testcase SKILL.md skillA

testcase from xtieume/testcase is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add xtieume/testcase/testcase@git:20261006.db7fa20

Pins git:20261006.db7fa20 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
xtieume/testcase
Path
.agents/skills/testcase/SKILL.md
Versions recorded
7
Latest version
git:20261006.db7fa20, committed Oct 6, 2026
First version recorded
Sep 1, 2026
Size
16,501 bytes
Repository stars
5
License
MIT

Generate or review test cases from requirements, specs, tickets, UI descriptions, API specs, Figma designs, or code changes, then implement the automatable ones as runnable tests in the repo's own framework. Also validates a build against its design and files reproducible bug reports from what fails. Use whenever the user asks to write, create, generate, implement, review, improve, or check test cases, to compare a screen against its Figma design, or to write up a bug. Runs a mandatory…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Test Case Generator & Anti-Miss Review

You are a senior QA engineer. The objective is not case count:

> **Understand the behavior, identify risks, explore systematically, minimize missed cases.**

Never stop at the happy paths.

## Quick start

| Ask | What happens |
| --- | ------------ |
| "write test cases for <requirement>" | Full workflow: coverage map → cases → adversarial second pass → lint |
| "review these test cases" | `references/review-mode.md`, then the same second pass over the existing table |
| "does this screen match the Figma?" | `references/design-validation.md` — the frame must be named, approved and mapped first; discrepancies then become `D<n>` rows in the same table |
| "write up this bug" | `references/bug-report.md` — the judgement your tracker's form cannot check |
| "implement the automatable ones" | Step 7 only, against an existing table |

Deliverable is `paths.testcases` (`.testcases/runs/<id>/testcase/testcases.md`) plus
whatever ships as runnable tests. Editing that table invalidates proof; put it in the repo
only if the user names a path. The run is not finished until `summarize.py` exits clean (step 6).

## Select the persistent run
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add xtieume/testcase/testcase@sha256:041e6c22a2cc4588

The line at the top of this page pins the label git:20261006.db7fa20, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_tcxrc6uaia7ty6rk.svg)](https://markdownregistry.com/a/art_tcxrc6uaia7ty6rk)

6 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 7 versions of this file, between Sep 1, 2026 and Oct 6, 2026, about one every 6 days.

versioncommittedcommitsizeaudit
git:20261006.db7fa20 latest2026-10-06 db7fa20 16,501 BA view · diff
git:20260923.ed0aea42026-09-23 ed0aea4 15,787 BA view · diff
git:20260921.c7eb2e92026-09-21 c7eb2e9 13,600 BA view · diff
git:20260919.ebd4b452026-09-19 ebd4b45 11,964 BA view · diff
git:20260916.792c5c72026-09-16 792c5c7 11,261 BA view · diff
git:20260908.7a5acfd2026-09-08 7a5acfd 9,654 BA view · diff
git:20260901.a0394082026-09-01 a039408 9,121 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the 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 (16501 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

xtieume/testcase · 5 stars · license MIT · pushed 2026-10-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_tcxrc6uaia7ty6rk
GET https://markdownregistry.com/api/v1/resolve?ref=xtieume/testcase/testcase
GET https://markdownregistry.com/api/v1/blob/041e6c22a2cc4588fcaea9a0cedcfb85a93ef2255986c2f546e0196f83518ed4

Your AI assistant 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.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from xtieume/testcase

docs-review SKILL.md skill
xtieume/testcase · .agents/skills/docs-review/SKILL.md · Use when the user asks to review or audit documentation, check whether docs cover a spec, build a requirements…
git:20261006.db7fa20 · audit A · 5 stars
goalrun SKILL.md skill
xtieume/testcase · .agents/skills/goalrun/SKILL.md · Use when a user wants work driven to completion or wants to know whether it truly is complete — "build X and don't stop…
git:20261006.db7fa20 · audit A · 5 stars
normalize SKILL.md skill
xtieume/testcase · .agents/skills/normalize/SKILL.md · Rewrites a casual, rambling everyday prompt into a compact engineering prompt — structured sections, imperative…
git:20260923.288e78f · audit A · 5 stars
playwright-cdp SKILL.md skill
xtieume/testcase · .agents/skills/playwright-cdp/SKILL.md · Use when pulling a requirement out of Notion or Slack into local markdown — body, every comment, and the attachments —…
git:20260923.6a5e63b · audit B · 5 stars

Every file in xtieume/testcase

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