test-idea-rewriting

test-idea-rewriting is a skill for Claude Code from summarybotng/summarybot-ng. It costs 51 tokens per session (1,661 once invoked), scanned A, original, MIT.

A rewriting method for turning vague test descriptions such as “Verify X” into active steps with a clear trigger and observable result. It preserves the original test metadata and checks that vague patterns are gone.

In plain words
What is it for?
Use it to rewrite test cases, identify vague wording, assign suitable action verbs, and produce clearer descriptions for manual or automated testing.
Why use it?
Unclear test ideas are difficult to implement and review consistently. Describing what to do and what to observe makes each test more specific and actionable.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to rewrite test cases, identify vague wording, assign suitable action verbs, and produce clearer descriptions for manual or automated testing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/summarybotng/summarybot-ng/test-idea-rewriting
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add summarybotng/summarybot-ng --skill test-idea-rewriting
Clone the repo
git clone --depth 1 https://github.com/summarybotng/summarybot-ng

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for test-idea-rewriting

README.md
[![agentmods](https://agentmods.dev/badge/skills/summarybotng/summarybot-ng/test-idea-rewriting/github.svg)](https://agentmods.dev/skills/summarybotng/summarybot-ng/test-idea-rewriting)
Your own site
<a href="https://agentmods.dev/skills/summarybotng/summarybot-ng/test-idea-rewriting"><img src="https://agentmods.dev/badge/skills/summarybotng/summarybot-ng/test-idea-rewriting/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for test-idea-rewriting

Your own site · 80×15
<a href="https://agentmods.dev/skills/summarybotng/summarybot-ng/test-idea-rewriting"><img src="https://agentmods.dev/badge/skills/summarybotng/summarybot-ng/test-idea-rewriting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,661 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.01661
Opus 5 $0.00026 $0.00830
Sonnet 5 $0.00010 $0.00332
Haiku 4.5 $0.00005 $0.00166

Measured 5d ago against content hash fff4f1056446, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

test-idea-rewriting scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/test-idea-rewriting/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

Category Verbs Use When
Interaction Click, Type, Submit, Navigate, Scroll UI actions
Trigger Send, Inject, Force, Simulate, Load API/system actions
Measurement Measure, Time, Count, Profile Performance checks
State Set, Configure, Enable, Disable, Toggle Setup actions
Observation Confirm, Assert, Check, Observe Outcome verification

Common Transformations

Before After
Verify login works Submit valid credentials; confirm session created
Verify API returns 200 Send GET request; assert 200 response within 500ms
Verify error displays Trigger validation error; observe error message
Verify data saves Insert record; query database; confirm fields match
Verify performance Execute 100 requests; measure p99 < 200ms

Transformation Rules

Pattern Detection

/<td>Verify\s/gi     // HTML table cells
/^Verify\s/gim       // Line starts
/"Verify\s[^"]+"/gi  // Quoted strings

Transformation Categories

API/Network Tests
Input Pattern Output Pattern
Verify API returns X Send [METHOD] request; assert [STATUS] response
Verify endpoint accepts Y Post [PAYLOAD] to endpoint; confirm [RESPONSE]
Verify webhook fires Trigger [EVENT]; observe webhook received

Read the full file on GitHub · 230 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 230 lines · 51 tokens per session scan A fff4f1056446

Subscribe to this mod's changes

test-idea-rewriting is a skill published in the GitHub repository summarybotng/summarybot-ng (2 stars, last pushed 3mo ago), licensed MIT. It adds 51 tokens to every session and 1,661 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.