Home / fusengine / agents · plugins/prompt-engineer/skills/prompt-testing/SKILL.md · GitHub

prompt-testing skillA

prompt-testing is agent-read markdown (skill) from fusengine/agents: Use when comparing two prompt variants, defining quality/efficiency/robustness metrics, or deciding whether to adopt a challenger prompt over a baseline..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

<objective>
Prompt Testing runs A/B comparisons between prompt variants through a 5-step workflow: define the objective and metrics, prepare variants A/B and a test dataset, execute on the dataset, analyze and compare results, then decide. Metrics span three categories -- quality (accuracy, compliance, consistency, relevance), efficiency (input/output tokens, latency, cost), and robustness (edge-case handling, jailbreak resistance, error recovery) -- plus a UX category detailed in `metrics.md`.

The adoption decision is rule-based: adopt B if its accuracy is at least equal with acceptable token cost, consider B as a trade-off if accuracy improves >10% despite <20% token regression, otherwise keep A or iterate. Requires a minimum of 20 test cases with 15-20% edge cases for statistical significance.
</objective>

# Prompt Testing

Skill for testing, comparing, and measuring prompt performance.

## References

- [metrics.md](references/metrics.md) - Load when: defining or scoring Quality/Efficiency/Robustness/UX metrics with thresholds and calculation formulas
…

Read the whole file at its exact version.

How to install

Latest version
mdr add fusengine/agents/prompt-testing@git:20260729.3b91eed
Exact content
mdr add fusengine/agents/prompt-testing@sha256:b5a7158e738b3bef

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_x2th6gxl7syz55ae.svg)](https://markdownregistry.com/a/art_x2th6gxl7syz55ae)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260729.3b91eed latest2026-07-29 3b91eed 4,121 BA view · diff
git:20260705.ba8ee522026-07-05 ba8ee52 3,348 BA view · diff
git:20260705.8c2f9bc2026-07-05 8c2f9bc 3,346 BA view · diff
git:20260124.acdc9412026-01-24 acdc941 4,478 BA view · diff
git:20260122.f6bc08c2026-01-22 f6bc08c 4,445 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4121 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

fusengine/agents · 28 stars · license MIT · pushed 2026-09-24 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_x2th6gxl7syz55ae
GET https://markdownregistry.com/api/v1/resolve?ref=fusengine/agents/prompt-testing
GET https://markdownregistry.com/api/v1/blob/b5a7158e738b3bef603d91a96f4cd10127351c99d391ff3a911251c10111f461

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from fusengine/agents

agent-creator skill
fusengine/agents · plugins/ai-pilot/skills/agent-creator/SKILL.md · Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
git:20260904.5f1d30f · audit A · 28 stars
apex-methodology skill
fusengine/agents · plugins/ai-pilot/skills/apex-methodology/SKILL.md · Use when starting ANY development task -- feature, bug fix, refactor, hotfix (triggers: implement, create, build, fix…
git:20260729.3b91eed · audit A · 28 stars
brainstorming skill
fusengine/agents · plugins/ai-pilot/skills/brainstorming/SKILL.md · Use when creating a feature/component or adding functionality. Fires BEFORE APEX Analyze to refine requirements via…
git:20260904.5f1d30f · audit A · 28 stars
challenge skill
fusengine/agents · plugins/ai-pilot/skills/challenge/SKILL.md · Use before a root-cause, done/verified claim, irreversible action, or 2nd-time fix reaches the owner (APEX or plain…
git:20260729.3b91eed · audit A · 28 stars
code-quality skill
fusengine/agents · plugins/ai-pilot/skills/code-quality/SKILL.md · Use when validating code quality after modifications -- SOLID compliance, DRY duplication, linter errors, architecture…
git:20260729.3b91eed · audit A · 28 stars
elicitation skill
fusengine/agents · plugins/ai-pilot/skills/elicitation/SKILL.md · Use when an expert agent self-reviews and self-corrects code after the Execute phase, before sniper validation…
git:20260729.3b91eed · audit A · 28 stars
exploration skill
fusengine/agents · plugins/ai-pilot/skills/exploration/SKILL.md · Use when exploring an unfamiliar codebase -- architecture analysis, pattern detection, dependency mapping, rapid…
git:20260729.3b91eed · audit A · 28 stars
fuse-browser-usage skill
fusengine/agents · plugins/ai-pilot/skills/fuse-browser-usage/SKILL.md · Use when about to call any mcp__fuse-browser__* tool. Routes fetch/crawl/SERP vs live browser session vs screenshot…
git:20260729.3b91eed · audit A · 28 stars
modularize skill
fusengine/agents · plugins/ai-pilot/skills/modularize/SKILL.md · Use when converting existing code to modular architecture (Laravel, Next.js, React). Triggers: "modularize", "convert…
git:20260729.3b91eed · audit A · 28 stars
pr-summary skill
fusengine/agents · plugins/ai-pilot/skills/pr-summary/SKILL.md · Summarize current pull request with diff, comments, and changed files. Use when reviewing PRs or before merging.
git:20260729.3b91eed · audit A · 28 stars
react-effects-audit skill
fusengine/agents · plugins/ai-pilot/skills/react-effects-audit/SKILL.md · Use when auditing React or Next.js components for unnecessary or unsafe useEffect usage -- detects 9 anti-patterns from…
git:20260729.3b91eed · audit A · 28 stars
research skill
fusengine/agents · plugins/ai-pilot/skills/research/SKILL.md · Use when researching documentation, best practices, or complex technical investigations -- Context7 + Exa + Sequential…
git:20260729.3b91eed · audit A · 28 stars

Every file in fusengine/agents

Other files named prompt-testing

prompt-testing skill
naodeng/awesome-qa-skills · skills/en/testing-types/prompt-testing/SKILL.md · Use this skill when you need to test prompt behavior, regression risk, and output boundaries across versions; triggers…
git:20260915.27b248b · audit A · 230 stars
prompt-testing skill
joe-qai/qa-skills · prompt-testing/SKILL.md · Use this skill when you need to generate concrete test cases for LLM prompt quality, including instruction following…
git:20260915.bc5a8d6 · audit A · 25 stars

Browse by kind, by grade A, or by owner.