Agent skill

Test Idea Rewriting

by proffesor-for-testing in proffesor-for-testing/agentic-qe

Transform passive 'Verify X' test descriptions into active, observable test actions.

MITAuto-check passed

Install Test Idea Rewriting

skills CLI
$ npx skills add proffesor-for-testing/agentic-qe --skill test-idea-rewriting -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install proffesor-for-testing/agentic-qe test-idea-rewriting --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/proffesor-for-testing/agentic-qe.git skills-src && mkdir -p .claude/skills && cp -r skills-src/assets/skills/test-idea-rewriting .claude/skills/test-idea-rewriting && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
test-idea-rewriting
GitHub stars
494
Token cost
~1.8k tokens
SKILL.md length
616 words
Files
1
Skills in repo
95
Repo updated
First seen
Licence
MIT

At a glance

Transform passive 'Verify X' test descriptions into active, observable test actions.

  • Works in 6 steps: DETECT all "Verify X" patterns via regex → IDENTIFY appropriate action verb category → TRANSFORM to "[ACTION] [trigger];… → …
  • Test ideas lack specificity
  • SKILL.md covers Quick Reference Card, Transformation Rules, Action Verb Reference and Quality Validation, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Test Idea Rewriting is an agent skill from proffesor-for-testing/agentic-qe. Transform passive 'Verify X' test descriptions into active, observable test actions. Use when test ideas lack specificity, use vague language, or fail quality validation. Converts to action-verb format for clearer, more testable descriptions.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Agentic QE Fleet is an open-source AI-powered QA/QE platform designed for use with Coding Agents (works best with Claude Code) featuring specialized agents and skills to support… The licence is MIT.

When your agent uses it

  • Test ideas lack specificity
  • Use vague language
  • Fail quality validation

Example prompts

  • “Verify X”
  • “/test-idea-rewriting”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. DETECT all "Verify X" patterns via regex
  2. IDENTIFY appropriate action verb category
  3. TRANSFORM to "[ACTION] [trigger]; [OBSERVE] [result]" pattern
  4. PRESERVE all metadata (IDs, priorities, automation types)
  5. VALIDATE zero "Verify" patterns remain
  6. OUTPUT in same format as input

What it can do on your machine

Read from SKILL.md and the folder at commit 829d030. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are regex, javascript and typescript).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Test Idea Rewriting loads about 1.8k tokens when it runs. Until then it costs about 66 tokens; SKILL.md has 616 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~66
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from proffesor-for-testing/agentic-qe at commit 829d030, republished under its MIT licence (© proffesor-for-testing). 616 words, ~1,817 tokens.

Download SKILL.mdSave it as .claude/skills/test-idea-rewriting/SKILL.md (or your agent's skills folder).
name
test-idea-rewriting
description
Transform passive 'Verify X' test descriptions into active, observable test actions. Use when test ideas lack specificity, use vague language, or fail quality validation. Converts to action-verb format for clearer, more testable descriptions.
category
test-design
priority
medium
tokenEstimate
800
agents
qe-test-idea-rewriter
implementation_status
optimized
optimization_version
1
last_optimized
2026-01-17
quick_reference_card
true
tags
test-ideas, rewriting, action-verbs, quality, transformation

Test Idea Rewriting

<default_to_action> When transforming test ideas:

  1. DETECT all "Verify X" patterns via regex
  2. IDENTIFY appropriate action verb category
  3. TRANSFORM to "[ACTION] [trigger]; [OBSERVE] [result]" pattern
  4. PRESERVE all metadata (IDs, priorities, automation types)
  5. VALIDATE zero "Verify" patterns remain
  6. OUTPUT in same format as input

