regression SKILL.md skillA
regression from drunkendealer/claude-code-qa-cycle is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add drunkendealer/claude-code-qa-cycle/regression@git:20261026.41d4c58Pins git:20261026.41d4c58 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- drunkendealer/claude-code-qa-cycle
- Path
skills/regression/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261026.41d4c58, committed Oct 26, 2026
- First version recorded
- Oct 4, 2026
- Size
- 16,045 bytes
- Repository stars
- 3
- License
- MIT
Post-feature verification gate — phase 1 reviews the code (bugs, pitfalls, code smells), phase 2 plays manual tester — it builds and runs the project's test suite on every platform, walks the blast radius, audits against the platform bar, and optionally drives an emulator, simulator or browser when a finding needs the thing running. Auto-detects the feature from git and the platform or area from the repo, so it works after a context compaction. Read-only report with a ship/fix verdict, then…
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
# Regression Run this when a feature is **done** and you want to know whether it's safe to ship. Two phases, one report: 1. **Code** — bugs, pitfalls, code smells in what changed. 2. **Regression session** — build it, run its suite, then find what a manual tester would break and whether the result follows the platform's UI/UX bar. Off-platform work (backend, CLI, library, tooling, data) is judged against the behavior that already exists instead. Built to be invoked **after a context compaction**: it reconstructs the feature from git, not from the conversation. It never assumes you still remember what was in the diff. **Read-only until the last step.** The report ends with a verdict and an offer to apply fixes; nothing is edited before you say so. Building, testing and driving the app are part of the pass — none of them edit the source tree. ## Relationship to the other skills | Want | Use | |---|---| | Just the code pass | `/code-review` | | Just the tester pass | `/manual-qa` | | Fix duplication / dead code / idioms | `/clean-up` | | **The full post-feature gate** | **this skill** | …
Read the whole file at its exact version.
How to install
mdr add drunkendealer/claude-code-qa-cycle/regression@sha256:2a22d0d4d94153c7The line at the top of this page pins the label git:20261026.41d4c58, 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.
[](https://markdownregistry.com/a/art_srclqs7nx4xgfb5s)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Oct 4, 2026 and Oct 26, 2026, about one every 6 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261026.41d4c58 latest | 2026-10-26 | 41d4c58 | 16,045 B | A | view · diff |
| git:20261026.35c77af | 2026-10-26 | 35c77af | 16,045 B | A | view · diff |
| git:20261004.0a0c331 | 2026-10-04 | 0a0c331 | 16,097 B | A | view · diff |
| git:20261004.c19f39a | 2026-10-04 | c19f39a | 16,007 B | A | view · diff |
| git:20261004.74656e9 | 2026-10-04 | 74656e9 | 16,020 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (16045 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
drunkendealer/claude-code-qa-cycle · 3 stars · license MIT · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_srclqs7nx4xgfb5s GET https://markdownregistry.com/api/v1/resolve?ref=drunkendealer/claude-code-qa-cycle/regression GET https://markdownregistry.com/api/v1/blob/2a22d0d4d94153c78ade2410f4e2c21cd17b3edb4f0d81b621e2271f44ccfc5e
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.