fastdeer3312-g22t0 GitHub avatar

prompt-regression-pack

fastdeer3312-g22t0

Prompt Regression Pack is a skill for catching prompt regressions by freezing golden inputs, defining must/must_not constraints, and generating drift reports and optional CI pseudo-code.

Stars

4

7-day growth

No data

Forks

1

Open issues

0

License

MIT

Last updated

2026-07-30

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It turns prompt quality into a regression-testable process with versioned golden inputs, machine-checkable constraints, and a drift table, so prompt edits can be safely gated before shipping.

Who it is for

  • LLM application developers who edit system or template prompts
  • Prompt engineers tracking format or policy drift
  • CI/CD practitioners maintaining prompt regression checks
  • Teams shipping prompt changes in structured workflows

Use cases

  • Gate every system or template prompt edit with golden-input regression tests
  • Run drift checks on prompts/** changes in CI
  • Track format and policy drift across prompt versions
  • Generate a gold case set plus constraint catalog before release

Strengths

  • Freezes golden user inputs against versioned prompts
  • Enforces machine-checkable must/must_not constraints
  • Produces drift tables and optional CI pseudo-code
  • Offers configurable options for language, size, check type, CI, and depth

Considerations

  • Prompt-scoped only; not a full multi-tool agent capability suite
  • Not designed for one-off creative chat or jailbreak exploit libraries
  • CI support may be pseudo-code or notes depending on the ci option

README quick start

Prompt Regression Pack

Golden inputs, expected constraints, drift table, and CI pseudo-code — catch prompt regressions before ship.

中文简介: 提示词回归包(金标输入、期望约束、漂移检测表、CI 伪代码)。 — 详见 README.zh.md.

What this skill does

  • Freezes golden user inputs against a versioned prompt
  • Defines machine-checkable must / must_not constraints
  • Produces a drift table vs baseline and optional CI pseudo-code
  • Stays prompt-scoped (not a full multi-tool agent suite)

Install

npx skills add / --skill prompt-regression-pack

Local monorepo: skills/prompt-regression-pack/.

Options

OptionValuesDefault
langen · zh · bilingualen
size12 · 25 · 5025
checkconstraints · exact · hybridconstraints
cinone · pseudo · github-actionspseudo
depthlite · standard · strictstandard

When to use

UseDon't
Gate every system/template prompt editOne-off creative chat
CI on prompts/** changesFull agent capability suite only
Track format/policy driftJailbreak exploit libraries

Deliverable

Gold case set + constraint catalog + drift table + CI notes.

See SKILL.md.

Example

../../output/samples/prompt-regression-pack-example-01.md

License

MIT — see LICENSE.

Related repositories

Similar projects matched by category, topics, and programming language.

MoonshotAI
Featured
MoonshotAI GitHub avatar

Kimi-K3

Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.

AI & Machine LearningAI Agents
3,348
xuchonglang
Featured
xuchonglang GitHub avatar

investing-for-beginners

A structured investing guide for Chinese beginners covering US stocks, options, and cryptocurrency, with focus on foundational concepts and risk awareness.

Blockchain & Web3
2,739
Krishnagangwal
Featured
Krishnagangwal GitHub avatar

CS-Fundamentals

A curated collection of Computer Science fundamentals (PDFs, notes, cheatsheets, interview question banks) for placement preparation, covering seven core subjects plus general resources.

Data & DatabasesDatabases & Storage
2,326