Success Criteria: /<td>Verify\s/gi returns 0 matches </default_to_action>

Quick Reference Card

Transformation Pattern
[ACTION VERB] [specific trigger]; [OUTCOME VERB] [observable result]
Action Verb Quick Reference
CategoryVerbsUse When
InteractionClick, Type, Submit, Navigate, ScrollUI actions
TriggerSend, Inject, Force, Simulate, LoadAPI/system actions
MeasurementMeasure, Time, Count, ProfilePerformance checks
StateSet, Configure, Enable, Disable, ToggleSetup actions
ObservationConfirm, Assert, Check, ObserveOutcome verification
Common Transformations
BeforeAfter
Verify login worksSubmit valid credentials; confirm session created
Verify API returns 200Send GET request; assert 200 response within 500ms
Verify error displaysTrigger validation error; observe error message
Verify data savesInsert record; query database; confirm fields match
Verify performanceExecute 100 requests; measure p99 < 200ms

Transformation Rules

Pattern Detection
regex
/<td>Verify\s/gi     // HTML table cells
/^Verify\s/gim       // Line starts
/"Verify\s[^"]+"/gi  // Quoted strings
Transformation Categories
API/Network Tests
Input PatternOutput Pattern
Verify API returns XSend [METHOD] request; assert [STATUS] response
Verify endpoint accepts YPost [PAYLOAD] to endpoint; confirm [RESPONSE]
Verify webhook firesTrigger [EVENT]; observe webhook received
UI/UX Tests
Input PatternOutput Pattern
Verify button worksClick [BUTTON]; observe [EFFECT]
Verify form submitsFill [FIELDS]; submit form; confirm [RESULT]
Verify navigation worksClick [LINK]; observe [PAGE] loads
Data Tests
Input PatternOutput Pattern
Verify data savesInsert [RECORD]; query; confirm [MATCH]
Verify validation worksEnter [INVALID]; observe [ERROR]
Verify format acceptedSubmit [FORMAT]; confirm [PROCESSED]
Performance Tests
Input PatternOutput Pattern
Verify performance is goodExecute [LOAD]; measure [METRIC] < [THRESHOLD]
Verify scalabilityIncrease [USERS] to [N]; monitor [RESOURCE]
Verify timeout worksInject [DELAY]; confirm timeout after [TIME]

Action Verb Reference

Interaction Verbs
VerbWhen to UseExample
ClickUI element interactionClick "Submit" button
TypeText entryType "user@example.com"
SubmitForm completionSubmit registration form
NavigatePage changesNavigate to /settings
ScrollViewport movementScroll to page bottom
DragDrag-and-dropDrag file to upload zone
HoverMouse positioningHover over tooltip trigger
SelectDropdown/checkboxSelect "Admin" from role dropdown
Show full SKILL.md (263 more words)Show less
Trigger Verbs
VerbWhen to UseExample
SendHTTP requestsSend POST to /api/orders
InjectFault injectionInject 500ms latency
ForceState manipulationForce offline mode
SimulateEvent generationSimulate device rotation
LoadResource loadingLoad 50MB test file
ExecuteScript/commandExecute database migration
InvokeFunction/webhookInvoke payment callback
TriggerEvent firingTrigger scheduled job
Measurement Verbs
VerbWhen to UseExample
MeasureQuantitative checkMeasure response time
TimeDuration trackingTime page render
CountQuantity checkCount search results
ProfileResource analysisProfile CPU usage
BenchmarkComparisonBenchmark against v1.0
CaptureState recordingCapture network traffic
MonitorOngoing observationMonitor memory for 5 minutes
Observation Verbs
VerbWhen to UseExample
ConfirmBoolean checkConfirm user is logged in
AssertValue comparisonAssert total equals $99.99
CheckState verificationCheck cart has 3 items
ObserveBehavior watchingObserve spinner appears
ValidateRule complianceValidate email format
ExpectPredicted outcomeExpect redirect to /home
Verify (avoid)Use alternativesUse confirm/assert instead

