diagnosing-bugs
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
Structured diagnostic-then-fix workflow using GitNexus knowledge graph and Ariya-4 problem framing. Gathers symptoms, isolates root causes, formulates hypotheses, verifies via reproduction, and applies targeted fixes.
Turn an English description (or mermaid source) into a diagram triplet: the source, an editable .excalidraw file you can open (gstack)
Compares two related malware samples to surface what changed between variants using section-level hashing, import-set differences, and fuzzy similarity scoring. Activates for requests to diff two samples, compare malware variants, or measure similarity between two binaries for variant tracking.
Rapid single-turn direct implementation workflow for unambiguous, low-risk, single-file code changes and bug fixes with known root causes. Enforces pre-action checks and post-edit sanity verification.
Use when a component has a disabled state/variant, or when building a compound component that owns a disabled state — inherit/provide it via the shared disabled context so state flows from parent to sub-components.
Discord ops via the message tool (channel=discord).
Covers Discord bot development using Discord.js in JavaScript and Pycord in Python. Addresses gateway intents, slash commands, interactive components, rate limiting, and sharding.
Supports parallel agent work when two or more tasks can be handled independently. Applies to tasks that require neither shared state nor sequential execution.
Guide development of projected Android XR experiences with Jetpack Compose Glimmer. Covers Glimmer design principles, implementation workflows, and interaction models tailored to display glasses.
Analyzes bootkit and rootkit samples by identifying boot-process tampering (MBR/VBR/ UEFI), kernel-mode components, and stealth hooking techniques from static indicators. Activates for requests to analyze a bootkit or rootkit, examine MBR/UEFI tampering, or identify kernel-mode stealth components.
Strip designs to their essence by removing unnecessary complexity. Great design is simple, powerful, and clean.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name