3 prompt-led asset flows, and compare time-to-first-approved asset. Decision gate: continue only if teams can reach a publishable draft faster than their current workflow.

chat thread

We are exploring a new AI notes product for solo consultants. Help me turn this into a research brief.

Objective: define whether solo consultants need an AI notes workspace or a lighter client-follow-up layer. Working assumptions: they already capture notes, but synthesis and next-step drafting are inconsistent. Audience: solo consultants with recurring client calls and limited operations support. Key questions: which notes become billable work, what gets lost after calls, and where CRM tools feel too heavy. Research plan: run 6 interviews, review 10 recent call-note workflows, and test one follow-up brief prototype.

chat thread

Here is the outline for our AI product landing page. Tell me what is unclear before we design it.

Core promise: visible, but still framed as a feature rather than a concrete user outcome. Unclear point: the page does not explain who gets value first or what workflow changes after signup. example gap: add before-after examples, model output samples, and one short trust signal near the hero. CTA issue: the primary action appears after too much explanation; move a use-oriented CTA closer to the quick-use section. Revision plan: sharpen the hero, add outcome cards, then rewrite objections before polishing visuals.