Quality Validation

Pre-Transform Checks
  1. Count "Verify" patterns in input
  2. Identify context for each pattern
  3. Map to appropriate action verb category
Post-Transform Checks
  1. Regex validation: zero "Verify" matches
  2. Every test idea starts with action verb
  3. Each test includes observable outcome
  4. All metadata preserved unchanged
Validation Regex
javascript
// Must return 0 matches for success
const verifyPattern = /<td>Verify\s/gi;
const matches = content.match(verifyPattern);
if (matches && matches.length > 0) {
  throw new Error(`${matches.length} "Verify" patterns remain`);
}

Agent Integration

typescript
// Single file transformation
await Task("Rewrite Test Ideas", {
  inputFile: "assessment.html",
  outputFile: "assessment-rewritten.html",
  preserveFormatting: true
}, "qe-test-idea-rewriter");

// Batch transformation
await Task("Batch Rewrite", {
  inputDir: "./assessments/",
  outputDir: "./assessments-clean/",
  pattern: "*.html"
}, "qe-test-idea-rewriter");

Memory Namespace

aqe/rewriting/
├── transformations/*  - Transformation logs
├── patterns/*         - Learned patterns
└── vocabulary/*       - Custom verb mappings


Remember

Every test idea should be actionable. "Verify X works" tells you nothing about HOW to test. "[Action] X; [Observe] Y" gives clear steps and expected outcomes. Transform passive descriptions into active, observable tests.

© proffesor-for-testing, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in assets/skills/test-idea-rewriting of proffesor-for-testing/agentic-qe.

Open the folder on GitHubat commit 829d030

Compare with similar skills

Test Idea Rewriting next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Test Idea Rewriting compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Test Idea Rewriting this skillproffesor-for-testing/agentic-qe494—~1.8kAutomated safety check: PassMIT
TransformersK-Dense-AI/scientific-agent-skills48k1 repos~2.8kAutomated safety check: NotesApache-2.0
Duplicate Descriptionthedaviddias/Front-End-Checklist74k—~695Automated safety check: PassMIT
Idea Darwinsickn33/agentic-awesome-skills47k2 repos~1.1kAutomated safety check: PassMIT
Idea Refinementaddyosmani/agent-skills103k6 repos~2kAutomated safety check: PassMIT
Rewrite Plannexu-io/open-design100k—~511Automated safety check: PassApache-2.0

Similar skills

  • Transformers

    K-Dense-AI/scientific-agent-skills

    Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal tasks.

    48k GitHub starsUsed in 1 repo~2.8k tokens
    AI & LLM EngineeringAuto-check: notes
  • Duplicate Description

    thedaviddias/Front-End-Checklist

    A skill your agent uses when auditing a site's meta tag uniqueness, generating page-specific meta descriptions, or reviewing CMS templates that inject the same description globally.

    74k GitHub stars~695 tokensUpdated 2 days ago
    Marketing & SEOAuto-check passed
  • Idea Darwin

    sickn33/agentic-awesome-skills

    Darwinian idea evolution engine — toss rough ideas onto an evolution island, let them compete, crossbreed, and mutate through structured rounds to surface your strongest concepts.

    47k GitHub starsUsed in 2 repos~1.1k tokens
    Auto-check passed
  • Idea Refinement

    addyosmani/agent-skills

    Guides a conversation that takes a vague idea through divergent and convergent thinking and ends in a markdown one-pager covering scope and assumptions.

    103k GitHub starsUsed in 6 repos~2k tokens
    Agent WorkflowsAuto-check passed
  • Rewrite Plan

    nexu-io/open-design

    Author a long-running multi-file rewrite plan that subsequent patch-edit + diff-review + build-test stages will execute, with explicit ownership boundaries and patch-safety guarantees.

    100k GitHub stars~511 tokensUpdated today
    Frontend & DesignAuto-check passed
  • PR Description

    voyager-crew/voyager

    Write or rewrite a Voyager pull request description. An agent skill from voyager-crew/voyager.

    20k GitHub stars~182 tokensUpdated yesterday
    DevelopmentAuto-check passed

More from proffesor-for-testing/agentic-qe

All 95 skills in this repo
  • Contract Testing

    proffesor-for-testing/agentic-qe

    Consumer-driven contract testing for microservices using Pact, schema validation, API versioning, and backward compatibility testing.

