- Home
- Skills
- Testing & Debugging
- issue coverage checker
More screenshots
Works with the AI Agents you already use
issue coverage checker
Map GitHub issue acceptance criteria to pytest files to find testing gaps and generate coverage matrices.
Free
issue coverage checker
Example session with this skill installed
Is issue #42 covered by tests? Check the current pytest suite and give me a coverage matrix.
- Read your context and instructions
- Compiled the issue coverage checker
I have analyzed GitHub Issue #42 ("Implement Repository Normalization") and scanned the tests/ directory. 2/3 criteria are covered, 1 is not covered.
Issue Coverage Report: #42
| ID | Criterion | Status | Evidence | Explanation |
|---|---|---|---|---|
| AC-1 | Handle trailing slashes in URLs | Covered | tests/test_utils.py:test_norm_trailing_slash | Specifically asserts slash removal. |
| AC-2 | Convert SSH to HTTPS format | Covered | tests/test_utils.py:test_ssh_to_https | Logic verified in utility unit tests. |
| AC-3 | Validate repo owner exists | Not covered | None | No test found calling the GitHub API validator. |
Missing Tests
High Priority
- Behavior: Validation of repository owner existence via API.
- Why it matters: Prevents 404 errors during downstream sync operations.
- Suggested Type: Integration (mocked API).
- Related Criterion: AC-3
- Risk: High. Invalid owners will cause background job failures.
Next steps
- Implement a new test in
tests/test_validators.pyto handle the API validation logic for AC-3. - Update Issue #42 to include the
validation_rulesdiscovered during extraction. - Run
pytestto verify the new coverage.
Connects securely to your tools. The creator never sees your data.
About this skill
Manual verification of test coverage for GitHub issues is slow and prone to oversight. This skill automates the mapping of issue acceptance criteria to existing pytest suites, identifying exactly what is tested and what remains vulnerable.
What it does
- Extracts criteria from GitHub issue bodies and comments to build a structured requirement list.
- Maps test coverage by scanning repo metadata for pytest files that match specific functional requirements.
- Generates a coverage matrix showing which acceptance criteria are covered, partially covered, or missing.
- Recommends specific tests for any identified gaps, including behavior descriptions and risk assessments.
- Flags issue gaps where the original ticket lacks sufficient detail for validation.
How it works
- Analyze issue content to define functional requirements and number acceptance criteria (AC-1, AC-2, etc.).
- Search the repository using domain-specific keywords to locate relevant
test_*.pyfiles. - Audit test functions to verify if specific assertions or docstrings satisfy the extracted criteria.
- Produce the report including the coverage table and prioritized recommendations for new tests.
Frameworks & tools
Built for projects using pytest and GitHub. It requires access to the repository via the gh CLI, GitHub MCP server, or a local checkout.
Why this beats prompting it yourself
Generic prompts often hallucinate test paths or fail to link specific code assertions to business requirements. This skill enforces strict evidence-based mapping, ensuring every "covered" claim is backed by a real file path and test name.
Use cases
- Pre-merge audits to ensure a PR actually addresses all requirements in the linked ticket.
- QA gap analysis to identify untested edge cases in existing features.
- Issue grooming to detect when a ticket's acceptance criteria are too vague to be validated.
Known limitations
Only supports pytest suites. Coverage judgment is based on test names, docstrings, and assertions; it does not perform dynamic execution or line-level coverage analysis.
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.
Requires pytest. Cannot perform dynamic execution; relies on static analysis of test metadata. Only extracts criteria from provided issue text or comments.
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 23 days ago
- Free with an Agensi account
- Software
GitHub CLI
orGitHub MCP
pytest
Permissions
Allowed Hosts
File Scopes
Reads GitHub issue text (to extract acceptance criteria) and existing pytest test files (to judge coverage). Read-only — never writes to the repo or modifies tests.