Loading...
Loading...
Found 2,138 Skills
Analyze gaps between requirements/features that should be tested and actual test coverage, identifying testing deficiencies and prioritizing test improvements
Whole-codebase vulnerability analysis leveraging 1M context window. Loads entire project source, runs deep security analysis in a single pass. Opus 4.6 found 500 zero-day vulnerabilities in pre-release testing — this skill weaponizes that capability.
Comprehensive n8n workflow testing including execution lifecycle, node connection patterns, data flow validation, and error handling strategies. Use when testing n8n workflow automation applications.
Artillery Config Generator - Auto-activating skill for Performance Testing. Triggers on: artillery config generator, artillery config generator Part of the Performance Testing skill category.
Kotlin language guardrails, patterns, and best practices for AI-assisted development. Use when working with Kotlin files (.kt, .kts), build.gradle.kts, or when the user mentions Kotlin. Provides null safety patterns, coroutine guidelines, data class conventions, and testing standards specific to this project's coding standards.
Design manual testing and exploratory testing plans, including test charters, heuristic methods, and session records. Default output is Markdown, Excel/CSV/JSON is available upon request. Use for manual testing.
Run single-file C# programs as scripts for quick experimentation, prototyping, and concept testing. Use when the user wants to write and execute a small C# program without creating a full project.
This skill covers designing and implementing security zones and conduits for industrial automation and control systems (IACS) per IEC 62443-3-2. It addresses zone partitioning based on risk assessment, assigning Security Level targets (SL-T), designing conduit security controls, implementing microsegmentation with industrial firewalls, and validating zone architecture through traffic analysis and penetration testing against the Purdue Reference Model.
Instrument Python LLM apps, build golden datasets, write eval-based tests, run them, and root-cause failures — covering the full eval-driven development cycle. Make sure to use this skill whenever a user is developing, testing, QA-ing, evaluating, or benchmarking a Python project that calls an LLM, even if they don't say "evals" explicitly. Use for making sure an AI app works correctly, catching regressions after prompt changes, debugging why an agent started behaving differently, or validating output quality before shipping.
OpenCode Multi-Agent Parallel Collaboration Configuration. Supports multiple agents working simultaneously to implement a pipeline development mode. Use when: (1) Need multiple agents to work in parallel (2) Need a master to schedule collaborative work among agents (3) Need to implement a standardized process of design → development → acceptance → testing (4) Need to configure OpenCode's multi-agent collaboration capability
Run isolated eval and grading calls using CC 2.1.81 --bare mode. Constructs claude -p --bare invocations for skill evaluation, trigger testing, and LLM grading without plugin/hook interference. Use when running eval pipelines, grading skill outputs, benchmarking prompt quality, or testing trigger accuracy in isolation.
Design and create a new hive task through guided conversation. Walks the user through problem definition, eval design, constraint specification, repo scaffolding, baseline testing with iteration, and upload. Use when user wants to create a new task, add a benchmark, or publish a challenge to the swarm.