prompt-engineer-toolkit
Turns marketing prompts into tested, versioned production assets: A/B prompt evaluation against structured test cases, immutable prompt version history with diffs, ready-to-use marketing prompt templates (ad copy, email campaigns, social posts, landing pages, SEO meta), and an LLM-governance playbook for marketing teams (claim discipline, disclosure rules, human-review gates). Use when a marketing team relies on AI-generated content and needs prompt quality to be measurable and safe — or when the user mentions 'prompt engineering,' 'improve my prompts,' 'prompt templates,' 'prompt versioning,' 'AI content workflow,' or 'AI governance for marketing.'
- License 许可
- MIT
- 最近更新
- 2026-08-25
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- prompt-engineer-toolkit
- license
- MIT
- metadata
- { "author": "Alireza Rezvani", "updated": 1772755200000, "version": "1.0.0", "category": "marketing" }
- description
- Turns marketing prompts into tested, versioned production assets: A/B prompt evaluation against structured test cases, immutable prompt version history with diffs, ready-to-use marketing prompt templates (ad copy, email campaigns, social posts, landing pages, SEO meta), and an LLM-governance playbook for marketing teams (claim discipline, disclosure rules, human-review gates). Use when a marketing team relies on AI-generated content and needs prompt quality to be measurable and safe — or when the user mentions 'prompt engineering,' 'improve my prompts,' 'prompt templates,' 'prompt versioning,' 'AI content workflow,' or 'AI governance for marketing.'
03 SKILL.md 正文
Prompt Engineer Toolkit
Overview
Use this skill to move prompts from ad-hoc drafts to production assets with repeatable testing, versioning, and regression safety. It emphasizes measurable quality over intuition. Apply it when launching a new LLM feature that needs reliable outputs, when prompt quality degrades after model or instruction changes, when multiple team members edit prompts and need history/diffs, when you need evidence-based prompt choice for production rollout, or when you want consistent prompt governance across environments.
Core Capabilities
- A/B prompt evaluation against structured test cases
- Quantitative scoring for adherence, relevance, and safety checks
- Prompt version tracking with immutable history and changelog
- Prompt diffs to review behavior-impacting edits
- Reusable prompt templates and selection guidance
- Regression-friendly workflows for model/prompt updates
Key Workflows
1. Run Prompt A/B Test
Prepare JSON test cases and run:
python3 scripts/prompt_tester.py \
--prompt-a-file prompts/a.txt \
--prompt-b-file prompts/b.txt \
--cases-file testcases.json \
--runner-cmd 'my-llm-cli --prompt {prompt} --input {input}' \
--format text
Input can also come from stdin/--input JSON payload.
2. Choose Winner With Evidence
The tester scores outputs per case and aggregates:
- expected content coverage
- forbidden content violations
- regex/format compliance
- output length sanity
Use the higher-scoring prompt as candidate baseline, then run regression suite.
3. Version Prompts
# Add version
python3 scripts/prompt_versioner.py add \
--name support_classifier \
--prompt-file prompts/support_v3.txt \
--author alice
# Diff versions
python3 scripts/prompt_versioner.py diff --name support_classifier --from-version 2 --to-version 3
# Changelog
python3 scripts/prompt_versioner.py changelog --name support_classifier
4. Regression Loop
- Store baseline version.
- Propose prompt edits.
- Re-run A/B test.
- Promote only if score and safety constraints improve.
Script Interfaces
python3 scripts/prompt_tester.py --help- Reads prompts/cases from stdin or
--input - Optional external runner command
- Emits text or JSON metrics
- Reads prompts/cases from stdin or
python3 scripts/prompt_versioner.py --help- Manages prompt history (
add,list,diff,changelog) - Stores metadata and content snapshots locally
- Manages prompt history (
Pitfalls, Best Practices & Review Checklist
Avoid these mistakes:
- Picking prompts from single-case outputs — use a realistic, edge-case-rich test suite.
- Changing prompt and model simultaneously — always isolate variables.
- Missing
must_not_contain(forbidden-content) checks in evaluation criteria. - Editing prompts without version metadata, author, or change rationale.
