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.Connects next-safe-action to forms using React Hook Form adapters or native HTML forms. Covers action hooks, optimistic form actions, error mapping, bound arguments, and uploads.
Builds local agents with a safe_browser tool that owns CDP and enforces a domain allowlist through Fetch interception. Lets Claude Agent SDK agents browse or scrape without raw browser, shell, or CDP access, and supports demonstrations of blocked navigation.
Apply one logical code change with mandatory impact mapping, git snapshot, verification, and automatic revert on failure. Load when the user asks for a safe edit, verified change, one change at a time with rollback, or codespine-style edit loop. Also triggers on "safe change", "edit with verification", "don't break the build", "revert if tests fail", or any non-trivial code edit where blast radius…
Diagnoses tracebacks, CUDA memory errors, checkpoint failures, shape mismatches, NaN losses, and other training failures. Keeps debugging fixes separate from research contributions and excludes speculative patching or broad refactoring.
Supports extraction, consolidation, ownership moves, and code cleanup. Requires verification around structural edits to establish that behavior remains intact.
Context-appropriate safety guardrails across three dynamic operational levels (Default, Strict, Relaxed). Enforces PII redaction, harmful content blocking, and specialized permissions for authorized security research.
Provides ElevenLabs text-to-speech with a user experience modeled on the macOS say command.
ElevenLabs text-to-speech with mac-style say UX.
Coordinates medium-to-large feature development through an orchestrator and worker subagents. Defines specifications, milestones, tasks, and validation criteria before parallel implementation, and supports resuming existing sagas.
Coordinate cross-service transactions and cross-aggregate workflows using saga patterns when two-phase commit is unavailable. Covers compensating actions for failed workflows and diagnosing stuck saga states or incomplete compensation steps.
Confirms saju birth information through an interview and uses the saju-fortune npm package for conversational interpretations. Covers romance, wealth, career, health, annual fortunes, and compatibility.
Prepares for salary negotiations through market-rate research and strategy development. Creates scripts for presenting counteroffers.
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