Auto-QA (QAMESH)

Trust Score 66/100

Project-level deterministic QA mesh (QAMESH) to plan, run, and release automated QA journeys and manage evidence and feedback.

triggers:qaqameshauto qaauto qa initauto qa run

GitHub SKILL.md

What it does

Auto-QA (QAMESH) supplies a structured QA mesh for projects: manifest-driven QA plans, deterministic run execution, evidence collection, redaction, and feedback generation. Implemented as a CLI template/harness for project integration.

When to use it

When you need reproducible project-scoped QA: creating Journey Packs, planning deterministic tests, running validation and evidence collection, or converting failed runs into repair feedback.

What's included

Scripts: template harnesses and CLI glue (template file shown; concrete installs include scripts).
References: templated manifests and guidance (has_references=false for template).
Instructions: command selection, guardrails for canary vs release, redaction and artifact policies.

Compatible agents

Code/CLI-capable agents (Gemini CLI, Claude Code, Codex).

Audit Summary

QAMESH auto-qa skill for the autopus-adk platform. It's a template file (.tmpl) providing CLI command selection guidance for QA orchestration — init, plan, run, release, coverage, evidence, and feedback workflows. No bundled scripts; purely instructional. The SKILL.md reads like a CLI man page with good guardrails (redaction fail-closed, untrusted evidence treatment) but relies entirely on an external antigravity-cli tool. Template placeholders ({{.ProjectName}}) are unprocessed.

Watch Out

Requires antigravity-cli platform which is niche
File is a .tmpl template, not a finalized SKILL.md
No actual scripts to execute — purely command guidance documentation
Korean-language section header mixed with English content

Notes

This is a well-intentioned QA orchestration skill with good security guardrails in its documentation. However, it's more of a CLI reference guide than an actionable agent skill. The .tmpl extension and unprocessed template variables suggest it may not be properly deployed. The niche platform dependency limits broad usefulness.

Information

Repository: wechat-publisher
Stars: 68

Trust Score

Overall66

Security88

Code Quality42

Architecture48

Usefulness35

Related Skills

Development Worktree

Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.

Readwise Reader Document Management

Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.

Bounty Hunter — Atlas

Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.

Junshi — Research Advisor

Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.

Full Stack Builder

End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.

ezBookkeeping API Tools

Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi

Feishu Voice Sender

Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.

Claw Bench

Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.

Back to Skills