- Skipping semantic diffs before deploying a new prompt version.
- Optimizing one benchmark while harming edge cases — track the full suite.
- Model swap without rerunning the baseline A/B suite.
Before promoting any prompt, confirm:
- [ ] Task intent is explicit and unambiguous.
- [ ] Output schema/format is explicit.
- [ ] Safety and exclusion constraints are explicit.
- [ ] No contradictory instructions.
- [ ] No unnecessary verbosity tokens.
- [ ] A/B score improves and violation count stays at zero.
References
- references/prompt-templates.md — 6 production marketing templates (ad copy, email sequence, social repurposing, landing sections, SEO meta, brand-voice rewrite) plus generic building blocks; each written to be graded by
prompt_tester.py - references/technique-guide.md — technique-selection table for marketing tasks + the LLM-governance stack for marketing teams (claim discipline, disclosure rules, data boundaries, human-review gates)
- references/evaluation-rubric.md — mechanical scoring weights, acceptance gates, marketing quality dimensions, test-suite design, and eval anti-patterns
- README.md
Evaluation Design
Each test case should define:
input: realistic production-like inputexpected_contains: required markers/contentforbidden_contains: disallowed phrases or unsafe contentexpected_regex: required structural patterns
This enables deterministic grading across prompt variants.
Versioning Policy
- Use semantic prompt identifiers per feature (
support_classifier,ad_copy_shortform). - Record author + change note for every revision.
- Never overwrite historical versions.
- Diff before promoting a new prompt to production.
Rollout Strategy
- Create baseline prompt version.
- Propose candidate prompt.
- Run A/B suite against same cases.
- Promote only if winner improves average and keeps violation count at zero.
- Track post-release feedback and feed new failure cases back into test suite.
04 同仓库更多 Skills
webmcpify
Make a web app agent-ready — propose a WebMCP tool manifest, integrate, verify in a real browser, heal; unrelated code stays untouched. Use for "webmcpify", "add WebMCP", or "expose app actions to AI agents".
vardoger-analyze
Use when the user asks to personalize the GitHub Copilot CLI assistant, adapt Copilot to their style, use vardoger, or analyze their Copilot CLI conversation history. Reads the local session directory at `~/.copilot/session-state/`, extracts recurring preferences and conventions, and writes a fenced personalization block into `~/.copilot/copilot-instructions.md`. Runs entirely on the user's machine via the local `vardoger` CLI (`pipx install vardoger`); no network calls and no uploads. Triggers: 'personalize my copilot', 'analyze my copilot history', 'tailor copilot to me', 'run vardoger', 'update my copilot instructions from history', 'make copilot learn my style'.
transloadit-media-processing
Process media files (video, audio, images, documents) using Transloadit. Use when asked to encode video to HLS/MP4, generate thumbnails, resize or watermark images, extract audio, concatenate clips, add subtitles, OCR documents, or run any media processing pipeline. Covers 86+ processing robots for file transformation at scale.
terraform-azurerm-set-diff-analyzer
Analyze Terraform plan JSON output for AzureRM Provider to distinguish between false-positive diffs (order-only changes in Set-type attributes) and actual resource changes. Use when reviewing terraform plan output for Azure resources like Application Gateway, Load Balancer, Firewall, Front Door, NSG, and other resources with Set-type attributes that cause spurious diffs due to internal ordering changes.
technical-job-search
Use this skill when a software engineer asks for help with job search tasks: parsing or analyzing a job description, tailoring a CV/resume, writing a cover letter, evaluating a job offer, or drafting a post-interview follow-up email. Do not activate for general career advice unrelated to an active job search action.
steno-mode
Shorthand-first response compression that cuts ~40% of response tokens while preserving technical precision and exact literals. Use when the user says "steno mode", "shorthand mode", "compressed responses", "token reduction", "brief structured output", or invokes /steno. Supports four compression levels: lite, brief, court, machine. Do not trigger for requests needing polished prose such as onboarding/tutorial content, stakeholder or customer-facing copy, or teaching-focused explanations.