sql-review
Pre-merge SQL quality gate — lint 26 anti-patterns, grade readability/performance A-F, validate syntax, and scan for injection threats. Use before committing…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-27 00:15
Testing & quality
12,751 results
context-debugging
Use when an agent is failing, producing wrong output, ignoring instructions, hallucinating, or behaving unexpectedly — and the cause isn't an obvious code bug.…
context-eval
Evaluate whether a context engineering harness actually improves agent outcomes. Use when the user wants to measure, benchmark, compare, or validate any…
test-challenger
Challenge AI-generated (or any) unit tests to find false positives — tests that pass against wrong behavior. Use this skill whenever the user asks to review,…
gm-emit
EMIT phase. Pre-emit debug, write files, post-emit verify from disk. Any new unknown triggers immediate snake back to planning — restart chain.
diff-review-doc
Generate comprehensive, reviewer-ready code review documents from git diffs. Use this when the user provides code changes (git diff output, file changes, or…
testing-workflows-with-subagents
Use when creating or editing commands, orchestrator prompts, or workflow documentation before deployment - applies RED-GREEN-REFACTOR to test instruction…
external-gitcode-ascend-ascendc-operator-performance-eval
Under ascend-kernel's csrc/ops/<op>/test, maintain profiler performance cases containing only JSONL, collect using torch_npu.profiler (fixed warmup=5, active=5), and summarize the ASCEND_PROFILER_OUTPUT/op_statistic.csv…
external-gitcode-ascend-auto-bug-fixer
Use when encountering bugs, test failures, or error logs that need root cause analysis and fix generation
external-gitcode-ascend-auto-develop-test-gen
Developer test auto-completion skill - generate high-quality unit tests for functions and classes, analyze coverage blind spots and generate high-value supplementary tests to improve effective coverage.
external-gitcode-ascend-triton-operator-code-review
Statically review Triton operator code quality (Host + Device side), targeting Ascend NPU. Discover potential bugs, API misuse, and performance hazards. Focus only on static code analysis. Keywords: code review, code inspection, static analysis.
supercharge
Evidence-first, read-only engineering-health assessment for application, architecture, and platform repositories. Use it for recurring focused code,…
meraki-wireless-ops
Cisco Meraki wireless (read-only) — SSID configuration, RF profiles, Air Marshal, channel utilization, signal quality, client connectivity events via Cisco's…
fix-e2e-tests
Given a wp-calypso PR number, identify the failing E2E test(s) in that PR's CI run so they can be fixed. Use when asked to investigate or fix a failing E2E…
nuke-pilot
Use when the user wants quality work done but has not named which ceremony — "nuke pilot", "where do I start", "make this repo good", "help me plan the…
task-creator
SkillsBench task authoring — walk a contributor from idea to submission-ready task following CONTRIBUTING.md and the task-implementation rubric. Use when the…
musts
Use the `musts` CLI to validate that your changes are done. Run `musts validate` to get the validation todo list; for deterministic checks (cargo/*,…
check-boundary-conditions
Evaluate how logic handles edge cases and extreme inputs. Use when checking robustness, debugging failures, or testing boundaries like empty input, zero…
quality-assurance
Comprehensive quality assurance skill for validating and verifying project deliverables and educational content. This skill should be used when establishing…
test-scenarios
Generate test scenario coverage from a feature spec — happy paths, edge cases, error handling, accessibility, security, and performance — with a coverage…
bellingcat-conflict
Investigate armed conflicts, political violence, weapons, and munitions. Track protest events, military movements, explosive ordnance, and police records. Use…
playwright-testing
Plan, implement, and debug frontend tests: unit/integration/E2E/visual/a11y. Use for Playwright/Cypress/Vitest/Jest/RTL, flaky test triage, CI stabilization,…
alicloud-ai-multimodal-qwen-ocr
Use when OCR-specialized extraction is needed with Alibaba Cloud Model Studio Qwen OCR models (`qwen-vl-ocr`, `qwen-vl-ocr-latest`, and snapshots), including…
investigate-ci
Investigate a ClickHouse CI failure end-to-end from a PR or S3 report URL. Fetches the failed tests and their output, classifies each as flaky vs a real…