13K skills · sorted by popularity
Audit code and configuration for security flaws, documenting attack paths, impact, evidence, and coverage gaps. Static review works without running the application; qualified runtime profiles add isolated reproduction and proposed repairs while keeping verification claims separate.
Find and fix bugs in websites, APIs, command-line tools, and background processes. Choose from three testing depths, verify fixes, and receive evidence of the changes plus a summary of readiness for release.
Check shell commands before they run and warn about destructive actions such as file deletion, database removal, and Git history changes. Users can approve ordinary warnings, while certain catastrophic command patterns are denied.
Enable warnings for destructive commands and restrict file edits to a chosen directory. It combines /careful and /freeze to help control work on live systems, while blocking certain catastrophic command patterns outright.
Investigate bugs in browser flows, APIs, command-line tools, background jobs, workers, and webhooks. Produce a structured report with reproduction steps and evidence or browser scores, without changing code to fix the issues.
Audit a developer product by trying its documentation and setup flow, measuring onboarding time, capturing errors, and reviewing command-line help. Produce an evidence-backed scorecard and compare results with earlier planning scores when available.
Measure web page loading times, rendering milestones, and resource sizes in a real browser. Save baseline measurements, compare results before and after code changes, and inspect historical trends to spot performance regressions.
Open web pages, follow navigation, and check form flows in a browser. Capture screenshots at different screen sizes, compare pages before and after actions, and collect console errors, the technical messages that can reveal page problems.
Test SwiftUI apps on a real iPhone or iPad by repeatedly capturing screens, analyzing them, taking actions, and verifying results. An embedded HTTP server enables interaction, with optional remote access through Tailscale.
Import cookies from a regular Chromium browser into a headless testing session, which runs without a visible window. Choose the browser profile and domains to prepare for testing pages that require sign-in.
Test websites and web apps in a real cloud browser, including local development servers. Check a specific user journey or several flows, then receive a quality score from 1 to 5 with evidence and identified issues.
Verify that existing work meets its acceptance conditions using the smallest sufficient set of checks. Reuse results that still match the repository state, report outcomes precisely, and stop once the evidence is complete without adding unrelated work.
Review web application security across user input, authentication, external services, dependencies, personal data, and AI features. Identify threats, apply protective controls, and verify changes with checks covering access permissions, sensitive information, and untrusted model output.
Develop and fix code by first writing a failing test, then making it pass and improving the implementation. The skill follows the project's testing tools and checks both the intended behavior and existing functionality.
Test browser interfaces through Chrome DevTools MCP, a connection that lets an agent inspect a live browser. Check screenshots, errors, network traffic, accessibility, and performance to diagnose problems and verify fixes.
Audit a test suite to identify redundant tests, empty checks, and tests tied to internal implementation. Consolidate or remove them with evidence while preserving useful checks that detect regressions, meaning previously fixed problems returning.
Verify Paperclip through real browser or command-line journeys across source checkouts, published npm installations, or existing hosted environments. Record the exact version, platform, starting data, observed behavior, and supporting evidence for each tested journey.
Audit a project's verification skill and maps of features and agent access against source code and live behavior. Correct documented procedures and references, while clearly identifying untested operations, access gaps, and missing prerequisites.
Review Paperclip interface changes using Storybook, a catalog of component examples, alongside production source and existing browser tests. Report rendering, interaction, visual comparison, and production evidence separately, making simulated behavior and untested areas clear.
Generate a project-local skill that launches and operates an app through real user workflows. It documents feature checks, captures evidence, and cleans up created instances, then proves the generated instructions work with one end-to-end run.
Coordinate bounded test runs for one Terminal-Bench task through Paperclip. Record evidence, diagnose failures, and manage approval for product fixes while keeping reruns in the same isolated working copy.
Select, inspect, validate, and report Paperclip evaluations for Runner protocol behavior or complete product workflows. Interpret results with evidence, source revisions, costs, and failure categories, and refresh reports from retained evidence without new provider calls.
Create acceptance criteria and a manual validation plan for feature changes. Cover successful flows, unusual inputs, failures, and performance limits, with observable outcomes and clear evidence requirements so reviewers can decide whether each criterion passes.
Coordinate Paperclip vulnerability response from confidential report review and private fixes to local testing, CVE identifier requests, advisory publication, and immediate security releases, with human assistance for reporter communication.