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.Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
Identify and exploit Prototype Pollution vulnerabilities in JavaScript/Node.js applications. This skill covers the progression from polluting Object.prototype to identifying functional gadgets (like child_process.spawn) to achieve Remote Code Execution (RCE).
Verify that work actually shipped and actually works in production before telling the user it does. Checks uncommitted/unpushed code, every CI job, whether the live deployment is the current commit, whether real pages serve real content, whether API endpoints behave, whether logging and persistence are genuinely wired, and whether analytics events actually arrive. Use this skill before any claim t…
Critically audit agent skills and remove content that is outdated, disproven, model-specific, or based on poorly cited sources. Load when improve-skills runs its per-skill cycle, when the user asks to prune skills, remove outdated techniques, check if skills are still valid, verify citations in skills, audit skill sources, or update skills for a new model release. Also triggers on "are these skill…
Execute commands and binaries on remote Windows systems utilizing PsExec and SMB/RPC mechanisms. This skill details the mechanics behind tools like Sysinternals PsExec, Impacket's psexec.py, and their role in lateral movement via hidden administrative shares.
Creates and operates clean Linux hosts using `pu` for builds, CI, screenshots, videos, and issue reproduction. Covers connections, remote commands, artifact transfers, host destruction, and no-egress failures.
Use only when the user explicitly invokes PUA debugging for a bounded problem-solving push.
Uses PUG-REST or PubChemPy to search compounds by name, CID, or SMILES. Retrieves chemical properties and bioactivity and performs similarity and substructure searches for cheminformatics.
Publishes one compiled AL application to an already provisioned BCInsider sandbox. Uses the public prerelease ALTool.
Turns scripts, CLIs, models, or services into callable hotlines by writing workers, declaring contracts, registering, submitting, approving, and verifying them. Also troubleshoots published hotlines that agents cannot call correctly.
Package and publish a skill to the skills.sh community registry, a public GitHub repo, or both. Load when the user asks to publish a skill, share a skill publicly, submit a skill to the registry, release a skill, or when universal-skill-creator offers publishing as a final step after creation. Also triggers on "push this skill to skills.sh", "make this skill public", "share this skill", or "contri…
Creates or updates test cases in Excel, Xray, and TestRail from approved canonical JSON. Attaches Excel files to parent Jira stories and updates statuses after test runs.
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