Works with the AI Agents you already use
QA me
Risk-based software quality auditor that identifies testing gaps and builds a prioritized improvement strategy.
Free
QA me
Example session with this skill installed
Audit the current repository's Quality Assurance strategy. Look at the workflows and the tests to find gaps in our current approach.
- Read your context and instructions
- Compiled the qa me
I have completed the initial evidence collection by inspecting .github/workflows/ci.yml and the /tests/unit directory. I have separated observed facts from hypotheses regarding your quality coverage.
QA Assessment Findings
| Evidence Area | Observed Fact | Risk/Hypothesis | Priority |
|---|---|---|---|
| CI Pipeline | ci.yml triggers on push to main only. | Regression risk on feature branches; high exposure for broken builds. | High |
| Test Suite | 12 files found in /tests/unit, mostly mocking DB calls. | Integration gaps; business logic involving the actual database is untested. | Medium |
| Dependency Security | No npm audit or Snyk steps found in workflow. | Vulnerable packages may reach production unnoticed. | High |
| Architecture | auth-service.js has no corresponding test file. | High-harm area (Authentication) lacks automated verification. | Critical |
Decision Round 1: Critical Gaps
-
Evidence:
auth-service.jslacks tests whileuser-profile.jshas 100% coverage.
Why it matters: Authentication failure is high-harm. High coverage on low-risk profiles creates a false sense of security.
Proposed Approach: Prioritize integration tests for the auth flow over further unit tests for UI components.
Tradeoff: This requires setting up a test container or mock auth provider, increasing CI time by ~30s. -
Evidence: CI only runs on the
mainbranch.
Why it matters: Errors are caught late in the cycle, making them harder and more expensive to reverse.
Proposed Approach: Update workflow triggers to include pull requests.
Tradeoff: Increased GitHub Actions usage/cost.
Next steps
- Provide feedback on the proposed priority shift for the
auth-service. - Confirm if I should proceed with drafting the updated CI trigger configuration.
- Specify if there are internal docs regarding the database integration strategy.
Connects securely to your tools. The creator never sees your data.
About this skill
Testing silos and vanity coverage metrics often hide the actual risks in a software project. This skill audits your repository to find where quality practices don't match the potential for harm.
What it does
- Evidence collection scans your architecture, CI configs, and existing tests to separate facts from assumptions.
- Risk prioritization identifies gaps based on likely harm and exposure rather than generic checklists.
- Guided interview resolves unknowns through short, targeted rounds of questioning about trade-offs and constraints.
- Strategic mapping builds a prioritized list of improvements with concrete verification criteria.
- Constraint awareness acknowledges access limits and missing evidence without treating them as inherent defects.
How it works
- Inspection starts by analyzing your provided code, documentation, and pipeline configurations.
- Gap analysis identifies what is working and where evidence of quality is missing or contradictory.
- Decision rounds present you with specific risks, the evidence found, and proposed approaches for feedback.
- Finalization generates a summary of agreed improvements, deferred risks, and unresolved blockers.
Frameworks & tools
This skill is framework-agnostic. it works with any repository containing CI/CD yaml files, test suites (Jest, Pytest, Go test, etc.), and architecture documentation.
Why this beats prompting it yourself
Generic prompts often hallucinate requirements or demand 100% coverage. This skill uses a structured risk-based approach that cites specific file paths and forces a distinction between a test file's existence and actual runtime proof.
Use cases
- QA strategy review to align testing efforts with high-risk architectural components.
- Pre-implementation audit to agree on quality bars before starting a high-stakes feature.
- Legacy code discovery to find where documentation claims and test evidence diverge.
- CI/CD optimization to ensure pipeline checks actually validate the failures that matter.
Known limitations
The skill cannot execute code, install dependencies, or access external systems. It relies on static analysis of provided files and user interview responses.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Testing & Debugging.
Cannot execute project code, install dependencies, or access external systems. Relies on static analysis and user-provided evidence.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 4 days ago
- Free with an Agensi account