Testing & Quality skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

myco:community-pr-review

Use this skill when reviewing or merging any community PR in unifi-mcp — even if the user just says "take a look at this PR" or "can we merge this." Covers the quality gate checklist (f-string logger ban, Ruff lint, validator registration, doc site update ordering), the fork-edit model for trusted contributors, org-fork push limitations, dual-subagent review, PR body standards, live smoke tests, mutating cycles, the unresponsive-first-time-contributor fork-edit exception, and the close-and-redirect pattern. Also covers community infrastructure setup (.github/ health files, issue routing, bug report template design) and evidence-first bug triage protocol. Apply this skill before approving any externally-authored PR, before running the merge command, when auditing merged PRs retroactively, and when setting up community engagement infrastructure.

523 repo starsObserved in 1 repos
Testing & Quality
GitHub

myco:live-smoke-testing

Activate this skill when running, interpreting, extending, or debugging the live hardware smoke test harness in `scripts/live_smoke.py`. Covers all aspects of manifest-driven live testing against real UniFi hardware: .env credential setup, tool classification tiers, --phase flag selection to bound blast radius, the human-in-the-loop confirmation gate for mutations, artifact interpretation in live-smoke-results/, adding new tools to the harness, and recognizing known API contract failure patterns that mock-based CI cannot catch. Apply this skill even if the user doesn't explicitly ask about the harness — activate whenever a PR requires live smoke evidence, a new tool category needs coverage, or an API contract mismatch is suspected. CRITICAL: Treat live smoke as a PRE-MERGE BLOCKING GATE when code changes API response parsing (new fields, filtering logic, payload normalization).

523 repo starsObserved in 1 repos
Testing & Quality
GitHub

review-mr

Review code changes in a PETSc GitLab merge request and report findings to stdout. Use when the user asks to "review this MR", "review MR <number>", "look at MR !N", or provides a merge_requests URL/IID, and wants the review printed (not posted as comments).

523 repo starsObserved in 1 repos
Testing & Quality
GitHub

review-mr-post

Review a PETSc GitLab merge request and post the findings back as inline DiffNote comments (with apply-able suggestion blocks where possible). Use when the user asks to "post review comments on MR <N>", "leave inline comments on the MR", or "review and post" — anything that should land on GitLab, not stdout.

523 repo starsObserved in 1 repos
Testing & Quality
GitHub

pr-cleaner-master

Maintainer's daily PR sweep tool. Batch-review all open PRs in the current repo, classify each into merge / fix-and-merge / request-changes / waiting / cached, and present a three-section table. Incremental by default: unchanged PRs since last sweep are folded away. Use when: "review PRs", "pr cleaner", "pr sweep", "pr triage", "daily PR review", "project maintainer PR management", sweeping open PRs as a project owner. Passing a PR number narrows the sweep to that PR. Do not use for: single-PR deep review or evaluating review comments on your own PR (use pr-eval), issue management (use issue-cleaner-master), or automated merging.

522 repo starsObserved in 2 repos
Testing & Quality
GitHub

verify-release

Pre-release verification — checks README, docs, roadmap, test coverage, examples, and runs the full test suite to catch regressions.

519 repo starsObserved in 1 repos
Testing & Quality
GitHub

Comprehensive Classification Model Evaluation and Visualization

Generates a comprehensive set of evaluation metrics and visualizations for classification models, including classification reports, confusion matrices, ROC curves (binary and multi-class One-vs-Rest), and density plots of predicted probabilities.

518 repo starsObserved in 3 repos
Testing & Quality
GitHub

PyTorch Tensor Shape Debugging

Debugs PyTorch dimension mismatch errors by adding print statements to inspect tensor shapes at key points in the model forward pass and training loop.

518 repo starsObserved in 3 repos
Testing & Quality
GitHub

LL(1) Grammar Verification

Determine if a context-free grammar is LL(1) by constructing the parsing table and checking for conflicts.

518 repo starsObserved in 2 repos
Testing & Quality
GitHub

Тестер и исправитель C-кода с оптимизацией под слабое CPU

Анализирует C-код (особенно FFmpeg/RKNN) на ошибки и баги, оптимизирует вычисления для однопроцессорных систем. Соблюдает строгие правила модификации: не удалять комментарии, не переименовывать идентификаторы, не добавлять новый функционал, возвращать полный код и объяснять правки отдельно.

518 repo starsObserved in 2 repos
Testing & Quality
GitHub