    494 GitHub stars~1.8k tokensUpdated 4 days ago
    Auto-check passed
  • Mutation Testing

    proffesor-for-testing/agentic-qe

    Test quality validation through mutation testing, assessing test suite effectiveness by introducing code mutations and measuring kill rate.

    494 GitHub stars~1.7k tokensUpdated 4 days ago
    Auto-check passed
  • Performance Testing

    proffesor-for-testing/agentic-qe

    Profiles application performance under load using k6, Artillery, or JMeter to measure latency, throughput, and error rates.

    494 GitHub stars~2.4k tokensUpdated 4 days ago
    Auto-check passed
  • Code Review Quality

    proffesor-for-testing/agentic-qe

    Conduct context-driven code reviews focusing on quality, testability, and maintainability.

    494 GitHub starsUsed in 1 repo~1.9k tokens
    Auto-check passed
  • Security Testing

    proffesor-for-testing/agentic-qe

    Scans for security vulnerabilities including XSS, SQL injection, CSRF, and auth flaws using OWASP Top 10 methodology.

    494 GitHub stars~2.7k tokensUpdated 4 days ago
    Auto-check: notes
  • Database Testing

    proffesor-for-testing/agentic-qe

    Database schema validation, data integrity testing, migration testing, transaction isolation, and query performance.

    494 GitHub starsUsed in 1 repo~1.7k tokens
    Auto-check passed

Questions about Test Idea Rewriting

What does Test Idea Rewriting do?

Transform passive 'Verify X' test descriptions into active, observable test actions. Test Idea Rewriting is an agent skill from proffesor-for-testing/agentic-qe. Transform passive 'Verify X' test descriptions into active, observable test actions.

When should I use Test Idea Rewriting?

Test Idea Rewriting fits situations like: test ideas lack specificity; use vague language; fail quality validation.

How do I install Test Idea Rewriting in Claude Code?

Run `npx skills add proffesor-for-testing/agentic-qe --skill test-idea-rewriting -a claude-code`. Or copy the skill folder (assets/skills/test-idea-rewriting in proffesor-for-testing/agentic-qe) into .claude/skills/test-idea-rewriting in your project. Claude Code loads it when a task matches its description.

How do I install Test Idea Rewriting in Codex?

Run `npx skills add proffesor-for-testing/agentic-qe --skill test-idea-rewriting -a codex`. Or copy the skill folder (assets/skills/test-idea-rewriting in proffesor-for-testing/agentic-qe) into .agents/skills/test-idea-rewriting in your project. Codex loads it when a task matches its description.

Can I use Test Idea Rewriting in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add proffesor-for-testing/agentic-qe --skill test-idea-rewriting -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/test-idea-rewriting, .gemini/skills/test-idea-rewriting, .github/skills/test-idea-rewriting and .opencode/skills/test-idea-rewriting in your project.

What does Test Idea Rewriting need to run?

SKILL.md names no scripts, command-line tools or credentials: Test Idea Rewriting is instructions for the agent only.

Does Test Idea Rewriting access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Test Idea Rewriting safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Test Idea Rewriting use?

Test Idea Rewriting is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Test Idea Rewriting use?

About 1.8k tokens (SKILL.md is roughly 7.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Test Idea Rewriting?

Skills that share tags, products or a category with Test Idea Rewriting: Transformers (K-Dense-AI/scientific-agent-skills, 48k stars), Duplicate Description (thedaviddias/Front-End-Checklist, 74k stars), Idea Darwin (sickn33/agentic-awesome-skills, 47k stars) and Idea Refinement (addyosmani/agent-skills, 103k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Test Idea Rewriting?

proffesor-for-testing (a GitHub user) maintains it in proffesor-for-testing/agentic-qe, which has 494 GitHub stars. The repository holds 95 skills in this directory. The repository was last updated on October 4, 2026.

Source: proffesor-for-testing/agentic-qe on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.